| 1. | Buroni, Giovanni; Bontempi, Gianluca; Determe, Karl: A tutorial on network-wide multi-horizon traffic forecasting with deep learning. In: CEUR Workshop Proceedings, 2841 , 2021, (Language of publication: en). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/322517, title = {A tutorial on network-wide multi-horizon traffic forecasting with deep learning}, author = {Giovanni Buroni and Gianluca Bontempi and Karl Determe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/322517/3/EasyChair-Preprint-4944.pdf}, year = {2021}, date = {2021-01-01}, journal = {CEUR Workshop Proceedings}, volume = {2841}, abstract = {Traffic flow forecasting is fundamental to today's Intelligent Transportation Systems (ITS). It involves the task of learning traffic complex dynamics in order to predict future conditions. This is particularly challenging when it comes to predict the traffic status for multiple horizons into the future and at the same time for the entire transportation network. In this context deep learning models have recently shown promising results. This models can inherently capture the non-linear space-temporal correlations (ST) in traffic by taking advantage of the huge volume of data available. In this study the authors present a LSTM encoder-decoder for multi-horizon traffic flow predictions. We adopted a direct approach in which the model simultaneously predict traffic conditions for the entire Belgian motorway transport network at each time step. The results clearly show the superiority of this model when compared with other deep learning models. In the workshop, conference attendees will learn how to process and visualize mobility data, obtain optimal features for traffic flow forecasting, build a LSTM encoder-decoder and perform predictions in an online manner.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } Traffic flow forecasting is fundamental to today's Intelligent Transportation Systems (ITS). It involves the task of learning traffic complex dynamics in order to predict future conditions. This is particularly challenging when it comes to predict the traffic status for multiple horizons into the future and at the same time for the entire transportation network. In this context deep learning models have recently shown promising results. This models can inherently capture the non-linear space-temporal correlations (ST) in traffic by taking advantage of the huge volume of data available. In this study the authors present a LSTM encoder-decoder for multi-horizon traffic flow predictions. We adopted a direct approach in which the model simultaneously predict traffic conditions for the entire Belgian motorway transport network at each time step. The results clearly show the superiority of this model when compared with other deep learning models. In the workshop, conference attendees will learn how to process and visualize mobility data, obtain optimal features for traffic flow forecasting, build a LSTM encoder-decoder and perform predictions in an online manner. |
| 2. | Bontempi, Gianluca; Chavarriaga, Ricardo; eD Canck, Hans; Girardi, Emanuela; Hoos, Holger H; Kilbane-Dawe, Iarla; Ball, Tonio; Nowe, Ann; Sousa, Jose; Bacciu, Davide; Aldinucci, Marco; eD Domenico, Manlio; Saffiotti, Alessandro; Maratea, Marco: The CLAIRE COVID-19 initiative: approach, experiences and recommendations. In: Ethics and information technology, 2021, (DOI: 10.1007/s10676-020-09567-7). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/321123, title = {The CLAIRE COVID-19 initiative: approach, experiences and recommendations}, author = {Gianluca Bontempi and Ricardo Chavarriaga and Hans eD Canck and Emanuela Girardi and Holger H Hoos and Iarla Kilbane-Dawe and Tonio Ball and Ann Nowe and Jose Sousa and Davide Bacciu and Marco Aldinucci and Manlio eD Domenico and Alessandro Saffiotti and Marco Maratea}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/321123/3/Bontempi2021_Article_TheCLAIRECOVID-19InitiativeApp-2.pdf}, year = {2021}, date = {2021-01-01}, journal = {Ethics and information technology}, abstract = {A volunteer effort by Artificial Intelligence (AI) researchers has shown it can deliver significant research outcomes rapidly to help tackle COVID-19. Within two months, CLAIRE's self-organising volunteers delivered the World's first comprehensive curated repository of COVID-19-related datasets useful for drug-repurposing, drafted review papers on the role CT/X-ray scan analysis and robotics could play, and progressed research in other areas. Given the pace required and nature of voluntary efforts, the teams faced a number of challenges. These offer insights in how better to prepare for future volunteer scientific efforts and large scale, data-dependent AI collaborations in general. We offer seven recommendations on how to best leverage such efforts and collaborations in the context of managing future crises.}, note = {DOI: 10.1007/s10676-020-09567-7}, keywords = {}, pubstate = {published}, tppubtype = {article} } A volunteer effort by Artificial Intelligence (AI) researchers has shown it can deliver significant research outcomes rapidly to help tackle COVID-19. Within two months, CLAIRE's self-organising volunteers delivered the World's first comprehensive curated repository of COVID-19-related datasets useful for drug-repurposing, drafted review papers on the role CT/X-ray scan analysis and robotics could play, and progressed research in other areas. Given the pace required and nature of voluntary efforts, the teams faced a number of challenges. These offer insights in how better to prepare for future volunteer scientific efforts and large scale, data-dependent AI collaborations in general. We offer seven recommendations on how to best leverage such efforts and collaborations in the context of managing future crises. |
| 3. | Bontempi, Gianluca: Statistical foundations of machine learning. 2021, (Language of publication: en). (Type: Book | Links | BibTeX) @book{info:hdl:2013/325210, title = {Statistical foundations of machine learning}, author = {Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/325210/3/syl.pdf}, year = {2021}, date = {2021-01-01}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {book} } |
| 4. | Guida, Sibilla Di; Han, The Anh T A H; Kirchsteiger, Georg; Lenaerts, Tom; Zisis, Ioannis: Repeated interaction and its impact on cooperation and surplus allocation---an experimental analysis. In: Games, 12 (1), 2021, (DOI: 10.3390/g12010025). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/321049, title = {Repeated interaction and its impact on cooperation and surplus allocation---an experimental analysis}, author = {Sibilla Di Guida and The Anh T A H Han and Georg Kirchsteiger and Tom Lenaerts and Ioannis Zisis}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/321049/1/doi_304693.pdf}, year = {2021}, date = {2021-01-01}, journal = {Games}, volume = {12}, number = {1}, abstract = {This paper investigates how the possibility of affecting group composition combined with the possibility of repeated interaction impacts cooperation within groups and surplus distribution. We developed and tested experimentally a Surplus Allocation Game where cooperation of four agents is needed to produce surplus, but only two have the power to allocate it among the group members. Three matching procedures (corresponding to three separate experimental treatments) were used to test the impact of the variables of interest. A total of 400 subjects participated in our research, which was computer-based and conducted in a laboratory. Our results show that allowing for repeated interaction with the same partners leads to a self-selection of agents into groups with different life spans, whose duration is correlated with the behavior of both distributors and receivers. While behavior at the group level is diverse for surplus allocation and amount of cooperation, aggregate behavior is instead similar when repeated interaction is allowed or not allowed. We developed a behavioral model that captures the dynamics observed in the experimental data and sheds light into the rationales that drive the agents' individual behavior, suggesting that the most generous distributors are those acting for fear of rejection, not for true generosity, while the groups lasting the longest are those composed by this type of distributors and ``undemanding'' receivers.}, note = {DOI: 10.3390/g12010025}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper investigates how the possibility of affecting group composition combined with the possibility of repeated interaction impacts cooperation within groups and surplus distribution. We developed and tested experimentally a Surplus Allocation Game where cooperation of four agents is needed to produce surplus, but only two have the power to allocate it among the group members. Three matching procedures (corresponding to three separate experimental treatments) were used to test the impact of the variables of interest. A total of 400 subjects participated in our research, which was computer-based and conducted in a laboratory. Our results show that allowing for repeated interaction with the same partners leads to a self-selection of agents into groups with different life spans, whose duration is correlated with the behavior of both distributors and receivers. While behavior at the group level is diverse for surplus allocation and amount of cooperation, aggregate behavior is instead similar when repeated interaction is allowed or not allowed. We developed a behavioral model that captures the dynamics observed in the experimental data and sheds light into the rationales that drive the agents' individual behavior, suggesting that the most generous distributors are those acting for fear of rejection, not for true generosity, while the groups lasting the longest are those composed by this type of distributors and ``undemanding'' receivers. |
| 5. | `e, Nathaniel Vincent Mon P; Lenaerts, Tom; d dos Pacheco, Jorge Manuel Santos J M S; Dingli, David: Multistage feedback-driven compartmental dynamics of hematopoiesis. In: iScience, 24 (4), 2021, (DOI: 10.1016/j.isci.2021.102326). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/322462, title = {Multistage feedback-driven compartmental dynamics of hematopoiesis}, author = {Nathaniel Vincent Mon P{`e}re and Tom Lenaerts and Jorge Manuel Santos J M d S dos Pacheco and David Dingli}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/322462/1/doi_306106.pdf}, year = {2021}, date = {2021-01-01}, journal = {iScience}, volume = {24}, number = {4}, abstract = {Human hematopoiesis is surprisingly resilient to disruptions, providing suitable responses to severe bleeding, long-lasting immune activation, and even bone marrow transplants. Still, many blood disorders exist which push the system past its natural plasticity, resulting in abnormalities in the circulating blood. While proper treatment of such diseases can benefit from understanding the underlying cell dynamics, these are non-trivial to predict due to the hematopoietic system's hierarchical nature and complex feedback networks. To characterize the dynamics following different types of perturbations, we investigate a model representing hematopoiesis as a sequence of compartments covering all maturation stages---from stem to mature cells---where feedback regulates cell production to ongoing necessities. We find that a stable response to perturbations requires the simultaneous adaptation of cell differentiation and self-renewal rates, and show that under conditions of continuous disruption---as found in chronic hemolytic states---compartment cell numbers evolve to novel stable states.}, note = {DOI: 10.1016/j.isci.2021.102326}, keywords = {}, pubstate = {published}, tppubtype = {article} } Human hematopoiesis is surprisingly resilient to disruptions, providing suitable responses to severe bleeding, long-lasting immune activation, and even bone marrow transplants. Still, many blood disorders exist which push the system past its natural plasticity, resulting in abnormalities in the circulating blood. While proper treatment of such diseases can benefit from understanding the underlying cell dynamics, these are non-trivial to predict due to the hematopoietic system's hierarchical nature and complex feedback networks. To characterize the dynamics following different types of perturbations, we investigate a model representing hematopoiesis as a sequence of compartments covering all maturation stages---from stem to mature cells---where feedback regulates cell production to ongoing necessities. We find that a stable response to perturbations requires the simultaneous adaptation of cell differentiation and self-renewal rates, and show that under conditions of continuous disruption---as found in chronic hemolytic states---compartment cell numbers evolve to novel stable states. |
| 6. | `e, Quentin Rivi; Xiao, Qiying; Gutsch, Annelie; Defrance, Matthieu; Webb, A A R; Verbruggen, Nathalie: Mg deficiency interacts with the circadian clock and phytochromes pathways in Arabidopsis. In: Annals of Applied Biology, 178 (2), pp. 387-399, 2021, (DOI: 10.1111/aab.12659). (Type: Journal Article | Links | BibTeX) @article{info:hdl:2013/322914, title = {Mg deficiency interacts with the circadian clock and phytochromes pathways in Arabidopsis}, author = {Quentin Rivi{`e}re and Qiying Xiao and Annelie Gutsch and Matthieu Defrance and A A R Webb and Nathalie Verbruggen}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/322914/3/MgDeficiencyInPlantsLightClock.pdf}, year = {2021}, date = {2021-01-01}, journal = {Annals of Applied Biology}, volume = {178}, number = {2}, pages = {387-399}, note = {DOI: 10.1111/aab.12659}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
| 7. | Ciortan, Madalina; Defrance, Matthieu: Contrastive self-supervised clustering of scRNA-seq data.. In: BMC bioinformatics, 22 (1), pp. 280, 2021, (DOI: 10.1186/s12859-021-04210-8). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/325214, title = {Contrastive self-supervised clustering of scRNA-seq data.}, author = {Madalina Ciortan and Matthieu Defrance}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/325214/1/doi_308858.pdf}, year = {2021}, date = {2021-01-01}, journal = {BMC bioinformatics}, volume = {22}, number = {1}, pages = {280}, abstract = {Single-cell RNA sequencing (scRNA-seq) has emerged has a main strategy to study transcriptional activity at the cellular level. Clustering analysis is routinely performed on scRNA-seq data to explore, recognize or discover underlying cell identities. The high dimensionality of scRNA-seq data and its significant sparsity accentuated by frequent dropout events, introducing false zero count observations, make the clustering analysis computationally challenging. Even though multiple scRNA-seq clustering techniques have been proposed, there is no consensus on the best performing approach. On a parallel research track, self-supervised contrastive learning recently achieved state-of-the-art results on images clustering and, subsequently, image classification.}, note = {DOI: 10.1186/s12859-021-04210-8}, keywords = {}, pubstate = {published}, tppubtype = {article} } Single-cell RNA sequencing (scRNA-seq) has emerged has a main strategy to study transcriptional activity at the cellular level. Clustering analysis is routinely performed on scRNA-seq data to explore, recognize or discover underlying cell identities. The high dimensionality of scRNA-seq data and its significant sparsity accentuated by frequent dropout events, introducing false zero count observations, make the clustering analysis computationally challenging. Even though multiple scRNA-seq clustering techniques have been proposed, there is no consensus on the best performing approach. On a parallel research track, self-supervised contrastive learning recently achieved state-of-the-art results on images clustering and, subsequently, image classification. |
| 8. | Pollaris, Arnaud; Bontempi, Gianluca: Latent Causation: An algorithm for pairs of correlated latent variables in Linear Non-Gaussian Structural Equation Modeling. 2020, (Conference: BNAIC/BENELEARN (19 & 20 November 2020: Leiden (online))). (Type: Miscellaneous | Abstract | Links | BibTeX) @misc{info:hdl:2013/314680, title = {Latent Causation: An algorithm for pairs of correlated latent variables in Linear Non-Gaussian Structural Equation Modeling}, author = {Arnaud Pollaris and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/314680/3/BNAICBENELEARN_2020_Final_paper.pdf}, year = {2020}, date = {2020-01-01}, abstract = {This paper addresses the problem of inferring causation in a pair of linearly correlated continuous latent variables. We first discuss the limitations of the Direction Dependance Analysis (DDA) approach and then introduce the Latent Causation (LC). Five variants (in terms of dependency statistic) of the LC algorithm are assessed with ROC curves, then we consider the case of a latent confounder (uniform or chi-square distributed). While the distribution and the correlations of the latent confounder influence the accuracy, experimental results show the robustness of the method using bootstrapped p-values. Implications and limits of the experimental results are then discussed together with future directions.}, note = {Conference: BNAIC/BENELEARN (19 & 20 November 2020: Leiden (online))}, keywords = {}, pubstate = {published}, tppubtype = {misc} } This paper addresses the problem of inferring causation in a pair of linearly correlated continuous latent variables. We first discuss the limitations of the Direction Dependance Analysis (DDA) approach and then introduce the Latent Causation (LC). Five variants (in terms of dependency statistic) of the LC algorithm are assessed with ROC curves, then we consider the case of a latent confounder (uniform or chi-square distributed). While the distribution and the correlations of the latent confounder influence the accuracy, experimental results show the robustness of the method using bootstrapped p-values. Implications and limits of the experimental results are then discussed together with future directions. |
| 9. | Simar, Cédric; Petieau, Mathieu; Cebolla, Ana Maria; Leroy, Axelle; Bontempi, Gianluca; Chéron, Guy: EEG-based brain-computer interface for alpha speed control of a small robot using the MUSE headband. In: 2020, (DOI: 10.1109/IJCNN48605.2020.9207486). (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{info:hdl:2013/315071, title = {EEG-based brain-computer interface for alpha speed control of a small robot using the MUSE headband}, author = {Cédric Simar and Mathieu Petieau and Ana Maria Cebolla and Axelle Leroy and Gianluca Bontempi and Guy Chéron}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/315071}, year = {2020}, date = {2020-01-01}, abstract = {Non-invasive BMI applications are increasingly used in different contexts ranging from industrial, clinical and gaming. After having tested the difference between a classical EEG recorder with electroconductive gel (ANT system) and the MUSE EEG headband, we studied the BCI performances of the later during the control of a small robot. We demonstrated that the participants were able to successfully control the robot using an online brain-computer interface based on the signal power in different frequency bands (delta, theta and alpha) characterizing the eyes-opened and relaxed eyes-closed states. Additionally, we performed a correlation analysis which demonstrated that the BCI commands were more related to a delta or theta power decrease for the determination of the classifier output probability and to the alpha power increase for the speed control of the robot.}, note = {DOI: 10.1109/IJCNN48605.2020.9207486}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Non-invasive BMI applications are increasingly used in different contexts ranging from industrial, clinical and gaming. After having tested the difference between a classical EEG recorder with electroconductive gel (ANT system) and the MUSE EEG headband, we studied the BCI performances of the later during the control of a small robot. We demonstrated that the participants were able to successfully control the robot using an online brain-computer interface based on the signal power in different frequency bands (delta, theta and alpha) characterizing the eyes-opened and relaxed eyes-closed states. Additionally, we performed a correlation analysis which demonstrated that the BCI commands were more related to a delta or theta power decrease for the determination of the classifier output probability and to the alpha power increase for the speed control of the robot. |
| 10. | Caro, Fabrizio De; Stefani, Jacopo De; Bontempi, Gianluca; Vaccaro, Alfredo A; Villacci, Domenico D: Robust Assessment of Short-Term Wind Power Forecasting Models on Multiple Time Horizons. In: Technology and Economics of Smart Grids and Sustainable Energy, 5 (1), 2020, (DOI: 10.1007/s40866-020-00090-8). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/314435, title = {Robust Assessment of Short-Term Wind Power Forecasting Models on Multiple Time Horizons}, author = {Fabrizio De Caro and Jacopo De Stefani and Gianluca Bontempi and Alfredo A Vaccaro and Domenico D Villacci}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/314435/1/doi_298079.pdf}, year = {2020}, date = {2020-01-01}, journal = {Technology and Economics of Smart Grids and Sustainable Energy}, volume = {5}, number = {1}, abstract = {The massive penetration of renewable power generation in modern power grids is an effective way to reduce the impact of energy production on global warming. Unfortunately, the wind power generation may affect the regular operation of electrical systems, due to the stochastic and intermittent nature of the wind. For this reason, reducing the uncertainty about the wind evolution, e.g. by using short-term wind power forecasting methodologies, is a priority for system operators and wind producers to implement low-carbon power grids. Unfortunately, though the complexity of this task implies the comparison of several alternative forecasting methodologies and dimensionality reduction techniques, a general and robust procedure of model assessment still lacks in literature. In this paper the authors propose a robust methodology, based on extensive statistical analysis and resampling routines, to supply the most effective wind power forecasting method by testing a vast ensemble of methodologies over multiple time-scales and on a real case study. Experimental results on real data collected in an Italian wind farm show the potential of ensemble approaches integrating both statistical and machine learning methods.}, note = {DOI: 10.1007/s40866-020-00090-8}, keywords = {}, pubstate = {published}, tppubtype = {article} } The massive penetration of renewable power generation in modern power grids is an effective way to reduce the impact of energy production on global warming. Unfortunately, the wind power generation may affect the regular operation of electrical systems, due to the stochastic and intermittent nature of the wind. For this reason, reducing the uncertainty about the wind evolution, e.g. by using short-term wind power forecasting methodologies, is a priority for system operators and wind producers to implement low-carbon power grids. Unfortunately, though the complexity of this task implies the comparison of several alternative forecasting methodologies and dimensionality reduction techniques, a general and robust procedure of model assessment still lacks in literature. In this paper the authors propose a robust methodology, based on extensive statistical analysis and resampling routines, to supply the most effective wind power forecasting method by testing a vast ensemble of methodologies over multiple time-scales and on a real case study. Experimental results on real data collected in an Italian wind farm show the potential of ensemble approaches integrating both statistical and machine learning methods. |
| 11. | Simar, Cédric; Cebolla, Ana Maria; "e, Ga; Petieau, Mathieu; Bontempi, Gianluca; Berthoz, Alain; Cheron, Guy: Hyperscanning EEG and Classification Based on Riemannian Geometry for Festive and Violent Mental State Discrimination. In: Frontiers in Neuroscience, 14 , 2020, (DOI: 10.3389/fnins.2020.588357). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/317394, title = {Hyperscanning EEG and Classification Based on Riemannian Geometry for Festive and Violent Mental State Discrimination}, author = {Cédric Simar and Ana Maria Cebolla and Ga{"e}lle Chartier and Mathieu Petieau and Gianluca Bontempi and Alain Berthoz and Guy Cheron}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/317394/3/pdf}, year = {2020}, date = {2020-01-01}, journal = {Frontiers in Neuroscience}, volume = {14}, abstract = {Interactions between two brains constitute the essence of social communication. Daily movements are commonly executed during social interactions and are determined by different mental states that may express different positive or negative behavioral intent. In this context, the effective recognition of festive or violent intent before the action execution remains crucial for survival. Here, we hypothesize that the EEG signals contain the distinctive features characterizing movement intent already expressed before movement execution and that such distinctive information can be identified by state-of-the-art classification algorithms based on Riemannian geometry. We demonstrated for the first time that a classifier based on covariance matrices and Riemannian geometry can effectively discriminate between neutral, festive, and violent mental states only on the basis of non-invasive EEG signals in both the actor and observer participants. These results pave the way for new electrophysiological discrimination of mental states based on non-invasive EEG recordings and cutting-edge machine learning techniques.}, note = {DOI: 10.3389/fnins.2020.588357}, keywords = {}, pubstate = {published}, tppubtype = {article} } Interactions between two brains constitute the essence of social communication. Daily movements are commonly executed during social interactions and are determined by different mental states that may express different positive or negative behavioral intent. In this context, the effective recognition of festive or violent intent before the action execution remains crucial for survival. Here, we hypothesize that the EEG signals contain the distinctive features characterizing movement intent already expressed before movement execution and that such distinctive information can be identified by state-of-the-art classification algorithms based on Riemannian geometry. We demonstrated for the first time that a classifier based on covariance matrices and Riemannian geometry can effectively discriminate between neutral, festive, and violent mental states only on the basis of non-invasive EEG signals in both the actor and observer participants. These results pave the way for new electrophysiological discrimination of mental states based on non-invasive EEG recordings and cutting-edge machine learning techniques. |
| 12. | Colaprico, Antonio; Olsen, Catharina; Bailey, Matthew; Odom, Gabriel G J; Terkelsen, Thilde; Silva, Tiago Chedraoui; Olsen, André Vidas; Cantini, Laura; Zinovyev, Andrey; Barillot, Emmanuel; Noushmehr, Houtan; Bertoli, Gloria; Castiglioni, Isabella; Cava, Claudia; Bontempi, Gianluca; Chen, Xi Steven; Papaleo, Elena: Interpreting pathways to discover cancer driver genes with Moonlight. In: Nature communications, 11 (1), 2020, (DOI: 10.1038/s41467-019-13803-0). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/301750, title = {Interpreting pathways to discover cancer driver genes with Moonlight}, author = {Antonio Colaprico and Catharina Olsen and Matthew Bailey and Gabriel G J Odom and Thilde Terkelsen and Tiago Chedraoui Silva and André Vidas Olsen and Laura Cantini and Andrey Zinovyev and Emmanuel Barillot and Houtan Noushmehr and Gloria Bertoli and Isabella Castiglioni and Claudia Cava and Gianluca Bontempi and Xi Steven Chen and Elena Papaleo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/301750/1/doi_285394.pdf}, year = {2020}, date = {2020-01-01}, journal = {Nature communications}, volume = {11}, number = {1}, abstract = {Cancer driver gene alterations influence cancer development, occurring in oncogenes, tumor suppressors, and dual role genes. Discovering dual role cancer genes is difficult because of their elusive context-dependent behavior. We define oncogenic mediators as genes controlling biological processes. With them, we classify cancer driver genes, unveiling their roles in cancer mechanisms. To this end, we present Moonlight, a tool that incorporates multiple -omics data to identify critical cancer driver genes. With Moonlight, we analyze 8000+ tumor samples from 18 cancer types, discovering 3310 oncogenic mediators, 151 having dual roles. By incorporating additional data (amplification, mutation, DNA methylation, chromatin accessibility), we reveal 1000+ cancer driver genes, corroborating known molecular mechanisms. Additionally, we confirm critical cancer driver genes by analysing cell-line datasets. We discover inactivation of tumor suppressors in intron regions and that tissue type and subtype indicate dual role status. These findings help explain tumor heterogeneity and could guide therapeutic decisions.}, note = {DOI: 10.1038/s41467-019-13803-0}, keywords = {}, pubstate = {published}, tppubtype = {article} } Cancer driver gene alterations influence cancer development, occurring in oncogenes, tumor suppressors, and dual role genes. Discovering dual role cancer genes is difficult because of their elusive context-dependent behavior. We define oncogenic mediators as genes controlling biological processes. With them, we classify cancer driver genes, unveiling their roles in cancer mechanisms. To this end, we present Moonlight, a tool that incorporates multiple -omics data to identify critical cancer driver genes. With Moonlight, we analyze 8000+ tumor samples from 18 cancer types, discovering 3310 oncogenic mediators, 151 having dual roles. By incorporating additional data (amplification, mutation, DNA methylation, chromatin accessibility), we reveal 1000+ cancer driver genes, corroborating known molecular mechanisms. Additionally, we confirm critical cancer driver genes by analysing cell-line datasets. We discover inactivation of tumor suppressors in intron regions and that tissue type and subtype indicate dual role status. These findings help explain tumor heterogeneity and could guide therapeutic decisions. |
| 13. | Duerinckx, Sarah; Jacquemin, Valérie; Drunat, Séverine; Vial, Yoann; Passemard, Sandrine; Perazzolo, Camille; Massart, Annick; Soblet, Julie; Racapé, Judith; Desmyter, Laurence; Badoer, Cindy; Papadimitriou, Sofia; "e, Yann-A; Lefort, Anne; Libert, Frédérick; Maertelaer, Viviane De; Rooman, Marianne; Costagliola, Sabine; Verloes, Alain; Lenaerts, Tom; Pirson, Isabelle; Abramowicz, Marc: Digenic inheritance of human primary microcephaly delineates centrosomal and non centrosomal pathways.. In: Human mutation, 41 (2), pp. 512-524, 2020, (DOI: 10.1002/humu.23948). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/296188, title = {Digenic inheritance of human primary microcephaly delineates centrosomal and non centrosomal pathways.}, author = {Sarah Duerinckx and Valérie Jacquemin and Séverine Drunat and Yoann Vial and Sandrine Passemard and Camille Perazzolo and Annick Massart and Julie Soblet and Judith Racapé and Laurence Desmyter and Cindy Badoer and Sofia Papadimitriou and Yann-A{"e}l Le Borgne and Anne Lefort and Frédérick Libert and Viviane De Maertelaer and Marianne Rooman and Sabine Costagliola and Alain Verloes and Tom Lenaerts and Isabelle Pirson and Marc Abramowicz}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/296188/4/Supp_Mat.pdf}, year = {2020}, date = {2020-01-01}, journal = {Human mutation}, volume = {41}, number = {2}, pages = {512-524}, abstract = {Primary Microcephaly (PM) is characterized by a small head since birth and is vastly heterogeneous both genetically and phenotypically. While most cases are monogenic, genetic interactions between Aspm and Wdr62 have recently been described in a mouse model of PM. Here, we used two complementary, holistic in vivo approaches: high throughput DNA sequencing of multiple PM genes in human PM patients, and genome-edited zebrafish modeling for digenic inheritance of PM. Exomes of PM patients showed a significant burden of variants in 75 PM genes, that persisted after removing monogenic causes of PM (e.g., biallelic pathogenic variants in CEP152). This observation was replicated in an independent cohort of PM patients, where a PM gene panel showed in addition that the burden was carried by six centrosomal genes. Allelic frequencies were consistent with digenic inheritance. In zebrafish, non-centrosomal gene casc5 -/- produced a severe PM phenotype, that was not modified by centrosomal genes aspm or wdr62 invalidation. A digenic, quadriallelic PM phenotype was produced by aspm and wdr62. Our observations provide strong evidence for digenic inheritance of human PM, involving centrosomal genes. Absence of genetic interaction between casc5 and aspm or wdr62 further delineates centrosomal and non-centrosomal pathways in PM. This article is protected by copyright. All rights reserved.}, note = {DOI: 10.1002/humu.23948}, keywords = {}, pubstate = {published}, tppubtype = {article} } Primary Microcephaly (PM) is characterized by a small head since birth and is vastly heterogeneous both genetically and phenotypically. While most cases are monogenic, genetic interactions between Aspm and Wdr62 have recently been described in a mouse model of PM. Here, we used two complementary, holistic in vivo approaches: high throughput DNA sequencing of multiple PM genes in human PM patients, and genome-edited zebrafish modeling for digenic inheritance of PM. Exomes of PM patients showed a significant burden of variants in 75 PM genes, that persisted after removing monogenic causes of PM (e.g., biallelic pathogenic variants in CEP152). This observation was replicated in an independent cohort of PM patients, where a PM gene panel showed in addition that the burden was carried by six centrosomal genes. Allelic frequencies were consistent with digenic inheritance. In zebrafish, non-centrosomal gene casc5 -/- produced a severe PM phenotype, that was not modified by centrosomal genes aspm or wdr62 invalidation. A digenic, quadriallelic PM phenotype was produced by aspm and wdr62. Our observations provide strong evidence for digenic inheritance of human PM, involving centrosomal genes. Absence of genetic interaction between casc5 and aspm or wdr62 further delineates centrosomal and non-centrosomal pathways in PM. This article is protected by copyright. All rights reserved. |
| 14. | Rocha, Luis Mateus; Singh, Vikramjit; Esch, Markus; Lenaerts, Tom; Liljeros, Fredrik; Thorson, Anna: Dynamic contact networks of patients and MRSA spread in hospitals. In: Scientific reports, 10 (1), 2020, (DOI: 10.1038/s41598-020-66270-9). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/308993, title = {Dynamic contact networks of patients and MRSA spread in hospitals}, author = {Luis Mateus Rocha and Vikramjit Singh and Markus Esch and Tom Lenaerts and Fredrik Liljeros and Anna Thorson}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/308993/1/doi_292637.pdf}, year = {2020}, date = {2020-01-01}, journal = {Scientific reports}, volume = {10}, number = {1}, abstract = {Methicillin-resistant Staphylococcus aureus (MRSA) is a difficult-to-treat infection. Increasing efforts have been taken to mitigate the epidemics and to avoid potential outbreaks in low endemic settings. Understanding the population dynamics of MRSA is essential to identify the causal mechanisms driving the epidemics and to generalise conclusions to different contexts. Previous studies neglected the temporal structure of contacts between patients and assumed homogeneous behaviour. We developed a high-resolution data-driven contact network model of interactions between 743,182 patients in 485 hospitals during 3,059 days to reproduce the exact contact sequences of the hospital population. Our model captures the exact spatial and temporal human contact behaviour and the dynamics of referrals within and between wards and hospitals at a large scale, revealing highly heterogeneous contact and mobility patterns of individual patients. A simulation exercise of epidemic spread shows that heterogeneous contacts cause the emergence of super-spreader patients, slower than exponential polynomial growth of the prevalence, and fast epidemic spread between wards and hospitals. In our simulated scenarios, screening upon hospital admittance is potentially more effective than reducing infection probability to reduce the final outbreak size. Our findings are useful to understand not only MRSA spread but also other hospital-acquired infections.}, note = {DOI: 10.1038/s41598-020-66270-9}, keywords = {}, pubstate = {published}, tppubtype = {article} } Methicillin-resistant Staphylococcus aureus (MRSA) is a difficult-to-treat infection. Increasing efforts have been taken to mitigate the epidemics and to avoid potential outbreaks in low endemic settings. Understanding the population dynamics of MRSA is essential to identify the causal mechanisms driving the epidemics and to generalise conclusions to different contexts. Previous studies neglected the temporal structure of contacts between patients and assumed homogeneous behaviour. We developed a high-resolution data-driven contact network model of interactions between 743,182 patients in 485 hospitals during 3,059 days to reproduce the exact contact sequences of the hospital population. Our model captures the exact spatial and temporal human contact behaviour and the dynamics of referrals within and between wards and hospitals at a large scale, revealing highly heterogeneous contact and mobility patterns of individual patients. A simulation exercise of epidemic spread shows that heterogeneous contacts cause the emergence of super-spreader patients, slower than exponential polynomial growth of the prevalence, and fast epidemic spread between wards and hospitals. In our simulated scenarios, screening upon hospital admittance is potentially more effective than reducing infection probability to reduce the final outbreak size. Our findings are useful to understand not only MRSA spread but also other hospital-acquired infections. |
| 15. | "e, Ma; Demetter, Pieter; Wind, Roland De; Galdon, Maria Gomez; Velde, Sylvie Vande; Lens, Gaspard; Craciun, Ligia; Deleruelle, Amélie; Larsimont, Denis; Lenaerts, Tom; Sclafani, Francesco; Deleporte, Amélie; Donckier, Vincent; Hendlisz, Alain; Vandeputte, Caroline: Infiltrative tumour growth pattern correlates with poor outcome in oesophageal cancer.. In: BMJ open gastroenterology, 7 (1), 2020, (DOI: 10.1136/bmjgast-2020-000431). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/312667, title = {Infiltrative tumour growth pattern correlates with poor outcome in oesophageal cancer.}, author = {Ma{"e}lle Anciaux and Pieter Demetter and Roland De Wind and Maria Gomez Galdon and Sylvie Vande Velde and Gaspard Lens and Ligia Craciun and Amélie Deleruelle and Denis Larsimont and Tom Lenaerts and Francesco Sclafani and Amélie Deleporte and Vincent Donckier and Alain Hendlisz and Caroline Vandeputte}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/312667/1/doi_296311.pdf}, year = {2020}, date = {2020-01-01}, journal = {BMJ open gastroenterology}, volume = {7}, number = {1}, abstract = {Oesophageal cancer (OEC) is an aggressive disease with a poor survival rate. Prognostic markers are thus urgently needed. Due to the demonstrated prognostic value of histopathological growth pattern (HGP) in other cancers, we performed a retrospective assessment of HGP in patients suffering from invasive OEC.}, note = {DOI: 10.1136/bmjgast-2020-000431}, keywords = {}, pubstate = {published}, tppubtype = {article} } Oesophageal cancer (OEC) is an aggressive disease with a poor survival rate. Prognostic markers are thus urgently needed. Due to the demonstrated prognostic value of histopathological growth pattern (HGP) in other cancers, we performed a retrospective assessment of HGP in patients suffering from invasive OEC. |
| 16. | 'c, Jelena Gruji; Lenaerts, Tom: Do people imitate when making decisions? Evidence from a spatial Prisoner's Dilemma experiment: Do people imitate when making decisions. In: Royal Society open science, 7 (7), 2020, (DOI: 10.1098/rsos.200618). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/313051, title = {Do people imitate when making decisions? Evidence from a spatial Prisoner's Dilemma experiment: Do people imitate when making decisions}, author = {Jelena Gruji{'c} and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/313051/3/rsos.200618.pdf}, year = {2020}, date = {2020-01-01}, journal = {Royal Society open science}, volume = {7}, number = {7}, abstract = {How do people decide which action to take? This question is best answered using Game Theory, which has proposed a series of decision-making mechanisms that people potentially use. In network simulations, wherein games are repeated and pay-off differences can be observed, those mechanisms often rely on imitation of successful behaviour. Surprisingly, little to no evidence has been provided about whether people actually imitate more successful opponents when altering their actions in that context. By comparing two experimental treatments wherein participants play the iterated Prisoner's Dilemma game in a lattice, we aim to answer whether more successful actions are imitated. While in the first treatment, participants have the possibility to use pay-off differences in making their decision, the second treatment hinders such imitation as no information about the gains is provided. If imitation of the more successful plays a role then there should be a difference in how players switch from cooperation to defection between both treatments. Although, cooperation and pay-off levels do not appear to be significantly different between both treatments, detailed analysis shows that there are behavioural differences: when confronted with a more successful co-player, the focal player will imitate her behaviour as the switching is related to the experienced pay-off inequality.}, note = {DOI: 10.1098/rsos.200618}, keywords = {}, pubstate = {published}, tppubtype = {article} } How do people decide which action to take? This question is best answered using Game Theory, which has proposed a series of decision-making mechanisms that people potentially use. In network simulations, wherein games are repeated and pay-off differences can be observed, those mechanisms often rely on imitation of successful behaviour. Surprisingly, little to no evidence has been provided about whether people actually imitate more successful opponents when altering their actions in that context. By comparing two experimental treatments wherein participants play the iterated Prisoner's Dilemma game in a lattice, we aim to answer whether more successful actions are imitated. While in the first treatment, participants have the possibility to use pay-off differences in making their decision, the second treatment hinders such imitation as no information about the gains is provided. If imitation of the more successful plays a role then there should be a difference in how players switch from cooperation to defection between both treatments. Although, cooperation and pay-off levels do not appear to be significantly different between both treatments, detailed analysis shows that there are behavioural differences: when confronted with a more successful co-player, the focal player will imitate her behaviour as the switching is related to the experienced pay-off inequality. |
| 17. | Domingos, Elias Fernández; 'c, Jelena Gruji; Burguillo, Juan J C; Kirchsteiger, Georg; Santos, Francisco C; Lenaerts, Tom: Timing Uncertainty in Collective Risk Dilemmas Encourages Group Reciprocation and Polarization. In: iScience, 23 (12), 2020, (DOI: 10.1016/j.isci.2020.101752). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/315240, title = {Timing Uncertainty in Collective Risk Dilemmas Encourages Group Reciprocation and Polarization}, author = {Elias Fernández Domingos and Jelena Gruji{'c} and Juan J C Burguillo and Georg Kirchsteiger and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/315240/1/doi_298884.pdf}, year = {2020}, date = {2020-01-01}, journal = {iScience}, volume = {23}, number = {12}, abstract = {Social dilemmas are often shaped by actions involving uncertain returns only achievable in the future, such as climate action or voluntary vaccination. In this context, uncertainty may produce non-trivial effects. Here, we assess experimentally --- through a collective risk dilemma --- the effect of timing uncertainty, i.e. how uncertainty about when a target needs to be reached affects the participants' behaviors. We show that timing uncertainty prompts not only early generosity but also polarized outcomes, where participants' total contributions are distributed unevenly. Furthermore, analyzing participants' behavior under timing uncertainty reveals an increase in reciprocal strategies. A data-driven game-theoretical model captures the self-organizing dynamics underpinning these behavioral patterns. Timing uncertainty thus casts a shadow on the future that leads participants to respond early, whereas reciprocal strategies appear to be important for group success. Yet, the same uncertainty also leads to inequity and polarization, requiring the inclusion of new incentives handling these societal issues.}, note = {DOI: 10.1016/j.isci.2020.101752}, keywords = {}, pubstate = {published}, tppubtype = {article} } Social dilemmas are often shaped by actions involving uncertain returns only achievable in the future, such as climate action or voluntary vaccination. In this context, uncertainty may produce non-trivial effects. Here, we assess experimentally --- through a collective risk dilemma --- the effect of timing uncertainty, i.e. how uncertainty about when a target needs to be reached affects the participants' behaviors. We show that timing uncertainty prompts not only early generosity but also polarized outcomes, where participants' total contributions are distributed unevenly. Furthermore, analyzing participants' behavior under timing uncertainty reveals an increase in reciprocal strategies. A data-driven game-theoretical model captures the self-organizing dynamics underpinning these behavioral patterns. Timing uncertainty thus casts a shadow on the future that leads participants to respond early, whereas reciprocal strategies appear to be important for group success. Yet, the same uncertainty also leads to inequity and polarization, requiring the inclusion of new incentives handling these societal issues. |
| 18. | Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann: How Expert Confidence Can Improve Collective Decision-Making in Contextual Multi-Armed Bandit Problems. In: Lecture notes in computer science, 12496 LNAI , pp. 125-138, 2020, (DOI: 10.1007/978-3-030-63007-2_10). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/316598, title = {How Expert Confidence Can Improve Collective Decision-Making in Contextual Multi-Armed Bandit Problems}, author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/316598/4/howexpertconfidence.pdf}, year = {2020}, date = {2020-01-01}, journal = {Lecture notes in computer science}, volume = {12496 LNAI}, pages = {125-138}, abstract = {In collective decision-making (CDM) a group of experts with a shared set of values and a common goal must combine their knowledge to make a collectively optimal decision. Whereas existing research on CDM primarily focuses on making binary decisions, we focus here on CDM applied to solving contextual multi-armed bandit (CMAB) problems, where the goal is to exploit contextual information to select the best arm among a set. To address the limiting assumptions of prior work, we introduce confidence estimates and propose a novel approach to deciding with expert advice which can take advantage of these estimates. We further show that, when confidence estimates are imperfect, the proposed approach is more robust than the classical confidence-weighted majority vote.}, note = {DOI: 10.1007/978-3-030-63007-2_10}, keywords = {}, pubstate = {published}, tppubtype = {article} } In collective decision-making (CDM) a group of experts with a shared set of values and a common goal must combine their knowledge to make a collectively optimal decision. Whereas existing research on CDM primarily focuses on making binary decisions, we focus here on CDM applied to solving contextual multi-armed bandit (CMAB) problems, where the goal is to exploit contextual information to select the best arm among a set. To address the limiting assumptions of prior work, we introduce confidence estimates and propose a novel approach to deciding with expert advice which can take advantage of these estimates. We further show that, when confidence estimates are imperfect, the proposed approach is more robust than the classical confidence-weighted majority vote. |
| 19. | Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann: Collective Decision-Making as a Contextual Multi-armed Bandit Problem. In: Lecture notes in computer science, 12496 LNAI , pp. 113-124, 2020, (DOI: 10.1007/978-3-030-63007-2_9). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/316605, title = {Collective Decision-Making as a Contextual Multi-armed Bandit Problem}, author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/316605/5/colascdm.pdf}, year = {2020}, date = {2020-01-01}, journal = {Lecture notes in computer science}, volume = {12496 LNAI}, pages = {113-124}, abstract = {Collective decision-making (CDM) processes -- wherein the knowledge of a group of individuals with a common goal must be combined to make optimal decisions -- can be formalized within the framework of the deciding with expert advice setting. Traditional approaches to tackle this problem focus on finding appropriate weights for the individuals in the group. In contrast, we propose here meta-CMAB, a meta approach that learns a mapping from expert advice to expected outcomes. In summary, our work reveals that, when trying to make the best choice in a problem with multiple alternatives, meta-CMAB assures that the collective knowledge of experts leads to the best outcome without the need for accurate confidence estimates.}, note = {DOI: 10.1007/978-3-030-63007-2_9}, keywords = {}, pubstate = {published}, tppubtype = {article} } Collective decision-making (CDM) processes -- wherein the knowledge of a group of individuals with a common goal must be combined to make optimal decisions -- can be formalized within the framework of the deciding with expert advice setting. Traditional approaches to tackle this problem focus on finding appropriate weights for the individuals in the group. In contrast, we propose here meta-CMAB, a meta approach that learns a mapping from expert advice to expected outcomes. In summary, our work reveals that, when trying to make the best choice in a problem with multiple alternatives, meta-CMAB assures that the collective knowledge of experts leads to the best outcome without the need for accurate confidence estimates. |
| 20. | Han, The Anh T A H; 'i, Lu; Santos, Francisco C; Lenaerts, Tom: To regulate or not: A social dynamics analysis of an idealised ai race. In: The journal of artificial intelligence research, 69 , pp. 881-921, 2020, (DOI: 10.1613/JAIR.1.12225). (Type: Journal Article | Abstract | Links | BibTeX) @article{info:hdl:2013/319033, title = {To regulate or not: A social dynamics analysis of an idealised ai race}, author = {The Anh T A H Han and Lu{'i}s Marcelo Pereira and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/319033/17/1907-12393.pdf}, year = {2020}, date = {2020-01-01}, journal = {The journal of artificial intelligence research}, volume = {69}, pages = {881-921}, abstract = {Rapid technological advancements in Artificial Intelligence (AI), as well as the growing deployment of intelligent technologies in new application domains, have generated serious anxiety and a fear of missing out among different stake-holders, fostering a racing narrative. Whether real or not, the belief in such a race for domain supremacy through AI, can make it real simply from its consequences, as put forward by the Thomas theorem. These consequences may be negative, as racing for technological supremacy creates a complex ecology of choices that could push stake-holders to underestimate or even ignore ethical and safety procedures. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements, contemplating the use of the precautionary principle in AI innovation and research. Yet, given the breadth and depth of AI and its advances, it is difficult to assess which technology needs regulation and when. As there is no easy access to data describing this alleged AI race, theoretical models are necessary to understand its potential dynamics, allowing for the identification of when procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which domain supremacy can be achieved plays a crucial role. When this can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that imposing regulations for all risk and timing conditions may not have the anticipated effect as only for specific conditions a dilemma arises between what is individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short-term situation, conditions can be identified that require the promotion of risk-taking as opposed to compliance with safety regulations in order to improve social welfare. These results remain robust both when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for applications of AI, a clear understanding of the time-scale of the race is thus required, as this may induce important non-trivial effects.}, note = {DOI: 10.1613/JAIR.1.12225}, keywords = {}, pubstate = {published}, tppubtype = {article} } Rapid technological advancements in Artificial Intelligence (AI), as well as the growing deployment of intelligent technologies in new application domains, have generated serious anxiety and a fear of missing out among different stake-holders, fostering a racing narrative. Whether real or not, the belief in such a race for domain supremacy through AI, can make it real simply from its consequences, as put forward by the Thomas theorem. These consequences may be negative, as racing for technological supremacy creates a complex ecology of choices that could push stake-holders to underestimate or even ignore ethical and safety procedures. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements, contemplating the use of the precautionary principle in AI innovation and research. Yet, given the breadth and depth of AI and its advances, it is difficult to assess which technology needs regulation and when. As there is no easy access to data describing this alleged AI race, theoretical models are necessary to understand its potential dynamics, allowing for the identification of when procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which domain supremacy can be achieved plays a crucial role. When this can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that imposing regulations for all risk and timing conditions may not have the anticipated effect as only for specific conditions a dilemma arises between what is individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short-term situation, conditions can be identified that require the promotion of risk-taking as opposed to compliance with safety regulations in order to improve social welfare. These results remain robust both when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for applications of AI, a clear understanding of the time-scale of the race is thus required, as this may induce important non-trivial effects. |
2020 |
Duerinckx, Sarah; Jacquemin, Valérie; Drunat, Séverine; Vial, Yoann; Passemard, Sandrine; Perazzolo, Camille; Massart, Annick; Soblet, Julie; Racapé, Judith; Desmyter, Laurence; Badoer, Cindy; Papadimitriou, Sofia; "e, Yann-A; Lefort, Anne; Libert, Frédérick; Maertelaer, Viviane De; Rooman, Marianne; Costagliola, Sabine; Verloes, Alain; Lenaerts, Tom; Pirson, Isabelle; Abramowicz, Marc Digenic inheritance of human primary microcephaly delineates centrosomal and non centrosomal pathways. Journal Article In: Human mutation, 41 (2), pp. 512-524, 2020, (DOI: 10.1002/humu.23948). @article{info:hdl:2013/296188, title = {Digenic inheritance of human primary microcephaly delineates centrosomal and non centrosomal pathways.}, author = {Sarah Duerinckx and Valérie Jacquemin and Séverine Drunat and Yoann Vial and Sandrine Passemard and Camille Perazzolo and Annick Massart and Julie Soblet and Judith Racapé and Laurence Desmyter and Cindy Badoer and Sofia Papadimitriou and Yann-A{"e}l Le Borgne and Anne Lefort and Frédérick Libert and Viviane De Maertelaer and Marianne Rooman and Sabine Costagliola and Alain Verloes and Tom Lenaerts and Isabelle Pirson and Marc Abramowicz}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/296188/4/Supp_Mat.pdf}, year = {2020}, date = {2020-01-01}, journal = {Human mutation}, volume = {41}, number = {2}, pages = {512-524}, abstract = {Primary Microcephaly (PM) is characterized by a small head since birth and is vastly heterogeneous both genetically and phenotypically. While most cases are monogenic, genetic interactions between Aspm and Wdr62 have recently been described in a mouse model of PM. Here, we used two complementary, holistic in vivo approaches: high throughput DNA sequencing of multiple PM genes in human PM patients, and genome-edited zebrafish modeling for digenic inheritance of PM. Exomes of PM patients showed a significant burden of variants in 75 PM genes, that persisted after removing monogenic causes of PM (e.g., biallelic pathogenic variants in CEP152). This observation was replicated in an independent cohort of PM patients, where a PM gene panel showed in addition that the burden was carried by six centrosomal genes. Allelic frequencies were consistent with digenic inheritance. In zebrafish, non-centrosomal gene casc5 -/- produced a severe PM phenotype, that was not modified by centrosomal genes aspm or wdr62 invalidation. A digenic, quadriallelic PM phenotype was produced by aspm and wdr62. Our observations provide strong evidence for digenic inheritance of human PM, involving centrosomal genes. Absence of genetic interaction between casc5 and aspm or wdr62 further delineates centrosomal and non-centrosomal pathways in PM. This article is protected by copyright. All rights reserved.}, note = {DOI: 10.1002/humu.23948}, keywords = {}, pubstate = {published}, tppubtype = {article} } Primary Microcephaly (PM) is characterized by a small head since birth and is vastly heterogeneous both genetically and phenotypically. While most cases are monogenic, genetic interactions between Aspm and Wdr62 have recently been described in a mouse model of PM. Here, we used two complementary, holistic in vivo approaches: high throughput DNA sequencing of multiple PM genes in human PM patients, and genome-edited zebrafish modeling for digenic inheritance of PM. Exomes of PM patients showed a significant burden of variants in 75 PM genes, that persisted after removing monogenic causes of PM (e.g., biallelic pathogenic variants in CEP152). This observation was replicated in an independent cohort of PM patients, where a PM gene panel showed in addition that the burden was carried by six centrosomal genes. Allelic frequencies were consistent with digenic inheritance. In zebrafish, non-centrosomal gene casc5 -/- produced a severe PM phenotype, that was not modified by centrosomal genes aspm or wdr62 invalidation. A digenic, quadriallelic PM phenotype was produced by aspm and wdr62. Our observations provide strong evidence for digenic inheritance of human PM, involving centrosomal genes. Absence of genetic interaction between casc5 and aspm or wdr62 further delineates centrosomal and non-centrosomal pathways in PM. This article is protected by copyright. All rights reserved. |
Simar, Cédric; Petieau, Mathieu; Cebolla, Ana Maria; Leroy, Axelle; Bontempi, Gianluca; Chéron, Guy EEG-based brain-computer interface for alpha speed control of a small robot using the MUSE headband Inproceedings In: 2020, (DOI: 10.1109/IJCNN48605.2020.9207486). @inproceedings{info:hdl:2013/315071, title = {EEG-based brain-computer interface for alpha speed control of a small robot using the MUSE headband}, author = {Cédric Simar and Mathieu Petieau and Ana Maria Cebolla and Axelle Leroy and Gianluca Bontempi and Guy Chéron}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/315071}, year = {2020}, date = {2020-01-01}, abstract = {Non-invasive BMI applications are increasingly used in different contexts ranging from industrial, clinical and gaming. After having tested the difference between a classical EEG recorder with electroconductive gel (ANT system) and the MUSE EEG headband, we studied the BCI performances of the later during the control of a small robot. We demonstrated that the participants were able to successfully control the robot using an online brain-computer interface based on the signal power in different frequency bands (delta, theta and alpha) characterizing the eyes-opened and relaxed eyes-closed states. Additionally, we performed a correlation analysis which demonstrated that the BCI commands were more related to a delta or theta power decrease for the determination of the classifier output probability and to the alpha power increase for the speed control of the robot.}, note = {DOI: 10.1109/IJCNN48605.2020.9207486}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Non-invasive BMI applications are increasingly used in different contexts ranging from industrial, clinical and gaming. After having tested the difference between a classical EEG recorder with electroconductive gel (ANT system) and the MUSE EEG headband, we studied the BCI performances of the later during the control of a small robot. We demonstrated that the participants were able to successfully control the robot using an online brain-computer interface based on the signal power in different frequency bands (delta, theta and alpha) characterizing the eyes-opened and relaxed eyes-closed states. Additionally, we performed a correlation analysis which demonstrated that the BCI commands were more related to a delta or theta power decrease for the determination of the classifier output probability and to the alpha power increase for the speed control of the robot. |
Pollaris, Arnaud; Bontempi, Gianluca Latent Causation: An algorithm for pairs of correlated latent variables in Linear Non-Gaussian Structural Equation Modeling Miscellaneous 2020, (Conference: BNAIC/BENELEARN (19 & 20 November 2020: Leiden (online))). @misc{info:hdl:2013/314680, title = {Latent Causation: An algorithm for pairs of correlated latent variables in Linear Non-Gaussian Structural Equation Modeling}, author = {Arnaud Pollaris and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/314680/3/BNAICBENELEARN_2020_Final_paper.pdf}, year = {2020}, date = {2020-01-01}, abstract = {This paper addresses the problem of inferring causation in a pair of linearly correlated continuous latent variables. We first discuss the limitations of the Direction Dependance Analysis (DDA) approach and then introduce the Latent Causation (LC). Five variants (in terms of dependency statistic) of the LC algorithm are assessed with ROC curves, then we consider the case of a latent confounder (uniform or chi-square distributed). While the distribution and the correlations of the latent confounder influence the accuracy, experimental results show the robustness of the method using bootstrapped p-values. Implications and limits of the experimental results are then discussed together with future directions.}, note = {Conference: BNAIC/BENELEARN (19 & 20 November 2020: Leiden (online))}, keywords = {}, pubstate = {published}, tppubtype = {misc} } This paper addresses the problem of inferring causation in a pair of linearly correlated continuous latent variables. We first discuss the limitations of the Direction Dependance Analysis (DDA) approach and then introduce the Latent Causation (LC). Five variants (in terms of dependency statistic) of the LC algorithm are assessed with ROC curves, then we consider the case of a latent confounder (uniform or chi-square distributed). While the distribution and the correlations of the latent confounder influence the accuracy, experimental results show the robustness of the method using bootstrapped p-values. Implications and limits of the experimental results are then discussed together with future directions. |
Colaprico, Antonio; Olsen, Catharina; Bailey, Matthew; Odom, Gabriel G J; Terkelsen, Thilde; Silva, Tiago Chedraoui; Olsen, André Vidas; Cantini, Laura; Zinovyev, Andrey; Barillot, Emmanuel; Noushmehr, Houtan; Bertoli, Gloria; Castiglioni, Isabella; Cava, Claudia; Bontempi, Gianluca; Chen, Xi Steven; Papaleo, Elena Interpreting pathways to discover cancer driver genes with Moonlight Journal Article In: Nature communications, 11 (1), 2020, (DOI: 10.1038/s41467-019-13803-0). @article{info:hdl:2013/301750, title = {Interpreting pathways to discover cancer driver genes with Moonlight}, author = {Antonio Colaprico and Catharina Olsen and Matthew Bailey and Gabriel G J Odom and Thilde Terkelsen and Tiago Chedraoui Silva and André Vidas Olsen and Laura Cantini and Andrey Zinovyev and Emmanuel Barillot and Houtan Noushmehr and Gloria Bertoli and Isabella Castiglioni and Claudia Cava and Gianluca Bontempi and Xi Steven Chen and Elena Papaleo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/301750/1/doi_285394.pdf}, year = {2020}, date = {2020-01-01}, journal = {Nature communications}, volume = {11}, number = {1}, abstract = {Cancer driver gene alterations influence cancer development, occurring in oncogenes, tumor suppressors, and dual role genes. Discovering dual role cancer genes is difficult because of their elusive context-dependent behavior. We define oncogenic mediators as genes controlling biological processes. With them, we classify cancer driver genes, unveiling their roles in cancer mechanisms. To this end, we present Moonlight, a tool that incorporates multiple -omics data to identify critical cancer driver genes. With Moonlight, we analyze 8000+ tumor samples from 18 cancer types, discovering 3310 oncogenic mediators, 151 having dual roles. By incorporating additional data (amplification, mutation, DNA methylation, chromatin accessibility), we reveal 1000+ cancer driver genes, corroborating known molecular mechanisms. Additionally, we confirm critical cancer driver genes by analysing cell-line datasets. We discover inactivation of tumor suppressors in intron regions and that tissue type and subtype indicate dual role status. These findings help explain tumor heterogeneity and could guide therapeutic decisions.}, note = {DOI: 10.1038/s41467-019-13803-0}, keywords = {}, pubstate = {published}, tppubtype = {article} } Cancer driver gene alterations influence cancer development, occurring in oncogenes, tumor suppressors, and dual role genes. Discovering dual role cancer genes is difficult because of their elusive context-dependent behavior. We define oncogenic mediators as genes controlling biological processes. With them, we classify cancer driver genes, unveiling their roles in cancer mechanisms. To this end, we present Moonlight, a tool that incorporates multiple -omics data to identify critical cancer driver genes. With Moonlight, we analyze 8000+ tumor samples from 18 cancer types, discovering 3310 oncogenic mediators, 151 having dual roles. By incorporating additional data (amplification, mutation, DNA methylation, chromatin accessibility), we reveal 1000+ cancer driver genes, corroborating known molecular mechanisms. Additionally, we confirm critical cancer driver genes by analysing cell-line datasets. We discover inactivation of tumor suppressors in intron regions and that tissue type and subtype indicate dual role status. These findings help explain tumor heterogeneity and could guide therapeutic decisions. |
Simar, Cédric; Cebolla, Ana Maria; "e, Ga; Petieau, Mathieu; Bontempi, Gianluca; Berthoz, Alain; Cheron, Guy Hyperscanning EEG and Classification Based on Riemannian Geometry for Festive and Violent Mental State Discrimination Journal Article In: Frontiers in Neuroscience, 14 , 2020, (DOI: 10.3389/fnins.2020.588357). @article{info:hdl:2013/317394, title = {Hyperscanning EEG and Classification Based on Riemannian Geometry for Festive and Violent Mental State Discrimination}, author = {Cédric Simar and Ana Maria Cebolla and Ga{"e}lle Chartier and Mathieu Petieau and Gianluca Bontempi and Alain Berthoz and Guy Cheron}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/317394/3/pdf}, year = {2020}, date = {2020-01-01}, journal = {Frontiers in Neuroscience}, volume = {14}, abstract = {Interactions between two brains constitute the essence of social communication. Daily movements are commonly executed during social interactions and are determined by different mental states that may express different positive or negative behavioral intent. In this context, the effective recognition of festive or violent intent before the action execution remains crucial for survival. Here, we hypothesize that the EEG signals contain the distinctive features characterizing movement intent already expressed before movement execution and that such distinctive information can be identified by state-of-the-art classification algorithms based on Riemannian geometry. We demonstrated for the first time that a classifier based on covariance matrices and Riemannian geometry can effectively discriminate between neutral, festive, and violent mental states only on the basis of non-invasive EEG signals in both the actor and observer participants. These results pave the way for new electrophysiological discrimination of mental states based on non-invasive EEG recordings and cutting-edge machine learning techniques.}, note = {DOI: 10.3389/fnins.2020.588357}, keywords = {}, pubstate = {published}, tppubtype = {article} } Interactions between two brains constitute the essence of social communication. Daily movements are commonly executed during social interactions and are determined by different mental states that may express different positive or negative behavioral intent. In this context, the effective recognition of festive or violent intent before the action execution remains crucial for survival. Here, we hypothesize that the EEG signals contain the distinctive features characterizing movement intent already expressed before movement execution and that such distinctive information can be identified by state-of-the-art classification algorithms based on Riemannian geometry. We demonstrated for the first time that a classifier based on covariance matrices and Riemannian geometry can effectively discriminate between neutral, festive, and violent mental states only on the basis of non-invasive EEG signals in both the actor and observer participants. These results pave the way for new electrophysiological discrimination of mental states based on non-invasive EEG recordings and cutting-edge machine learning techniques. |
Caro, Fabrizio De; Stefani, Jacopo De; Bontempi, Gianluca; Vaccaro, Alfredo A; Villacci, Domenico D Robust Assessment of Short-Term Wind Power Forecasting Models on Multiple Time Horizons Journal Article In: Technology and Economics of Smart Grids and Sustainable Energy, 5 (1), 2020, (DOI: 10.1007/s40866-020-00090-8). @article{info:hdl:2013/314435, title = {Robust Assessment of Short-Term Wind Power Forecasting Models on Multiple Time Horizons}, author = {Fabrizio De Caro and Jacopo De Stefani and Gianluca Bontempi and Alfredo A Vaccaro and Domenico D Villacci}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/314435/1/doi_298079.pdf}, year = {2020}, date = {2020-01-01}, journal = {Technology and Economics of Smart Grids and Sustainable Energy}, volume = {5}, number = {1}, abstract = {The massive penetration of renewable power generation in modern power grids is an effective way to reduce the impact of energy production on global warming. Unfortunately, the wind power generation may affect the regular operation of electrical systems, due to the stochastic and intermittent nature of the wind. For this reason, reducing the uncertainty about the wind evolution, e.g. by using short-term wind power forecasting methodologies, is a priority for system operators and wind producers to implement low-carbon power grids. Unfortunately, though the complexity of this task implies the comparison of several alternative forecasting methodologies and dimensionality reduction techniques, a general and robust procedure of model assessment still lacks in literature. In this paper the authors propose a robust methodology, based on extensive statistical analysis and resampling routines, to supply the most effective wind power forecasting method by testing a vast ensemble of methodologies over multiple time-scales and on a real case study. Experimental results on real data collected in an Italian wind farm show the potential of ensemble approaches integrating both statistical and machine learning methods.}, note = {DOI: 10.1007/s40866-020-00090-8}, keywords = {}, pubstate = {published}, tppubtype = {article} } The massive penetration of renewable power generation in modern power grids is an effective way to reduce the impact of energy production on global warming. Unfortunately, the wind power generation may affect the regular operation of electrical systems, due to the stochastic and intermittent nature of the wind. For this reason, reducing the uncertainty about the wind evolution, e.g. by using short-term wind power forecasting methodologies, is a priority for system operators and wind producers to implement low-carbon power grids. Unfortunately, though the complexity of this task implies the comparison of several alternative forecasting methodologies and dimensionality reduction techniques, a general and robust procedure of model assessment still lacks in literature. In this paper the authors propose a robust methodology, based on extensive statistical analysis and resampling routines, to supply the most effective wind power forecasting method by testing a vast ensemble of methodologies over multiple time-scales and on a real case study. Experimental results on real data collected in an Italian wind farm show the potential of ensemble approaches integrating both statistical and machine learning methods. |
Lipski, D; Foucart, Vincent; Dewispelaere, Remi; Caspers, Laure; Defrance, Matthieu; Bruyns, Catherine; Willermain, Francois Retinal endothelial cell phenotypic modifications during experimental autoimmune uveitis: A transcriptomic approach Journal Article In: BMC ophthalmology, 20 (1), 2020, (DOI: 10.1186/s12886-020-1333-5). @article{info:hdl:2013/305060, title = {Retinal endothelial cell phenotypic modifications during experimental autoimmune uveitis: A transcriptomic approach}, author = {D Lipski and Vincent Foucart and Remi Dewispelaere and Laure Caspers and Matthieu Defrance and Catherine Bruyns and Francois Willermain}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/305060/1/doi_288704.pdf}, year = {2020}, date = {2020-01-01}, journal = {BMC ophthalmology}, volume = {20}, number = {1}, abstract = {Background: Blood-retinal barrier cells are known to exhibit a massive phenotypic change during experimental autoimmune uveitis (EAU) development. In an attempt to investigate the mechanisms of blood-retinal barrier (BRB) breakdown at a global level, we studied the gene regulation of total retinal cells and retinal endothelial cells during non-infectious uveitis. Methods: Retinal endothelial cells were isolated by flow cytometry either in Tie2-GFP mice (CD31+ CD45- GFP+ cells), or in wild type C57BL/6 mice (CD31+ CD45- endoglin+ cells). EAU was induced in C57BL/6 mice by adoptive transfer of IRBP1-20-specific T cells. Total retinal cells and retinal endothelial cells from na"ive and EAU mice were sorted and their gene expression compared by RNA-Seq. Protein expression of selected genes was validated by immunofluorescence on retinal wholemounts and cryosections and by flow cytometry. Results: Retinal endothelial cell sorting in wild type C57BL/6 mice was validated by comparative transcriptome analysis with retinal endothelial cells sorted from Tie2-GFP mice, which express GFP under the control of the endothelial-specific receptor tyrosine kinase promoter Tie2. RNA-Seq analysis of total retinal cells mainly brought to light upregulation of genes involved in antigen presentation and T cell activation during EAU. Specific transcriptome analysis of retinal endothelial cells allowed us to identify 82 genes modulated in retinal endothelial cells during EAU development. Protein expression of 5 of those genes (serpina3n, lcn2, ackr1, lrg1 and lamc3) was validated at the level of inner BRB cells. Conclusion: Those data not only confirm the involvement of known pathogenic molecules but further provide a list of new candidate genes and pathways possibly implicated in inner BRB breakdown during non-infectious posterior uveitis.}, note = {DOI: 10.1186/s12886-020-1333-5}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Blood-retinal barrier cells are known to exhibit a massive phenotypic change during experimental autoimmune uveitis (EAU) development. In an attempt to investigate the mechanisms of blood-retinal barrier (BRB) breakdown at a global level, we studied the gene regulation of total retinal cells and retinal endothelial cells during non-infectious uveitis. Methods: Retinal endothelial cells were isolated by flow cytometry either in Tie2-GFP mice (CD31+ CD45- GFP+ cells), or in wild type C57BL/6 mice (CD31+ CD45- endoglin+ cells). EAU was induced in C57BL/6 mice by adoptive transfer of IRBP1-20-specific T cells. Total retinal cells and retinal endothelial cells from na"ive and EAU mice were sorted and their gene expression compared by RNA-Seq. Protein expression of selected genes was validated by immunofluorescence on retinal wholemounts and cryosections and by flow cytometry. Results: Retinal endothelial cell sorting in wild type C57BL/6 mice was validated by comparative transcriptome analysis with retinal endothelial cells sorted from Tie2-GFP mice, which express GFP under the control of the endothelial-specific receptor tyrosine kinase promoter Tie2. RNA-Seq analysis of total retinal cells mainly brought to light upregulation of genes involved in antigen presentation and T cell activation during EAU. Specific transcriptome analysis of retinal endothelial cells allowed us to identify 82 genes modulated in retinal endothelial cells during EAU development. Protein expression of 5 of those genes (serpina3n, lcn2, ackr1, lrg1 and lamc3) was validated at the level of inner BRB cells. Conclusion: Those data not only confirm the involvement of known pathogenic molecules but further provide a list of new candidate genes and pathways possibly implicated in inner BRB breakdown during non-infectious posterior uveitis. |
Lorenzo, Ramiro; Onizuka, Michiho; Defrance, Matthieu; Laurent, Patrick Combining single-cell RNA-sequencing with a molecular atlas unveils new markers for Caenorhabditis elegans neuron classes Journal Article In: Nucleic acids research, 2020, (DOI: 10.1093/nar/gkaa486). @article{info:hdl:2013/316017, title = {Combining single-cell RNA-sequencing with a molecular atlas unveils new markers for Caenorhabditis elegans neuron classes}, author = {Ramiro Lorenzo and Michiho Onizuka and Matthieu Defrance and Patrick Laurent}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/316017/1/doi_299661.pdf}, year = {2020}, date = {2020-01-01}, journal = {Nucleic acids research}, abstract = {Abstract Single-cell RNA-sequencing (scRNA-seq) of the Caenorhabditis elegans nervous system offers the unique opportunity to obtain a partial expression profile for each neuron within a known connectome. Building on recent scRNA-seq data and on a molecular atlas describing the expression pattern of ∼800 genes at the single cell resolution, we designed an iterative clustering analysis aiming to match each cell-cluster to the ∼100 anatomically defined neuron classes of C. elegans. This heuristic approach successfully assigned 97 of the 118 neuron classes to a cluster. Sixty two clusters were assigned to a single neuron class and 15 clusters grouped neuron classes sharing close molecular signatures. Pseudotime analysis revealed a maturation process occurring in some neurons (e.g. PDA) during the L2 stage. Based on the molecular profiles of all identified neurons, we predicted cell fate regulators and experimentally validated unc-86 for the normal differentiation of RMG neurons. Furthermore, we observed that different classes of genes functionally diversify sensory neurons, interneurons and motorneurons. Finally, we designed 15 new neuron class-specific promoters validated in vivo. Amongst them, 10 represent the only specific promoter reported to this day, expanding the list of neurons amenable to genetic manipulations.}, note = {DOI: 10.1093/nar/gkaa486}, keywords = {}, pubstate = {published}, tppubtype = {article} } Abstract Single-cell RNA-sequencing (scRNA-seq) of the Caenorhabditis elegans nervous system offers the unique opportunity to obtain a partial expression profile for each neuron within a known connectome. Building on recent scRNA-seq data and on a molecular atlas describing the expression pattern of ∼800 genes at the single cell resolution, we designed an iterative clustering analysis aiming to match each cell-cluster to the ∼100 anatomically defined neuron classes of C. elegans. This heuristic approach successfully assigned 97 of the 118 neuron classes to a cluster. Sixty two clusters were assigned to a single neuron class and 15 clusters grouped neuron classes sharing close molecular signatures. Pseudotime analysis revealed a maturation process occurring in some neurons (e.g. PDA) during the L2 stage. Based on the molecular profiles of all identified neurons, we predicted cell fate regulators and experimentally validated unc-86 for the normal differentiation of RMG neurons. Furthermore, we observed that different classes of genes functionally diversify sensory neurons, interneurons and motorneurons. Finally, we designed 15 new neuron class-specific promoters validated in vivo. Amongst them, 10 represent the only specific promoter reported to this day, expanding the list of neurons amenable to genetic manipulations. |
Han, The Anh T A H; 'i, Lu; Santos, Francisco C; Lenaerts, Tom To regulate or not: A social dynamics analysis of an idealised ai race Journal Article In: The journal of artificial intelligence research, 69 , pp. 881-921, 2020, (DOI: 10.1613/JAIR.1.12225). @article{info:hdl:2013/319033, title = {To regulate or not: A social dynamics analysis of an idealised ai race}, author = {The Anh T A H Han and Lu{'i}s Marcelo Pereira and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/319033/17/1907-12393.pdf}, year = {2020}, date = {2020-01-01}, journal = {The journal of artificial intelligence research}, volume = {69}, pages = {881-921}, abstract = {Rapid technological advancements in Artificial Intelligence (AI), as well as the growing deployment of intelligent technologies in new application domains, have generated serious anxiety and a fear of missing out among different stake-holders, fostering a racing narrative. Whether real or not, the belief in such a race for domain supremacy through AI, can make it real simply from its consequences, as put forward by the Thomas theorem. These consequences may be negative, as racing for technological supremacy creates a complex ecology of choices that could push stake-holders to underestimate or even ignore ethical and safety procedures. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements, contemplating the use of the precautionary principle in AI innovation and research. Yet, given the breadth and depth of AI and its advances, it is difficult to assess which technology needs regulation and when. As there is no easy access to data describing this alleged AI race, theoretical models are necessary to understand its potential dynamics, allowing for the identification of when procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which domain supremacy can be achieved plays a crucial role. When this can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that imposing regulations for all risk and timing conditions may not have the anticipated effect as only for specific conditions a dilemma arises between what is individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short-term situation, conditions can be identified that require the promotion of risk-taking as opposed to compliance with safety regulations in order to improve social welfare. These results remain robust both when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for applications of AI, a clear understanding of the time-scale of the race is thus required, as this may induce important non-trivial effects.}, note = {DOI: 10.1613/JAIR.1.12225}, keywords = {}, pubstate = {published}, tppubtype = {article} } Rapid technological advancements in Artificial Intelligence (AI), as well as the growing deployment of intelligent technologies in new application domains, have generated serious anxiety and a fear of missing out among different stake-holders, fostering a racing narrative. Whether real or not, the belief in such a race for domain supremacy through AI, can make it real simply from its consequences, as put forward by the Thomas theorem. These consequences may be negative, as racing for technological supremacy creates a complex ecology of choices that could push stake-holders to underestimate or even ignore ethical and safety procedures. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements, contemplating the use of the precautionary principle in AI innovation and research. Yet, given the breadth and depth of AI and its advances, it is difficult to assess which technology needs regulation and when. As there is no easy access to data describing this alleged AI race, theoretical models are necessary to understand its potential dynamics, allowing for the identification of when procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which domain supremacy can be achieved plays a crucial role. When this can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that imposing regulations for all risk and timing conditions may not have the anticipated effect as only for specific conditions a dilemma arises between what is individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short-term situation, conditions can be identified that require the promotion of risk-taking as opposed to compliance with safety regulations in order to improve social welfare. These results remain robust both when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for applications of AI, a clear understanding of the time-scale of the race is thus required, as this may induce important non-trivial effects. |
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann Collective Decision-Making as a Contextual Multi-armed Bandit Problem Journal Article In: Lecture notes in computer science, 12496 LNAI , pp. 113-124, 2020, (DOI: 10.1007/978-3-030-63007-2_9). @article{info:hdl:2013/316605, title = {Collective Decision-Making as a Contextual Multi-armed Bandit Problem}, author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/316605/5/colascdm.pdf}, year = {2020}, date = {2020-01-01}, journal = {Lecture notes in computer science}, volume = {12496 LNAI}, pages = {113-124}, abstract = {Collective decision-making (CDM) processes -- wherein the knowledge of a group of individuals with a common goal must be combined to make optimal decisions -- can be formalized within the framework of the deciding with expert advice setting. Traditional approaches to tackle this problem focus on finding appropriate weights for the individuals in the group. In contrast, we propose here meta-CMAB, a meta approach that learns a mapping from expert advice to expected outcomes. In summary, our work reveals that, when trying to make the best choice in a problem with multiple alternatives, meta-CMAB assures that the collective knowledge of experts leads to the best outcome without the need for accurate confidence estimates.}, note = {DOI: 10.1007/978-3-030-63007-2_9}, keywords = {}, pubstate = {published}, tppubtype = {article} } Collective decision-making (CDM) processes -- wherein the knowledge of a group of individuals with a common goal must be combined to make optimal decisions -- can be formalized within the framework of the deciding with expert advice setting. Traditional approaches to tackle this problem focus on finding appropriate weights for the individuals in the group. In contrast, we propose here meta-CMAB, a meta approach that learns a mapping from expert advice to expected outcomes. In summary, our work reveals that, when trying to make the best choice in a problem with multiple alternatives, meta-CMAB assures that the collective knowledge of experts leads to the best outcome without the need for accurate confidence estimates. |
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann How Expert Confidence Can Improve Collective Decision-Making in Contextual Multi-Armed Bandit Problems Journal Article In: Lecture notes in computer science, 12496 LNAI , pp. 125-138, 2020, (DOI: 10.1007/978-3-030-63007-2_10). @article{info:hdl:2013/316598, title = {How Expert Confidence Can Improve Collective Decision-Making in Contextual Multi-Armed Bandit Problems}, author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/316598/4/howexpertconfidence.pdf}, year = {2020}, date = {2020-01-01}, journal = {Lecture notes in computer science}, volume = {12496 LNAI}, pages = {125-138}, abstract = {In collective decision-making (CDM) a group of experts with a shared set of values and a common goal must combine their knowledge to make a collectively optimal decision. Whereas existing research on CDM primarily focuses on making binary decisions, we focus here on CDM applied to solving contextual multi-armed bandit (CMAB) problems, where the goal is to exploit contextual information to select the best arm among a set. To address the limiting assumptions of prior work, we introduce confidence estimates and propose a novel approach to deciding with expert advice which can take advantage of these estimates. We further show that, when confidence estimates are imperfect, the proposed approach is more robust than the classical confidence-weighted majority vote.}, note = {DOI: 10.1007/978-3-030-63007-2_10}, keywords = {}, pubstate = {published}, tppubtype = {article} } In collective decision-making (CDM) a group of experts with a shared set of values and a common goal must combine their knowledge to make a collectively optimal decision. Whereas existing research on CDM primarily focuses on making binary decisions, we focus here on CDM applied to solving contextual multi-armed bandit (CMAB) problems, where the goal is to exploit contextual information to select the best arm among a set. To address the limiting assumptions of prior work, we introduce confidence estimates and propose a novel approach to deciding with expert advice which can take advantage of these estimates. We further show that, when confidence estimates are imperfect, the proposed approach is more robust than the classical confidence-weighted majority vote. |
Domingos, Elias Fernández; 'c, Jelena Gruji; Burguillo, Juan J C; Kirchsteiger, Georg; Santos, Francisco C; Lenaerts, Tom Timing Uncertainty in Collective Risk Dilemmas Encourages Group Reciprocation and Polarization Journal Article In: iScience, 23 (12), 2020, (DOI: 10.1016/j.isci.2020.101752). @article{info:hdl:2013/315240, title = {Timing Uncertainty in Collective Risk Dilemmas Encourages Group Reciprocation and Polarization}, author = {Elias Fernández Domingos and Jelena Gruji{'c} and Juan J C Burguillo and Georg Kirchsteiger and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/315240/1/doi_298884.pdf}, year = {2020}, date = {2020-01-01}, journal = {iScience}, volume = {23}, number = {12}, abstract = {Social dilemmas are often shaped by actions involving uncertain returns only achievable in the future, such as climate action or voluntary vaccination. In this context, uncertainty may produce non-trivial effects. Here, we assess experimentally --- through a collective risk dilemma --- the effect of timing uncertainty, i.e. how uncertainty about when a target needs to be reached affects the participants' behaviors. We show that timing uncertainty prompts not only early generosity but also polarized outcomes, where participants' total contributions are distributed unevenly. Furthermore, analyzing participants' behavior under timing uncertainty reveals an increase in reciprocal strategies. A data-driven game-theoretical model captures the self-organizing dynamics underpinning these behavioral patterns. Timing uncertainty thus casts a shadow on the future that leads participants to respond early, whereas reciprocal strategies appear to be important for group success. Yet, the same uncertainty also leads to inequity and polarization, requiring the inclusion of new incentives handling these societal issues.}, note = {DOI: 10.1016/j.isci.2020.101752}, keywords = {}, pubstate = {published}, tppubtype = {article} } Social dilemmas are often shaped by actions involving uncertain returns only achievable in the future, such as climate action or voluntary vaccination. In this context, uncertainty may produce non-trivial effects. Here, we assess experimentally --- through a collective risk dilemma --- the effect of timing uncertainty, i.e. how uncertainty about when a target needs to be reached affects the participants' behaviors. We show that timing uncertainty prompts not only early generosity but also polarized outcomes, where participants' total contributions are distributed unevenly. Furthermore, analyzing participants' behavior under timing uncertainty reveals an increase in reciprocal strategies. A data-driven game-theoretical model captures the self-organizing dynamics underpinning these behavioral patterns. Timing uncertainty thus casts a shadow on the future that leads participants to respond early, whereas reciprocal strategies appear to be important for group success. Yet, the same uncertainty also leads to inequity and polarization, requiring the inclusion of new incentives handling these societal issues. |
'c, Jelena Gruji; Lenaerts, Tom Do people imitate when making decisions? Evidence from a spatial Prisoner's Dilemma experiment: Do people imitate when making decisions Journal Article In: Royal Society open science, 7 (7), 2020, (DOI: 10.1098/rsos.200618). @article{info:hdl:2013/313051, title = {Do people imitate when making decisions? Evidence from a spatial Prisoner's Dilemma experiment: Do people imitate when making decisions}, author = {Jelena Gruji{'c} and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/313051/3/rsos.200618.pdf}, year = {2020}, date = {2020-01-01}, journal = {Royal Society open science}, volume = {7}, number = {7}, abstract = {How do people decide which action to take? This question is best answered using Game Theory, which has proposed a series of decision-making mechanisms that people potentially use. In network simulations, wherein games are repeated and pay-off differences can be observed, those mechanisms often rely on imitation of successful behaviour. Surprisingly, little to no evidence has been provided about whether people actually imitate more successful opponents when altering their actions in that context. By comparing two experimental treatments wherein participants play the iterated Prisoner's Dilemma game in a lattice, we aim to answer whether more successful actions are imitated. While in the first treatment, participants have the possibility to use pay-off differences in making their decision, the second treatment hinders such imitation as no information about the gains is provided. If imitation of the more successful plays a role then there should be a difference in how players switch from cooperation to defection between both treatments. Although, cooperation and pay-off levels do not appear to be significantly different between both treatments, detailed analysis shows that there are behavioural differences: when confronted with a more successful co-player, the focal player will imitate her behaviour as the switching is related to the experienced pay-off inequality.}, note = {DOI: 10.1098/rsos.200618}, keywords = {}, pubstate = {published}, tppubtype = {article} } How do people decide which action to take? This question is best answered using Game Theory, which has proposed a series of decision-making mechanisms that people potentially use. In network simulations, wherein games are repeated and pay-off differences can be observed, those mechanisms often rely on imitation of successful behaviour. Surprisingly, little to no evidence has been provided about whether people actually imitate more successful opponents when altering their actions in that context. By comparing two experimental treatments wherein participants play the iterated Prisoner's Dilemma game in a lattice, we aim to answer whether more successful actions are imitated. While in the first treatment, participants have the possibility to use pay-off differences in making their decision, the second treatment hinders such imitation as no information about the gains is provided. If imitation of the more successful plays a role then there should be a difference in how players switch from cooperation to defection between both treatments. Although, cooperation and pay-off levels do not appear to be significantly different between both treatments, detailed analysis shows that there are behavioural differences: when confronted with a more successful co-player, the focal player will imitate her behaviour as the switching is related to the experienced pay-off inequality. |
"e, Ma; Demetter, Pieter; Wind, Roland De; Galdon, Maria Gomez; Velde, Sylvie Vande; Lens, Gaspard; Craciun, Ligia; Deleruelle, Amélie; Larsimont, Denis; Lenaerts, Tom; Sclafani, Francesco; Deleporte, Amélie; Donckier, Vincent; Hendlisz, Alain; Vandeputte, Caroline Infiltrative tumour growth pattern correlates with poor outcome in oesophageal cancer. Journal Article In: BMJ open gastroenterology, 7 (1), 2020, (DOI: 10.1136/bmjgast-2020-000431). @article{info:hdl:2013/312667, title = {Infiltrative tumour growth pattern correlates with poor outcome in oesophageal cancer.}, author = {Ma{"e}lle Anciaux and Pieter Demetter and Roland De Wind and Maria Gomez Galdon and Sylvie Vande Velde and Gaspard Lens and Ligia Craciun and Amélie Deleruelle and Denis Larsimont and Tom Lenaerts and Francesco Sclafani and Amélie Deleporte and Vincent Donckier and Alain Hendlisz and Caroline Vandeputte}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/312667/1/doi_296311.pdf}, year = {2020}, date = {2020-01-01}, journal = {BMJ open gastroenterology}, volume = {7}, number = {1}, abstract = {Oesophageal cancer (OEC) is an aggressive disease with a poor survival rate. Prognostic markers are thus urgently needed. Due to the demonstrated prognostic value of histopathological growth pattern (HGP) in other cancers, we performed a retrospective assessment of HGP in patients suffering from invasive OEC.}, note = {DOI: 10.1136/bmjgast-2020-000431}, keywords = {}, pubstate = {published}, tppubtype = {article} } Oesophageal cancer (OEC) is an aggressive disease with a poor survival rate. Prognostic markers are thus urgently needed. Due to the demonstrated prognostic value of histopathological growth pattern (HGP) in other cancers, we performed a retrospective assessment of HGP in patients suffering from invasive OEC. |
Rocha, Luis Mateus; Singh, Vikramjit; Esch, Markus; Lenaerts, Tom; Liljeros, Fredrik; Thorson, Anna Dynamic contact networks of patients and MRSA spread in hospitals Journal Article In: Scientific reports, 10 (1), 2020, (DOI: 10.1038/s41598-020-66270-9). @article{info:hdl:2013/308993, title = {Dynamic contact networks of patients and MRSA spread in hospitals}, author = {Luis Mateus Rocha and Vikramjit Singh and Markus Esch and Tom Lenaerts and Fredrik Liljeros and Anna Thorson}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/308993/1/doi_292637.pdf}, year = {2020}, date = {2020-01-01}, journal = {Scientific reports}, volume = {10}, number = {1}, abstract = {Methicillin-resistant Staphylococcus aureus (MRSA) is a difficult-to-treat infection. Increasing efforts have been taken to mitigate the epidemics and to avoid potential outbreaks in low endemic settings. Understanding the population dynamics of MRSA is essential to identify the causal mechanisms driving the epidemics and to generalise conclusions to different contexts. Previous studies neglected the temporal structure of contacts between patients and assumed homogeneous behaviour. We developed a high-resolution data-driven contact network model of interactions between 743,182 patients in 485 hospitals during 3,059 days to reproduce the exact contact sequences of the hospital population. Our model captures the exact spatial and temporal human contact behaviour and the dynamics of referrals within and between wards and hospitals at a large scale, revealing highly heterogeneous contact and mobility patterns of individual patients. A simulation exercise of epidemic spread shows that heterogeneous contacts cause the emergence of super-spreader patients, slower than exponential polynomial growth of the prevalence, and fast epidemic spread between wards and hospitals. In our simulated scenarios, screening upon hospital admittance is potentially more effective than reducing infection probability to reduce the final outbreak size. Our findings are useful to understand not only MRSA spread but also other hospital-acquired infections.}, note = {DOI: 10.1038/s41598-020-66270-9}, keywords = {}, pubstate = {published}, tppubtype = {article} } Methicillin-resistant Staphylococcus aureus (MRSA) is a difficult-to-treat infection. Increasing efforts have been taken to mitigate the epidemics and to avoid potential outbreaks in low endemic settings. Understanding the population dynamics of MRSA is essential to identify the causal mechanisms driving the epidemics and to generalise conclusions to different contexts. Previous studies neglected the temporal structure of contacts between patients and assumed homogeneous behaviour. We developed a high-resolution data-driven contact network model of interactions between 743,182 patients in 485 hospitals during 3,059 days to reproduce the exact contact sequences of the hospital population. Our model captures the exact spatial and temporal human contact behaviour and the dynamics of referrals within and between wards and hospitals at a large scale, revealing highly heterogeneous contact and mobility patterns of individual patients. A simulation exercise of epidemic spread shows that heterogeneous contacts cause the emergence of super-spreader patients, slower than exponential polynomial growth of the prevalence, and fast epidemic spread between wards and hospitals. In our simulated scenarios, screening upon hospital admittance is potentially more effective than reducing infection probability to reduce the final outbreak size. Our findings are useful to understand not only MRSA spread but also other hospital-acquired infections. |
2019 |
Libin, Pieter; Versbraegen, Nassim; Abecasis, Ana A B; Gomes, Perpétua; Lenaerts, Tom; Nowe, Ann Towards a phylogenetic measure to quantify HIV incidence Journal Article In: CEUR Workshop Proceedings, 2491 , 2019, (Language of publication: en). @article{info:hdl:2013/296964, title = {Towards a phylogenetic measure to quantify HIV incidence}, author = {Pieter Libin and Nassim Versbraegen and Ana A B Abecasis and Perpétua Gomes and Tom Lenaerts and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/296964/3/tapm.pdf}, year = {2019}, date = {2019-01-01}, journal = {CEUR Workshop Proceedings}, volume = {2491}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Versbraegen, Nassim; Fouché, Aziz; Nachtegael, Charlotte; Papadimitriou, Sofia; Gazzo, Andrea; Smits, Guillaume; Lenaerts, Tom Using game theory and decision decomposition to effectively discern and characterise bi-locus diseases Journal Article In: Artificial intelligence in medicine, 99 , 2019, (DOI: 10.1016/j.artmed.2019.06.006). @article{info:hdl:2013/292462, title = {Using game theory and decision decomposition to effectively discern and characterise bi-locus diseases}, author = {Nassim Versbraegen and Aziz Fouché and Charlotte Nachtegael and Sofia Papadimitriou and Andrea Gazzo and Guillaume Smits and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/292462/5/Elsevier_276089.pdf}, year = {2019}, date = {2019-01-01}, journal = {Artificial intelligence in medicine}, volume = {99}, abstract = {In order to gain insight into oligogenic disorders, understanding those involving bi-locus variant combinations appears to be key. In prior work, we showed that features at multiple biological scales can already be used to discriminate among two types, i.e. disorders involving true digenic and modifier combinations. The current study expands this machine learning work towards dual molecular diagnosis cases, providing a classifier able to effectively distinguish between these three types. To reach this goal and gain an in-depth understanding of the decision process, game theory and tree decomposition techniques are applied to random forest predictors to investigate the relevance of feature combinations in the prediction. A machine learning model with high discrimination capabilities was developed, effectively differentiating the three classes in a biologically meaningful manner. Combining prediction interpretation and statistical analysis, we propose a biologically meaningful characterization of each class relying on specific feature strengths. Figuring out how biological characteristics shift samples towards one of three classes provides clinically relevant insight into the underlying biological processes as well as the disease itself.}, note = {DOI: 10.1016/j.artmed.2019.06.006}, keywords = {}, pubstate = {published}, tppubtype = {article} } In order to gain insight into oligogenic disorders, understanding those involving bi-locus variant combinations appears to be key. In prior work, we showed that features at multiple biological scales can already be used to discriminate among two types, i.e. disorders involving true digenic and modifier combinations. The current study expands this machine learning work towards dual molecular diagnosis cases, providing a classifier able to effectively distinguish between these three types. To reach this goal and gain an in-depth understanding of the decision process, game theory and tree decomposition techniques are applied to random forest predictors to investigate the relevance of feature combinations in the prediction. A machine learning model with high discrimination capabilities was developed, effectively differentiating the three classes in a biologically meaningful manner. Combining prediction interpretation and statistical analysis, we propose a biologically meaningful characterization of each class relying on specific feature strengths. Figuring out how biological characteristics shift samples towards one of three classes provides clinically relevant insight into the underlying biological processes as well as the disease itself. |
Renaux, Alexandre; Papadimitriou, Sofia; Versbraegen, Nassim; Nachtegael, Charlotte; Boutry, Simon; Nowé, Ann; Smits, Guillaume; Lenaerts, Tom ORVAL: a novel platform for the prediction and exploration of disease-causing oligogenic variant combinations. Journal Article In: Nucleic acids research, 47 (W1), pp. W93-W98, 2019, (DOI: 10.1093/nar/gkz437). @article{info:hdl:2013/289958, title = {ORVAL: a novel platform for the prediction and exploration of disease-causing oligogenic variant combinations.}, author = {Alexandre Renaux and Sofia Papadimitriou and Nassim Versbraegen and Charlotte Nachtegael and Simon Boutry and Ann Nowé and Guillaume Smits and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/289958/4/doi_273585.pdf}, year = {2019}, date = {2019-01-01}, journal = {Nucleic acids research}, volume = {47}, number = {W1}, pages = {W93-W98}, abstract = {A tremendous amount of DNA sequencing data is being produced around the world with the ambition to capture in more detail the mechanisms underlying human diseases. While numerous bioinformatics tools exist that allow the discovery of causal variants in Mendelian diseases, little to no support is provided to do the same for variant combinations, an essential task for the discovery of the causes of oligogenic diseases. ORVAL (the Oligogenic Resource for Variant AnaLysis), which is presented here, provides an answer to this problem by focusing on generating networks of candidate pathogenic variant combinations in gene pairs, as opposed to isolated variants in unique genes. This online platform integrates innovative machine learning methods for combinatorial variant pathogenicity prediction with visualization techniques, offering several interactive and exploratory tools, such as pathogenic gene and protein interaction networks, a ranking of pathogenic gene pairs, as well as visual mappings of the cellular location and pathway information. ORVAL is the first web-based exploration platform dedicated to identifying networks of candidate pathogenic variant combinations with the sole ambition to help in uncovering oligogenic causes for patients that cannot rely on the classical disease analysis tools. ORVAL is available at https://orval.ibsquare.be.}, note = {DOI: 10.1093/nar/gkz437}, keywords = {}, pubstate = {published}, tppubtype = {article} } A tremendous amount of DNA sequencing data is being produced around the world with the ambition to capture in more detail the mechanisms underlying human diseases. While numerous bioinformatics tools exist that allow the discovery of causal variants in Mendelian diseases, little to no support is provided to do the same for variant combinations, an essential task for the discovery of the causes of oligogenic diseases. ORVAL (the Oligogenic Resource for Variant AnaLysis), which is presented here, provides an answer to this problem by focusing on generating networks of candidate pathogenic variant combinations in gene pairs, as opposed to isolated variants in unique genes. This online platform integrates innovative machine learning methods for combinatorial variant pathogenicity prediction with visualization techniques, offering several interactive and exploratory tools, such as pathogenic gene and protein interaction networks, a ranking of pathogenic gene pairs, as well as visual mappings of the cellular location and pathway information. ORVAL is the first web-based exploration platform dedicated to identifying networks of candidate pathogenic variant combinations with the sole ambition to help in uncovering oligogenic causes for patients that cannot rely on the classical disease analysis tools. ORVAL is available at https://orval.ibsquare.be. |
Papadimitriou, Sofia; Gazzo, Andrea; Versbraegen, Nassim; Nachtegael, Charlotte; Aerts, Jan; Moreau, Yves; Dooren, Sonia Van; Nowe, Ann; Smits, Guillaume; Lenaerts, Tom Predicting disease-causing variant combinations Journal Article In: Proceedings of the National Academy of Sciences of the United States of America, 116 (24), pp. 11878-11887, 2019, (DOI: 10.1073/pnas.1815601116). @article{info:hdl:2013/289724, title = {Predicting disease-causing variant combinations}, author = {Sofia Papadimitriou and Andrea Gazzo and Nassim Versbraegen and Charlotte Nachtegael and Jan Aerts and Yves Moreau and Sonia Van Dooren and Ann Nowe and Guillaume Smits and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/289724/4/doi_273351.pdf}, year = {2019}, date = {2019-01-01}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, volume = {116}, number = {24}, pages = {11878-11887}, abstract = {Notwithstanding important advances in the context of single-variant pathogenicity identification, novel breakthroughs in discerning the origins of many rare diseases require methods able to identify more complex genetic models. We present here the Variant Combinations Pathogenicity Predictor (VarCoPP), a machine-learning approach that identifies pathogenic variant combinations in gene pairs (called digenic or bilocus variant combinations). We show that the results produced by this method are highly accurate and precise, an efficacy that is endorsed when validating the method on recently published independent disease-causing data. Confidence labels of 95% and 99% are identified, representing the probability of a bilocus combination being a true pathogenic result, providing geneticists with rational markers to evaluate the most relevant pathogenic combinations and limit the search space and time. Finally, the VarCoPP has been designed to act as an interpretable method that can provide explanations on why a bilocus combination is predicted as pathogenic and which biological information is important for that prediction. This work provides an important step toward the genetic understanding of rare diseases, paving the way to clinical knowledge and improved patient care.}, note = {DOI: 10.1073/pnas.1815601116}, keywords = {}, pubstate = {published}, tppubtype = {article} } Notwithstanding important advances in the context of single-variant pathogenicity identification, novel breakthroughs in discerning the origins of many rare diseases require methods able to identify more complex genetic models. We present here the Variant Combinations Pathogenicity Predictor (VarCoPP), a machine-learning approach that identifies pathogenic variant combinations in gene pairs (called digenic or bilocus variant combinations). We show that the results produced by this method are highly accurate and precise, an efficacy that is endorsed when validating the method on recently published independent disease-causing data. Confidence labels of 95% and 99% are identified, representing the probability of a bilocus combination being a true pathogenic result, providing geneticists with rational markers to evaluate the most relevant pathogenic combinations and limit the search space and time. Finally, the VarCoPP has been designed to act as an interpretable method that can provide explanations on why a bilocus combination is predicted as pathogenic and which biological information is important for that prediction. This work provides an important step toward the genetic understanding of rare diseases, paving the way to clinical knowledge and improved patient care. |
Stefani, Jacopo De; Caelen, Olivier; Hattab, Dalila; "e, Yann-A; Bontempi, Gianluca A Multivariate and Multi-step Ahead Machine Learning Approach to Traditional and Cryptocurrencies Volatility Forecasting Inproceedings In: ECML PKDD 2018 Workshops, Springer, 2019, (Conference: ECML-PKDD 2018(Dublin)). @inproceedings{info:hdl:2013/284007, title = {A Multivariate and Multi-step Ahead Machine Learning Approach to Traditional and Cryptocurrencies Volatility Forecasting}, author = {Jacopo De Stefani and Olivier Caelen and Dalila Hattab and Yann-A{"e}l Le Borgne and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/284007}, year = {2019}, date = {2019-01-01}, booktitle = {ECML PKDD 2018 Workshops}, publisher = {Springer}, series = {Lecture Notes in Computer Science, 11054}, abstract = {Multivariate time series forecasting involves the learning of historical multivariate information in order to predict the future values of several quantities of interests, accounting for interdependencies among them. In finance, several of this quantities of interests (stock valuations, return, volatility) have been shown to be mutually influencing each other, making the prediction of such quantities a difficult task, especially while dealing with an high number of variables and multiple horizons in the future. Here we propose a machine learning based framework, the DFML, based on the Dynamic Factor Model, to first perform a dimensionality reduction and then perform a multiple step ahead forecasting of a reduced number of components. Finally, the components are transformed again into an high dimensional space, providing the desired forecast. Our results, comparing the DFML with several state of the art techniques from different domanins (PLS, RNN, LSTM, DFM), on both traditional stock markets and cryptocurrencies market and for different families of volatility proxies show that the DFML outperforms the concurrent methods, especially for longer horizons. We conclude by explaining how we wish to further improve the performances of the framework, both in terms of accuracy and computational efficiency.}, note = {Conference: ECML-PKDD 2018(Dublin)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Multivariate time series forecasting involves the learning of historical multivariate information in order to predict the future values of several quantities of interests, accounting for interdependencies among them. In finance, several of this quantities of interests (stock valuations, return, volatility) have been shown to be mutually influencing each other, making the prediction of such quantities a difficult task, especially while dealing with an high number of variables and multiple horizons in the future. Here we propose a machine learning based framework, the DFML, based on the Dynamic Factor Model, to first perform a dimensionality reduction and then perform a multiple step ahead forecasting of a reduced number of components. Finally, the components are transformed again into an high dimensional space, providing the desired forecast. Our results, comparing the DFML with several state of the art techniques from different domanins (PLS, RNN, LSTM, DFM), on both traditional stock markets and cryptocurrencies market and for different families of volatility proxies show that the DFML outperforms the concurrent methods, especially for longer horizons. We conclude by explaining how we wish to further improve the performances of the framework, both in terms of accuracy and computational efficiency. |
Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Modelling and influencing the AI bidding War: A research agenda Inproceedings In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, Association for Computing Machinery, 2019, (Conference: AAAI/ACM Conference on AI, Ethics, and Society(Honolulu, HI, USA)). @inproceedings{info:hdl:2013/314481, title = {Modelling and influencing the AI bidding War: A research agenda}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/314481}, year = {2019}, date = {2019-01-01}, booktitle = {Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society}, publisher = {Association for Computing Machinery}, series = {AIES'19 series}, abstract = {A race for technological supremacy in AI could lead to serious negative consequences, especially whenever ethical and safety procedures are underestimated or even ignored, leading potentially to the rejection of AI in general. For all to enjoy the benefits provided by safe, ethical and trustworthy AI systems, it is crucial to incentivise participants with appropriate strategies that ensure mutually beneficial normative behaviour and safety-compliance from all parties involved. Little attention has been given to understanding the dynamics and emergent behaviours arising from this AI bidding war, and moreover, how to influence it to achieve certain desirable outcomes (e.g. AI for public good and participant compliance). To bridge this gap, this paper proposes a research agenda to develop theoretical models that capture key factors of the AI race, revealing which strategic behaviours may emerge and hypothetical scenarios therein. Strategies from incentive and agreement modelling are directly applicable to systematically analyse how different types of incentives (namely, positive vs. negative, peer vs. institutional, and their combinations) influence safety-compliant behaviours over time, and how such behaviours should be configured to ensure desired global outcomes, studying at the same time how these mechanisms influence AI development. This agenda will provide actionable policies, showing how they need to be employed and deployed in order to achieve compliance and thereby avoid disasters as well as loosing confidence and trust in AI in general.}, note = {Conference: AAAI/ACM Conference on AI, Ethics, and Society(Honolulu, HI, USA)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } A race for technological supremacy in AI could lead to serious negative consequences, especially whenever ethical and safety procedures are underestimated or even ignored, leading potentially to the rejection of AI in general. For all to enjoy the benefits provided by safe, ethical and trustworthy AI systems, it is crucial to incentivise participants with appropriate strategies that ensure mutually beneficial normative behaviour and safety-compliance from all parties involved. Little attention has been given to understanding the dynamics and emergent behaviours arising from this AI bidding war, and moreover, how to influence it to achieve certain desirable outcomes (e.g. AI for public good and participant compliance). To bridge this gap, this paper proposes a research agenda to develop theoretical models that capture key factors of the AI race, revealing which strategic behaviours may emerge and hypothetical scenarios therein. Strategies from incentive and agreement modelling are directly applicable to systematically analyse how different types of incentives (namely, positive vs. negative, peer vs. institutional, and their combinations) influence safety-compliant behaviours over time, and how such behaviours should be configured to ensure desired global outcomes, studying at the same time how these mechanisms influence AI development. This agenda will provide actionable policies, showing how they need to be employed and deployed in order to achieve compliance and thereby avoid disasters as well as loosing confidence and trust in AI in general. |
Coppens, Youri; Efthymiadis, Kyriakos; Lenaerts, Tom; Nowé, Ann Distilling Deep Reinforcement Learning Policies in Soft Decision Trees Inproceedings In: Miller, Tim; Weber, Rosina; Magazzeni, Daniele (Ed.): Proceedings of the IJCAI 2019 Workshop on Explainable Artificial Intelligence, 2019, (Conference: (Macau, China)). @inproceedings{info:hdl:2013/302065, title = {Distilling Deep Reinforcement Learning Policies in Soft Decision Trees}, author = {Youri Coppens and Kyriakos Efthymiadis and Tom Lenaerts and Ann Nowé}, editor = {Tim Miller and Rosina Weber and Daniele Magazzeni}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/302065/3/xrl.pdf}, year = {2019}, date = {2019-01-01}, booktitle = {Proceedings of the IJCAI 2019 Workshop on Explainable Artificial Intelligence}, abstract = {An important step in Reinforcement Learning (RL) research is to create mechanisms that give higher level insights into the black-box policy models used nowadays and provide explanations for these learned behaviors or motivate the choices behind certain decision steps. In this paper, we illustrate how Soft Decision Tree (SDT) distillation can be used to make policies that are learned through RL more interpretable. Soft Decision Trees create binary trees of predetermined depth, where each branching node represents a hierarchical filter that influences the classification of input data. We distill SDTs from a deep neural network RL policy for the Mario AI benchmark and inspect the learned hierarchy of filters, showing which input features lead to specific action distributions in the episode. We realize preliminary steps towards interpreting the learned behavior of the policy and discuss future improvements.}, note = {Conference: (Macau, China)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } An important step in Reinforcement Learning (RL) research is to create mechanisms that give higher level insights into the black-box policy models used nowadays and provide explanations for these learned behaviors or motivate the choices behind certain decision steps. In this paper, we illustrate how Soft Decision Tree (SDT) distillation can be used to make policies that are learned through RL more interpretable. Soft Decision Trees create binary trees of predetermined depth, where each branching node represents a hierarchical filter that influences the classification of input data. We distill SDTs from a deep neural network RL policy for the Mario AI benchmark and inspect the learned hierarchy of filters, showing which input features lead to specific action distributions in the episode. We realize preliminary steps towards interpreting the learned behavior of the policy and discuss future improvements. |
Abels, Axel; Roijers, Diederik D M; Lenaerts, Tom; Nowe, Ann; Steckelmacher, Denis Dynamic Weights in Multi-Objective Deep Reinforcement Learning Inproceedings In: Proceedings of the 36th International Conference on Machine Learning, pp. 11-20, PMLR, 2019, (Language of publication: en). @inproceedings{info:hdl:2013/291979, title = {Dynamic Weights in Multi-Objective Deep Reinforcement Learning}, author = {Axel Abels and Diederik D M Roijers and Tom Lenaerts and Ann Nowe and Denis Steckelmacher}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/291979/3/abels19a.pdf}, year = {2019}, date = {2019-01-01}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {11-20}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Stefani, Jacopo De; Bontempi, Gianluca; Caelen, Olivier; Hattab, Dalila SYSTEM AND METHOD FOR MANAGING RISKS IN A PROCESS Miscellaneous 2019, (Language of publication: fr). @misc{info:hdl:2013/283233, title = {SYSTEM AND METHOD FOR MANAGING RISKS IN A PROCESS}, author = {Jacopo De Stefani and Gianluca Bontempi and Olivier Caelen and Dalila Hattab}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/283233}, year = {2019}, date = {2019-01-01}, abstract = {The invention relates to a system and a method for managing risk in a process of an industrial production chain, said system comprising at least one database containing at least one set of time series of raw data relating to said process, a set of devices storing at least one module or a set of modules, the execution of which makes it possible to implement the risk management method comprising at least the preprocessing of a set of raw data so as to produce a set of "proxies" of volatility, the analysis of correlations between the "proxies", the identification of at least one model and of optimal parameters depending at least on said "proxies" and the calculation of the predictions of the set of the "proxies" comprising the combination of at least one of said "proxies" with at least one exogenous parameter included in said set of "proxies".}, note = {Language of publication: fr}, keywords = {}, pubstate = {published}, tppubtype = {misc} } The invention relates to a system and a method for managing risk in a process of an industrial production chain, said system comprising at least one database containing at least one set of time series of raw data relating to said process, a set of devices storing at least one module or a set of modules, the execution of which makes it possible to implement the risk management method comprising at least the preprocessing of a set of raw data so as to produce a set of "proxies" of volatility, the analysis of correlations between the "proxies", the identification of at least one model and of optimal parameters depending at least on said "proxies" and the calculation of the predictions of the set of the "proxies" comprising the combination of at least one of said "proxies" with at least one exogenous parameter included in said set of "proxies". |
Bontempi, Gianluca The Induction Problem: A Machine Learning Vindication Argument Journal Article In: Lecture notes in computer science, 11943 LNCS , pp. 232-243, 2019, (DOI: 10.1007/978-3-030-37599-7_20). @article{info:hdl:2013/303320, title = {The Induction Problem: A Machine Learning Vindication Argument}, author = {Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/303320/3/lod2.pdf}, year = {2019}, date = {2019-01-01}, journal = {Lecture notes in computer science}, volume = {11943 LNCS}, pages = {232-243}, abstract = {The problem of induction is a central problem in philosophy of science and concerns whether it is sound or not to extract laws from observational data. Nowadays, this issue is more relevant than ever given the pervasive and growing role of the data discovery process in all sciences. If on one hand induction is routinely employed by automatic machine learning techniques, on the other most of the philosophical work criticises induction as if an alternative could exist. But is there indeed a reliable alternative to induction? Is it possible to discover or predict something in a non inductive manner? This paper formalises the question on the basis of statistical notions (bias, variance, mean squared error) borrowed from estimation theory and statistical machine learning. The result is a justification of induction as rational behaviour. In a decision-making process a behaviour is rational if it is based on making choices that result in the most optimal level of benefit or utility. If we measure utility in a prediction context in terms of expected accuracy, it follows that induction is the rational way of conduct.}, note = {DOI: 10.1007/978-3-030-37599-7_20}, keywords = {}, pubstate = {published}, tppubtype = {article} } The problem of induction is a central problem in philosophy of science and concerns whether it is sound or not to extract laws from observational data. Nowadays, this issue is more relevant than ever given the pervasive and growing role of the data discovery process in all sciences. If on one hand induction is routinely employed by automatic machine learning techniques, on the other most of the philosophical work criticises induction as if an alternative could exist. But is there indeed a reliable alternative to induction? Is it possible to discover or predict something in a non inductive manner? This paper formalises the question on the basis of statistical notions (bias, variance, mean squared error) borrowed from estimation theory and statistical machine learning. The result is a justification of induction as rational behaviour. In a decision-making process a behaviour is rational if it is based on making choices that result in the most optimal level of benefit or utility. If we measure utility in a prediction context in terms of expected accuracy, it follows that induction is the rational way of conduct. |
Carcillo, Fabrizio; "e, Yann-A; Caelen, Olivier; Kessaci, Yacine; Oblé, Frédéric; Bontempi, Gianluca Combining unsupervised and supervised learning in credit card fraud detection Journal Article In: Information sciences, 2019, (DOI: 10.1016/j.ins.2019.05.042). @article{info:hdl:2013/289125, title = {Combining unsupervised and supervised learning in credit card fraud detection}, author = {Fabrizio Carcillo and Yann-A{"e}l Le Borgne and Olivier Caelen and Yacine Kessaci and Frédéric Oblé and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/289125/1/Elsevier_272752.pdf}, year = {2019}, date = {2019-01-01}, journal = {Information sciences}, abstract = {Supervised learning techniques are widely employed in credit card fraud detection, as they make use of the assumption that fraudulent patterns can be learned from an analysis of past transactions. The task becomes challenging, however, when it has to take account of changes in customer behavior and fraudsters' ability to invent novel fraud patterns. In this context, unsupervised learning techniques can help the fraud detection systems to find anomalies. In this paper we present a hybrid technique that combines supervised and unsupervised techniques to improve the fraud detection accuracy. Unsupervised outlier scores, computed at different levels of granularity, are compared and tested on a real, annotated, credit card fraud detection dataset. Experimental results show that the combination is efficient and does indeed improve the accuracy of the detection.}, note = {DOI: 10.1016/j.ins.2019.05.042}, keywords = {}, pubstate = {published}, tppubtype = {article} } Supervised learning techniques are widely employed in credit card fraud detection, as they make use of the assumption that fraudulent patterns can be learned from an analysis of past transactions. The task becomes challenging, however, when it has to take account of changes in customer behavior and fraudsters' ability to invent novel fraud patterns. In this context, unsupervised learning techniques can help the fraud detection systems to find anomalies. In this paper we present a hybrid technique that combines supervised and unsupervised techniques to improve the fraud detection accuracy. Unsupervised outlier scores, computed at different levels of granularity, are compared and tested on a real, annotated, credit card fraud detection dataset. Experimental results show that the combination is efficient and does indeed improve the accuracy of the detection. |
Bontempi, Gianluca Comments on M4 competition Journal Article In: International journal of forecasting, 2019, (DOI: 10.1016/j.ijforecast.2019.03.028). @article{info:hdl:2013/292419, title = {Comments on M4 competition}, author = {Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/292419/1/Elsevier_276046.pdf}, year = {2019}, date = {2019-01-01}, journal = {International journal of forecasting}, note = {DOI: 10.1016/j.ijforecast.2019.03.028}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Mounir, Mohamed; Lucchetta, Marta; Silva, Tiago Henrique Da T C; Olsen, Catharina; Bontempi, Gianluca; Chen, Xi; Noushmehr, Houtan; Colaprico, Antonio; Papaleo, Elena New functionalities in the TCGAbiolinks package for the study and integration of cancer data from GDC and GTEx Journal Article In: PLoS computational biology, 15 (3), pp. e1006701, 2019, (DOI: 10.1371/journal.pcbi.1006701). @article{info:hdl:2013/286948, title = {New functionalities in the TCGAbiolinks package for the study and integration of cancer data from GDC and GTEx}, author = {Mohamed Mounir and Marta Lucchetta and Tiago Henrique Da T C Silva and Catharina Olsen and Gianluca Bontempi and Xi Chen and Houtan Noushmehr and Antonio Colaprico and Elena Papaleo}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/286948}, year = {2019}, date = {2019-01-01}, journal = {PLoS computational biology}, volume = {15}, number = {3}, pages = {e1006701}, abstract = {The advent of Next-Generation Sequencing (NGS) technologies has opened new perspectives in deciphering the genetic mechanisms underlying complex diseases. Nowadays, the amount of genomic data is massive and substantial efforts and new tools are required to unveil the information hidden in the data. The Genomic Data Commons (GDC) Data Portal is a platform that contains different genomic studies including the ones from The Cancer Genome Atlas (TCGA) and the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) initiatives, accounting for more than 40 tumor types originating from nearly 30000 patients. Such platforms, although very attractive, must make sure the stored data are easily accessible and adequately harmonized. Moreover, they have the primary focus on the data storage in a unique place, and they do not provide a comprehensive toolkit for analyses and interpretation of the data. To fulfill this urgent need, comprehensive but easily accessible computational methods for integrative analyses of genomic data that do not renounce a robust statistical and theoretical framework are required. In this context, the R/Bioconductor package TCGAbiolinks was developed, offering a variety of bioinformatics functionalities. Here we introduce new features and enhancements of TCGAbiolinks in terms of i) more accurate and flexible pipelines for differential expression analyses, ii) different methods for tumor purity estimation and filtering, iii) integration of normal samples from other platforms iv) support for other genomics datasets, exemplified here by the TARGET data. Evidence has shown that accounting for tumor purity is essential in the study of tumorigenesis, as these factors promote confounding behavior regarding differential expression analysis. With this in mind, we implemented these filtering procedures in TCGAbiolinks. Moreover, a limitation of some of the TCGA datasets is the unavailability or paucity of corresponding normal samples. We thus integrated into TCGAbiolinks the possibility to use normal samples from the Genotype-Tissue Expression (GTEx) project, which is another large-scale repository cataloging gene expression from healthy individuals. The new functionalities are available in the TCGAbiolinks version 2.8 and higher released in Bioconductor version 3.7.}, note = {DOI: 10.1371/journal.pcbi.1006701}, keywords = {}, pubstate = {published}, tppubtype = {article} } The advent of Next-Generation Sequencing (NGS) technologies has opened new perspectives in deciphering the genetic mechanisms underlying complex diseases. Nowadays, the amount of genomic data is massive and substantial efforts and new tools are required to unveil the information hidden in the data. The Genomic Data Commons (GDC) Data Portal is a platform that contains different genomic studies including the ones from The Cancer Genome Atlas (TCGA) and the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) initiatives, accounting for more than 40 tumor types originating from nearly 30000 patients. Such platforms, although very attractive, must make sure the stored data are easily accessible and adequately harmonized. Moreover, they have the primary focus on the data storage in a unique place, and they do not provide a comprehensive toolkit for analyses and interpretation of the data. To fulfill this urgent need, comprehensive but easily accessible computational methods for integrative analyses of genomic data that do not renounce a robust statistical and theoretical framework are required. In this context, the R/Bioconductor package TCGAbiolinks was developed, offering a variety of bioinformatics functionalities. Here we introduce new features and enhancements of TCGAbiolinks in terms of i) more accurate and flexible pipelines for differential expression analyses, ii) different methods for tumor purity estimation and filtering, iii) integration of normal samples from other platforms iv) support for other genomics datasets, exemplified here by the TARGET data. Evidence has shown that accounting for tumor purity is essential in the study of tumorigenesis, as these factors promote confounding behavior regarding differential expression analysis. With this in mind, we implemented these filtering procedures in TCGAbiolinks. Moreover, a limitation of some of the TCGA datasets is the unavailability or paucity of corresponding normal samples. We thus integrated into TCGAbiolinks the possibility to use normal samples from the Genotype-Tissue Expression (GTEx) project, which is another large-scale repository cataloging gene expression from healthy individuals. The new functionalities are available in the TCGAbiolinks version 2.8 and higher released in Bioconductor version 3.7. |
Verhelst, Theo; Caelen, Olivier; Dewitte, Jean Christophe; Lebichot, Bertrand; Bontempi, Gianluca Understanding telecom customer churn with machine learning: From prediction to causal inference Journal Article In: CEUR Workshop Proceedings, 2491 , 2019, (Language of publication: en). @article{info:hdl:2013/296511, title = {Understanding telecom customer churn with machine learning: From prediction to causal inference}, author = {Theo Verhelst and Olivier Caelen and Jean Christophe Dewitte and Bertrand Lebichot and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/296511/3/abstract28.pdf}, year = {2019}, date = {2019-01-01}, journal = {CEUR Workshop Proceedings}, volume = {2491}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Istaces, Nicolas; Splittgerber, Marion; Silva, Viviana Lima; Nguyen, Muriel; Thomas, Séverine; Le, Aurore; Achouri, Younes; Calonne, Emilie; Defrance, Matthieu; c c, Fran; Goriely, Stanislas; Azouz, Abdulkader EOMES interacts with RUNX3 and BRG1 to promote innate memory cell formation through epigenetic reprogramming Journal Article In: Nature communications, 10 (1), 2019, (DOI: 10.1038/s41467-019-11233-6). @article{info:hdl:2013/294385, title = {EOMES interacts with RUNX3 and BRG1 to promote innate memory cell formation through epigenetic reprogramming}, author = {Nicolas Istaces and Marion Splittgerber and Viviana Lima Silva and Muriel Nguyen and Séverine Thomas and Aurore Le and Younes Achouri and Emilie Calonne and Matthieu Defrance and Fran{c c}ois Fuks and Stanislas Goriely and Abdulkader Azouz}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/294385/1/doi_278012.pdf}, year = {2019}, date = {2019-01-01}, journal = {Nature communications}, volume = {10}, number = {1}, abstract = {Memory CD8+ T cells have the ability to provide lifelong immunity against pathogens. Although memory features generally arise after challenge with a foreign antigen, na"ive CD8 single positive (SP) thymocytes may acquire phenotypic and functional characteristics of memory cells in response to cytokines such as interleukin-4. This process is associated with the induction of the T-box transcription factor Eomesodermin (EOMES). However, the underlying molecular mechanisms remain ill-defined. Using epigenomic profiling, we show that these innate memory CD8SP cells acquire only a portion of the active enhancer repertoire of conventional memory cells. This reprograming is secondary to EOMES recruitment, mostly to RUNX3-bound enhancers. Furthermore, EOMES is found within chromatin-associated complexes containing BRG1 and promotes the recruitment of this chromatin remodelling factor. Also, the in vivo acquisition of EOMES-dependent program is BRG1-dependent. In conclusion, our results support a strong epigenetic basis for the EOMES-driven establishment of CD8+ T cell innate memory program.}, note = {DOI: 10.1038/s41467-019-11233-6}, keywords = {}, pubstate = {published}, tppubtype = {article} } Memory CD8+ T cells have the ability to provide lifelong immunity against pathogens. Although memory features generally arise after challenge with a foreign antigen, na"ive CD8 single positive (SP) thymocytes may acquire phenotypic and functional characteristics of memory cells in response to cytokines such as interleukin-4. This process is associated with the induction of the T-box transcription factor Eomesodermin (EOMES). However, the underlying molecular mechanisms remain ill-defined. Using epigenomic profiling, we show that these innate memory CD8SP cells acquire only a portion of the active enhancer repertoire of conventional memory cells. This reprograming is secondary to EOMES recruitment, mostly to RUNX3-bound enhancers. Furthermore, EOMES is found within chromatin-associated complexes containing BRG1 and promotes the recruitment of this chromatin remodelling factor. Also, the in vivo acquisition of EOMES-dependent program is BRG1-dependent. In conclusion, our results support a strong epigenetic basis for the EOMES-driven establishment of CD8+ T cell innate memory program. |
Saykali, Bechara; Nahaboo, Wallis; Mathiah, Navrita; Racu, Marie-Lucie; Defrance, Matthieu; Migeotte, Isabelle Distinct mesoderm migration phenotypes in extra-embryonic and embryonic regions of the early mouse embryo Journal Article In: eLife, 8 , 2019, (DOI: 10.7554/eLife.42434.001). @article{info:hdl:2013/282177, title = {Distinct mesoderm migration phenotypes in extra-embryonic and embryonic regions of the early mouse embryo}, author = {Bechara Saykali and Wallis Nahaboo and Navrita Mathiah and Marie-Lucie Racu and Matthieu Defrance and Isabelle Migeotte}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/282177/3/elife-42434-v1.pdf}, year = {2019}, date = {2019-01-01}, journal = {eLife}, volume = {8}, abstract = {In mouse embryo gastrulation, epiblast cells delaminate at the primitive streak to form mesoderm and definitive endoderm, through an epithelial-mesenchymal transition. Mosaic expression of a membrane reporter in nascent mesoderm enabled recording cell shape and trajectory through live imaging. Upon leaving the streak, cells changed shape and extended protrusions of distinct size and abundance depending on the neighboring germ layer, as well as the region of the embryo. Embryonic trajectories were meandrous but directional, while extra-embryonic mesoderm cells showed little net displacement. Embryonic and extra-embryonic mesoderm transcriptomes highlighted distinct guidance, cytoskeleton, adhesion, and extracellular matrix signatures. Specifically, intermediate filaments were highly expressed in extra-embryonic mesoderm, while live imaging for F-actin showed abundance of actin filaments in embryonic mesoderm only. Accordingly, Rhoa or Rac1 conditional deletion in mesoderm inhibited embryonic, but not extra-embryonic mesoderm migration. Overall, this indicates separate cytoskeleton regulation coordinating the morphology and migration of mesoderm subpopulations.}, note = {DOI: 10.7554/eLife.42434.001}, keywords = {}, pubstate = {published}, tppubtype = {article} } In mouse embryo gastrulation, epiblast cells delaminate at the primitive streak to form mesoderm and definitive endoderm, through an epithelial-mesenchymal transition. Mosaic expression of a membrane reporter in nascent mesoderm enabled recording cell shape and trajectory through live imaging. Upon leaving the streak, cells changed shape and extended protrusions of distinct size and abundance depending on the neighboring germ layer, as well as the region of the embryo. Embryonic trajectories were meandrous but directional, while extra-embryonic mesoderm cells showed little net displacement. Embryonic and extra-embryonic mesoderm transcriptomes highlighted distinct guidance, cytoskeleton, adhesion, and extracellular matrix signatures. Specifically, intermediate filaments were highly expressed in extra-embryonic mesoderm, while live imaging for F-actin showed abundance of actin filaments in embryonic mesoderm only. Accordingly, Rhoa or Rac1 conditional deletion in mesoderm inhibited embryonic, but not extra-embryonic mesoderm migration. Overall, this indicates separate cytoskeleton regulation coordinating the morphology and migration of mesoderm subpopulations. |
2018 |
Raimondi, Daniele; Orlando, Gabriele; Tabaro, Francesco; Lenaerts, Tom; Rooman, Marianne; Moreau, Yves; Vranken, Wim F Large-scale in-silico statistical mutagenesis analysis sheds light on the deleteriousness landscape of the human proteome. Journal Article In: Scientific reports, 8 (1), pp. 16980, 2018, (DOI: 10.1038/s41598-018-34959-7). @article{info:hdl:2013/283645, title = {Large-scale in-silico statistical mutagenesis analysis sheds light on the deleteriousness landscape of the human proteome.}, author = {Daniele Raimondi and Gabriele Orlando and Francesco Tabaro and Tom Lenaerts and Marianne Rooman and Yves Moreau and Wim F Vranken}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/283645/4/doi_267272.pdf}, year = {2018}, date = {2018-01-01}, journal = {Scientific reports}, volume = {8}, number = {1}, pages = {16980}, abstract = {Next generation sequencing technologies are providing increasing amounts of sequencing data, paving the way for improvements in clinical genetics and precision medicine. The interpretation of the observed genomic variants in the light of their phenotypic effects is thus emerging as a crucial task to solve in order to advance our understanding of how exomic variants affect proteins and how the proteins' functional changes affect human health. Since the experimental evaluation of the effects of every observed variant is unfeasible, Bioinformatics methods are being developed to address this challenge in-silico, by predicting the impact of millions of variants, thus providing insight into the deleteriousness landscape of entire proteomes. Here we show the feasibility of this approach by using the recently developed DEOGEN2 variant-effect predictor to perform the largest in-silico mutagenesis scan to date. We computed the deleteriousness score of 170 million variants over 15000 human proteins and we analysed the results, investigating how the predicted deleteriousness landscape of the proteins relates to known functionally and structurally relevant protein regions and biophysical properties. Moreover, we qualitatively validated our results by comparing them with two mutagenesis studies targeting two specific proteins, showing the consistency of DEOGEN2 predictions with respect to experimental data.}, note = {DOI: 10.1038/s41598-018-34959-7}, keywords = {}, pubstate = {published}, tppubtype = {article} } Next generation sequencing technologies are providing increasing amounts of sequencing data, paving the way for improvements in clinical genetics and precision medicine. The interpretation of the observed genomic variants in the light of their phenotypic effects is thus emerging as a crucial task to solve in order to advance our understanding of how exomic variants affect proteins and how the proteins' functional changes affect human health. Since the experimental evaluation of the effects of every observed variant is unfeasible, Bioinformatics methods are being developed to address this challenge in-silico, by predicting the impact of millions of variants, thus providing insight into the deleteriousness landscape of entire proteomes. Here we show the feasibility of this approach by using the recently developed DEOGEN2 variant-effect predictor to perform the largest in-silico mutagenesis scan to date. We computed the deleteriousness score of 170 million variants over 15000 human proteins and we analysed the results, investigating how the predicted deleteriousness landscape of the proteins relates to known functionally and structurally relevant protein regions and biophysical properties. Moreover, we qualitatively validated our results by comparing them with two mutagenesis studies targeting two specific proteins, showing the consistency of DEOGEN2 predictions with respect to experimental data. |
.z, Gra; Starzec, Mateusz; Byrski, Aleksander; Rycerz, Katarzyna; Kisiel-Dorohinicki, Marek; Turek, Wojciech; Krzywicki, Daniel; Lenaerts, Tom; Burguillo, Juan Carlos Flexible asynchronous simulation of iterated prisoner's dilemma based on actor model Journal Article In: Simulation modelling practice and theory, 83 , pp. 75-92, 2018, (DOI: 10.1016/j.simpat.2017.12.010). @article{info:hdl:2013/272556, title = {Flexible asynchronous simulation of iterated prisoner's dilemma based on actor model}, author = {Gra{.z}yna Skiba and Mateusz Starzec and Aleksander Byrski and Katarzyna Rycerz and Marek Kisiel-Dorohinicki and Wojciech Turek and Daniel Krzywicki and Tom Lenaerts and Juan Carlos Burguillo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/272556/1/Elsevier_256183.pdf}, year = {2018}, date = {2018-01-01}, journal = {Simulation modelling practice and theory}, volume = {83}, pages = {75-92}, abstract = {The wide range of applications of the Iterated prisoner's dilemma (IPD) game made it a popular subject of study for the research community. As a consequence, numerous experiments have been conducted by researchers along the last decades. However, topics related with scaling simulation leveraging existing HPC infrastructure in the field of IPD did not always play a relevant role in such experimental work. The main contribution of this paper is a new simulation framework, based on asynchronous communication and its implementation oriented to distributed environments. Such framework is based on the modern Akka actor platform, that supports concurrent, distributed and resilient message-driven simulations; which are exemplified over the IPD game as a case study. We also present several interesting results regarding the introduction of asynchrony into the IPD simulation in order to obtain an efficient framework, so the whole simulation becomes scalable when using HPC facilities. The influence of asynchrony on the algorithm itself is also discussed, and the results show that it does not hamper the simulation.}, note = {DOI: 10.1016/j.simpat.2017.12.010}, keywords = {}, pubstate = {published}, tppubtype = {article} } The wide range of applications of the Iterated prisoner's dilemma (IPD) game made it a popular subject of study for the research community. As a consequence, numerous experiments have been conducted by researchers along the last decades. However, topics related with scaling simulation leveraging existing HPC infrastructure in the field of IPD did not always play a relevant role in such experimental work. The main contribution of this paper is a new simulation framework, based on asynchronous communication and its implementation oriented to distributed environments. Such framework is based on the modern Akka actor platform, that supports concurrent, distributed and resilient message-driven simulations; which are exemplified over the IPD game as a case study. We also present several interesting results regarding the introduction of asynchrony into the IPD simulation in order to obtain an efficient framework, so the whole simulation becomes scalable when using HPC facilities. The influence of asynchrony on the algorithm itself is also discussed, and the results show that it does not hamper the simulation. |
Kieken, Fabien; Loth, Karine; van Nuland, Nico N A J; Tompa, Peter; Lenaerts, Tom Chemical shift assignments of the partially deuterated Fyn SH2--SH3 domain Journal Article In: Biomolecular N M R Assignments, 12 (1), pp. 117-122, 2018, (DOI: 10.1007/s12104-017-9792-1). @article{info:hdl:2013/272541, title = {Chemical shift assignments of the partially deuterated Fyn SH2--SH3 domain}, author = {Fabien Kieken and Karine Loth and Nico N A J van Nuland and Peter Tompa and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/272541}, year = {2018}, date = {2018-01-01}, journal = {Biomolecular N M R Assignments}, volume = {12}, number = {1}, pages = {117-122}, abstract = {Src Homology 2 and 3 (SH2 and SH3) are two key protein interaction modules involved in regulating the activity of many proteins such as tyrosine kinases and phosphatases by respective recognition of phosphotyrosine and proline-rich regions. In the Src family kinases, the inactive state of the protein is the direct result of the interaction of the SH2 and the SH3 domain with intra-molecular regions, leading to a closed structure incompetent with substrate modification. Here, we report the 1H, 15N and 13C backbone- and side-chain chemical shift assignments of the partially deuterated Fyn SH3--SH2 domain and structural differences between tandem and single domains. The BMRB accession number is 27165.}, note = {DOI: 10.1007/s12104-017-9792-1}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src Homology 2 and 3 (SH2 and SH3) are two key protein interaction modules involved in regulating the activity of many proteins such as tyrosine kinases and phosphatases by respective recognition of phosphotyrosine and proline-rich regions. In the Src family kinases, the inactive state of the protein is the direct result of the interaction of the SH2 and the SH3 domain with intra-molecular regions, leading to a closed structure incompetent with substrate modification. Here, we report the 1H, 15N and 13C backbone- and side-chain chemical shift assignments of the partially deuterated Fyn SH3--SH2 domain and structural differences between tandem and single domains. The BMRB accession number is 27165. |
Byrski, Aleksander; 'S, Ewelina ; Ł, Jakub ; Kisiel-Dorohinicki, Marek; Lenaerts, Tom; Samson, Dana; Indurkhya, Bipin Emergence of population structure in socio-cognitively inspired ant colony optimization Journal Article In: Computer Science, 19 (1), pp. 81-98, 2018, (DOI: 10.7494/csci.2018.19.1.2594). @article{info:hdl:2013/270586, title = {Emergence of population structure in socio-cognitively inspired ant colony optimization}, author = {Aleksander Byrski and Ewelina {'S}widerska and Jakub {Ł}asisz and Marek Kisiel-Dorohinicki and Tom Lenaerts and Dana Samson and Bipin Indurkhya}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/270586/1/doi_254213.pdf}, year = {2018}, date = {2018-01-01}, journal = {Computer Science}, volume = {19}, number = {1}, pages = {81-98}, abstract = {A metaheuristic proposed by us recently, Ant Colony Optimization (ACO) hybridized with socio-cognitive inspirations, turned out to generate interesting results when compared to classic ACO. Even though it does not always find better solutions to the considered problems, it usually finds sub-optimal solutions. Moreover, instead of a trial-and-error approach to configure the parameters of the ant species in the population, the actual structure of the population emerges from a predefined species-to-species ant migration strategies in our approach. Experimental results of our approach are compared to classic ACO and selected socio-cognitive versions of this algorithm.}, note = {DOI: 10.7494/csci.2018.19.1.2594}, keywords = {}, pubstate = {published}, tppubtype = {article} } A metaheuristic proposed by us recently, Ant Colony Optimization (ACO) hybridized with socio-cognitive inspirations, turned out to generate interesting results when compared to classic ACO. Even though it does not always find better solutions to the considered problems, it usually finds sub-optimal solutions. Moreover, instead of a trial-and-error approach to configure the parameters of the ant species in the population, the actual structure of the population emerges from a predefined species-to-species ant migration strategies in our approach. Experimental results of our approach are compared to classic ACO and selected socio-cognitive versions of this algorithm. |
`e, Nathaniel Mon P; Lenaerts, Tom; Pacheco, Jorge J M; Dingli, David Evolutionary Dynamics of Paroxysmal Nocturnal Hemoglobinuria Journal Article In: PLoS computational biology, 14 (6), 2018, (DOI: 10.1371/journal.pcbi.1006133). @article{info:hdl:2013/267360, title = {Evolutionary Dynamics of Paroxysmal Nocturnal Hemoglobinuria}, author = {Nathaniel Mon P{`e}re and Tom Lenaerts and Jorge J M Pacheco and David Dingli}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/267360/4/doi_250987.pdf}, year = {2018}, date = {2018-01-01}, journal = {PLoS computational biology}, volume = {14}, number = {6}, abstract = {Paroxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal blood disorder characterized by hemolysis and a high risk of thrombosis, that is due to a deficiency in several cell surface proteins that prevent complement activation. Its origin has been traced to a somatic mutation in the PIG-A gene within hematopoietic stem cells (HSC). However, to date the question of how this mutant clone expands in size to contribute significantly to hematopoiesis remains under debate. One hypothesis posits the existence of a selective advantage of PIG-A mutated cells due to an immune mediated attack on normal HSC, but the evidence supporting this hypothesis is inconclusive. An alternative (and simpler) explanation attributes clonal expansion to neutral drift, in which case selection neither favours nor inhibits expansion of PIG-A mutated HSC. Here we examine the implications of the neutral drift model by numerically evolving a Markov chain for the probabilities of all possible outcomes, and investigate the possible occurrence and evolution, within this framework, of multiple independently arising clones within the HSC pool. Predictions of the model agree well with the known incidence of the disease and average age at diagnosis. Notwithstanding the slight difference in clonal expansion rates between our results and those reported in the literature, our model results lead to a relative stability of clone size when averaging multiple cases, in accord with what has been observed in human trials. The probability of a patient harbouring a second clone in the HSC pool was found to be extremely low (~10-8). Thus our results suggest that in clinical cases of PNH where two independent clones of mutant cells are observed, only one of those is likely to have originated in the HSC pool.}, note = {DOI: 10.1371/journal.pcbi.1006133}, keywords = {}, pubstate = {published}, tppubtype = {article} } Paroxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal blood disorder characterized by hemolysis and a high risk of thrombosis, that is due to a deficiency in several cell surface proteins that prevent complement activation. Its origin has been traced to a somatic mutation in the PIG-A gene within hematopoietic stem cells (HSC). However, to date the question of how this mutant clone expands in size to contribute significantly to hematopoiesis remains under debate. One hypothesis posits the existence of a selective advantage of PIG-A mutated cells due to an immune mediated attack on normal HSC, but the evidence supporting this hypothesis is inconclusive. An alternative (and simpler) explanation attributes clonal expansion to neutral drift, in which case selection neither favours nor inhibits expansion of PIG-A mutated HSC. Here we examine the implications of the neutral drift model by numerically evolving a Markov chain for the probabilities of all possible outcomes, and investigate the possible occurrence and evolution, within this framework, of multiple independently arising clones within the HSC pool. Predictions of the model agree well with the known incidence of the disease and average age at diagnosis. Notwithstanding the slight difference in clonal expansion rates between our results and those reported in the literature, our model results lead to a relative stability of clone size when averaging multiple cases, in accord with what has been observed in human trials. The probability of a patient harbouring a second clone in the HSC pool was found to be extremely low (~10-8). Thus our results suggest that in clinical cases of PNH where two independent clones of mutant cells are observed, only one of those is likely to have originated in the HSC pool. |
Abels, Axel; Roijers, Diederik D M; Lenaerts, Tom; Nowe, Ann; Steckelmacher, Denis Dynamic Weights in Multi-Objective Deep Reinforcement Learning Inproceedings In: Proceedings of the 30th Benelux Conference on Artificial Intelligence, pp. 1-2, Springer, 2018, (Language of publication: en). @inproceedings{info:hdl:2013/291980, title = {Dynamic Weights in Multi-Objective Deep Reinforcement Learning}, author = {Axel Abels and Diederik D M Roijers and Tom Lenaerts and Ann Nowe and Denis Steckelmacher}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/291980/3/short.pdf}, year = {2018}, date = {2018-01-01}, booktitle = {Proceedings of the 30th Benelux Conference on Artificial Intelligence}, pages = {1-2}, publisher = {Springer}, series = {CCIS series}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Carcillo, Fabrizio 2018, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/272119, title = {Beyond Supervised Learning in Credit Card Fraud Detection: A Dive into Semi-supervised and Distributed Learning}, author = {Fabrizio Carcillo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/272119/5/ContratDiCarcillo.pdf}, year = {2018}, date = {2018-01-01}, abstract = {The expansion of the electronic commerce, as well as the increasing confidence of customers in electronic payments, makes of fraud detection a critical issue. The design of a prompt and accurate Fraud Detection System is a priority for many organizations in the business of credit cards. In this thesis we present a series of studies to increase the precision and the speed of fraud detection system. The thesis has three main contributions. The first concerns the integration of unsupervised techniques and supervised classifiers. We proposed several approaches to integrate outlier scores in the detection process and we found that the accuracy of a conventional classifier may be improved when information about the input distribution is used to augment the training set.The second contribution concerns the role of active learning in Fraud Detection. We have extensively compared several state-of-the-art techniques and found that Stochastic Semi-supervised Learning is a convenient approach to tackle the Selection Bias problem in the active learning process.The third contribution of the thesis is the design, implementation and assessment of SCARFF, an original framework for near real-time Streaming Fraud Detection. This framework integrates Big Data technology (notably tools like Kafka, Spark and Cassandra) with a machine learning approach to deal with imbalance, non-stationarity and feedback latency in a scalable manner. Experimental results on a massive dataset of real credit card transactions have showed that our framework is scalable, efficient and accurate over a big stream of transactions.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } The expansion of the electronic commerce, as well as the increasing confidence of customers in electronic payments, makes of fraud detection a critical issue. The design of a prompt and accurate Fraud Detection System is a priority for many organizations in the business of credit cards. In this thesis we present a series of studies to increase the precision and the speed of fraud detection system. The thesis has three main contributions. The first concerns the integration of unsupervised techniques and supervised classifiers. We proposed several approaches to integrate outlier scores in the detection process and we found that the accuracy of a conventional classifier may be improved when information about the input distribution is used to augment the training set.The second contribution concerns the role of active learning in Fraud Detection. We have extensively compared several state-of-the-art techniques and found that Stochastic Semi-supervised Learning is a convenient approach to tackle the Selection Bias problem in the active learning process.The third contribution of the thesis is the design, implementation and assessment of SCARFF, an original framework for near real-time Streaming Fraud Detection. This framework integrates Big Data technology (notably tools like Kafka, Spark and Cassandra) with a machine learning approach to deal with imbalance, non-stationarity and feedback latency in a scalable manner. Experimental results on a massive dataset of real credit card transactions have showed that our framework is scalable, efficient and accurate over a big stream of transactions. |
Stefani, Jacopo De; "e, Yann-A; Caelen, Olivier; Hattab, Dalila; Bontempi, Gianluca Batch and incremental dynamic factor machine learning for multivariate and multi-step-ahead forecasting Journal Article In: International journal of data science and analytics (Print), 7 (4), pp. 311-329, 2018, (DOI: 10.1007/s41060-018-0150-x). @article{info:hdl:2013/283230, title = {Batch and incremental dynamic factor machine learning for multivariate and multi-step-ahead forecasting}, author = {Jacopo De Stefani and Yann-A{"e}l Le Borgne and Olivier Caelen and Dalila Hattab and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/283230}, year = {2018}, date = {2018-01-01}, journal = {International journal of data science and analytics (Print)}, volume = {7}, number = {4}, pages = {311-329}, abstract = {Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g., issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizons. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine-learning version of the dynamic factor model, a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will discuss both a batch and an incremental version of DFML, and we will show that it can consistently outperform state-of-the-art methods in a number of Synthetic and real forecasting tasks.}, note = {DOI: 10.1007/s41060-018-0150-x}, keywords = {}, pubstate = {published}, tppubtype = {article} } Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g., issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizons. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine-learning version of the dynamic factor model, a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will discuss both a batch and an incremental version of DFML, and we will show that it can consistently outperform state-of-the-art methods in a number of Synthetic and real forecasting tasks. |
de Bony, Eric James; Bizet, Martin; Grembergen, Olivier Van; Hassabi, Bouchra; Calonne, Emilie; Putmans, Pascale; Bontempi, Gianluca; c c, Fran Comprehensive identification of long noncoding RNAs in colorectal cancer Journal Article In: Oncotarget, 9 (45), pp. 27605-27629, 2018, (DOI: 10.18632/oncotarget.25218). @article{info:hdl:2013/278063, title = {Comprehensive identification of long noncoding RNAs in colorectal cancer}, author = {Eric James de Bony and Martin Bizet and Olivier Van Grembergen and Bouchra Hassabi and Emilie Calonne and Pascale Putmans and Gianluca Bontempi and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/278063/3/doi_261690.pdf}, year = {2018}, date = {2018-01-01}, journal = {Oncotarget}, volume = {9}, number = {45}, pages = {27605-27629}, abstract = {Colorectal cancer (CRC) is one of the most common cancers in humans and a leading cause of cancer-related deaths worldwide. As in the case of other cancers, CRC heterogeneity leads to a wide range of clinical outcomes and complicates therapy. Over the years, multiple factors have emerged as markers of CRC heterogeneity, improving tumor classification and selection of therapeutic strategies. Understanding the molecular mechanisms underlying this heterogeneity remains a major challenge. A considerable research effort is therefore devoted to identifying additional features of colorectal tumors, in order to better understand CRC etiology and to multiply therapeutic avenues. Recently, long noncoding RNAs (lncRNAs) have emerged as important players in physiological and pathological processes, including CRC. Here we looked for lncRNAs that might contribute to the various colorectal tumor phenotypes. We thus monitored the expression of 4898 lncRNA genes across 566 CRC samples and identified 282 lncRNAs reflecting CRC heterogeneity. We then inferred potential functions of these lncRNAs. Our results highlight lncRNAs that may participate in the major processes altered in distinct CRC cases, such as WNT/β-catenin and TGF-β signaling, immunity, the epithelial-to-mesenchymal transition (EMT), and angiogenesis. For several candidates, we provide experimental evidence supporting our functional predictions that they may be involved in the cell cycle or the EMT. Overall, our work identifies lncRNAs associated with key CRC characteristics and provides insights into their respective functions. Our findings constitute a further step towards understanding the contribution of lncRNAs to CRC heterogeneity. They may open new therapeutic opportunities.}, note = {DOI: 10.18632/oncotarget.25218}, keywords = {}, pubstate = {published}, tppubtype = {article} } Colorectal cancer (CRC) is one of the most common cancers in humans and a leading cause of cancer-related deaths worldwide. As in the case of other cancers, CRC heterogeneity leads to a wide range of clinical outcomes and complicates therapy. Over the years, multiple factors have emerged as markers of CRC heterogeneity, improving tumor classification and selection of therapeutic strategies. Understanding the molecular mechanisms underlying this heterogeneity remains a major challenge. A considerable research effort is therefore devoted to identifying additional features of colorectal tumors, in order to better understand CRC etiology and to multiply therapeutic avenues. Recently, long noncoding RNAs (lncRNAs) have emerged as important players in physiological and pathological processes, including CRC. Here we looked for lncRNAs that might contribute to the various colorectal tumor phenotypes. We thus monitored the expression of 4898 lncRNA genes across 566 CRC samples and identified 282 lncRNAs reflecting CRC heterogeneity. We then inferred potential functions of these lncRNAs. Our results highlight lncRNAs that may participate in the major processes altered in distinct CRC cases, such as WNT/β-catenin and TGF-β signaling, immunity, the epithelial-to-mesenchymal transition (EMT), and angiogenesis. For several candidates, we provide experimental evidence supporting our functional predictions that they may be involved in the cell cycle or the EMT. Overall, our work identifies lncRNAs associated with key CRC characteristics and provides insights into their respective functions. Our findings constitute a further step towards understanding the contribution of lncRNAs to CRC heterogeneity. They may open new therapeutic opportunities. |
Carcillo, Fabrizio; "e, Yann-A; Caelen, Olivier; Bontempi, Gianluca Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization Journal Article In: International journal of data science and analytics (Print), 5 (4), pp. 285-300, 2018, (DOI: 10.1007/s41060-018-0116-z). @article{info:hdl:2013/311546, title = {Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization}, author = {Fabrizio Carcillo and Yann-A{"e}l Le Borgne and Olivier Caelen and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/311546}, year = {2018}, date = {2018-01-01}, journal = {International journal of data science and analytics (Print)}, volume = {5}, number = {4}, pages = {285-300}, abstract = {Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data are peculiar because they are obtained in a streaming fashion, and they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated with the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature.}, note = {DOI: 10.1007/s41060-018-0116-z}, keywords = {}, pubstate = {published}, tppubtype = {article} } Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data are peculiar because they are obtained in a streaming fashion, and they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated with the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature. |
Carcillo, Fabrizio; "e, Yann-A; Caelen, Olivier; Bontempi, Gianluca Correction to: Streaming active learning strategies for real-life credit detection: assessment and visualization Journal Article In: International journal of data science and analytics (Print), 5 (4), pp. 301-302, 2018, (DOI: 10.1007/s41060-018-0123-0). @article{info:hdl:2013/311389, title = {Correction to: Streaming active learning strategies for real-life credit detection: assessment and visualization}, author = {Fabrizio Carcillo and Yann-A{"e}l Le Borgne and Olivier Caelen and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/311389}, year = {2018}, date = {2018-01-01}, journal = {International journal of data science and analytics (Print)}, volume = {5}, number = {4}, pages = {301-302}, abstract = {A line was misplaced in Table 1. The correct Table 1 is given below. The original article has been corrected. (Table presented.).}, note = {DOI: 10.1007/s41060-018-0123-0}, keywords = {}, pubstate = {published}, tppubtype = {article} } A line was misplaced in Table 1. The correct Table 1 is given below. The original article has been corrected. (Table presented.). |
Ioannidis, J P A; Bhattacharya, S; Evers, J L H; Veen, Der F V; Somigliana, E; Barratt, C L R; Bontempi, Gianluca; Baird, D T; Crosignani, P; Devroey, P; Diedrich, Klaus; Farquharson, R G; Fraser, L R; Geraedts, Joep Pm M; Gianaroli, Luca; Vecchia, La C; Magli, C; Negri, E; Sunde, A; Tapanainen, J S; Tarlatzis, Basil; Steirteghem, A V; Veiga, A Protect us from poor-quality medical research Journal Article In: Human reproduction, 33 (5), pp. 770-776, 2018, (DOI: 10.1093/humrep/dey056). @article{info:hdl:2013/272828, title = {Protect us from poor-quality medical research}, author = {J P A Ioannidis and S Bhattacharya and J L H Evers and F V Der Veen and E Somigliana and C L R Barratt and Gianluca Bontempi and D T Baird and P Crosignani and P Devroey and Klaus Diedrich and R G Farquharson and L R Fraser and Joep Pm M Geraedts and Luca Gianaroli and C La Vecchia and C Magli and E Negri and A Sunde and J S Tapanainen and Basil Tarlatzis and A V Steirteghem and A Veiga}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/272828/1/doi_256455.pdf}, year = {2018}, date = {2018-01-01}, journal = {Human reproduction}, volume = {33}, number = {5}, pages = {770-776}, abstract = {Much of the published medical research is apparently flawed, cannot be replicated and/or has limited or no utility. This article presents an overview of the current landscape of biomedical research, identifies problems associated with common study designs and considers potential solutions. Randomized clinical trials, observational studies, systematic reviews and meta-analyses are discussed in terms of their inherent limitations and potential ways of improving their conduct, analysis and reporting. The current emphasis on statistical significance needs to be replaced by sound design, transparency and willingness to share data with a clear commitment towards improving the quality and utility of clinical research.}, note = {DOI: 10.1093/humrep/dey056}, keywords = {}, pubstate = {published}, tppubtype = {article} } Much of the published medical research is apparently flawed, cannot be replicated and/or has limited or no utility. This article presents an overview of the current landscape of biomedical research, identifies problems associated with common study designs and considers potential solutions. Randomized clinical trials, observational studies, systematic reviews and meta-analyses are discussed in terms of their inherent limitations and potential ways of improving their conduct, analysis and reporting. The current emphasis on statistical significance needs to be replaced by sound design, transparency and willingness to share data with a clear commitment towards improving the quality and utility of clinical research. |
Cava, Claudia; Bertoli, Gloria; Colaprico, Antonio; Bontempi, Gianluca; Mauri, Giancarlo; Castiglioni, Isabella In-silico integration approach to identify a key miRNA regulating a gene network in aggressive prostate cancer Journal Article In: International journal of molecular sciences, 19 (3), 2018, (DOI: 10.3390/ijms19030910). @article{info:hdl:2013/270452, title = {In-silico integration approach to identify a key miRNA regulating a gene network in aggressive prostate cancer}, author = {Claudia Cava and Gloria Bertoli and Antonio Colaprico and Gianluca Bontempi and Giancarlo Mauri and Isabella Castiglioni}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/270452/1/doi_254079.pdf}, year = {2018}, date = {2018-01-01}, journal = {International journal of molecular sciences}, volume = {19}, number = {3}, abstract = {Like other cancer diseases, prostate cancer (PC) is caused by the accumulation of genetic alterations in the cells that drives malignant growth. These alterations are revealed by gene profiling and copy number alteration (CNA) analysis. Moreover, recent evidence suggests that also microRNAs have an important role in PC development. Despite efforts to profile PC, the alterations (gene, CNA, and miRNA) and biological processes that correlate with disease development and progression remain partially elusive. Many gene signatures proposed as diagnostic or prognostic tools in cancer poorly overlap. The identification of co-expressed genes, that are functionally related, can identify a core network of genes associated with PC with a better reproducibility. By combining different approaches, including the integration of mRNA expression profiles, CNAs, and miRNA expression levels, we identified a gene signature of four genes overlapping with other published gene signatures and able to distinguish, in silico, high Gleason-scored PC from normal human tissue, which was further enriched to 19 genes by gene co-expression analysis. From the analysis of miRNAs possibly regulating this network, we found that hsa-miR-153 was highly connected to the genes in the network. Our results identify a four-gene signature with diagnostic and prognostic value in PC and suggest an interesting gene network that could play a key regulatory role in PC development and progression. Furthermore, hsa-miR-153, controlling this network, could be a potential biomarker for theranostics in high Gleason-scored PC.}, note = {DOI: 10.3390/ijms19030910}, keywords = {}, pubstate = {published}, tppubtype = {article} } Like other cancer diseases, prostate cancer (PC) is caused by the accumulation of genetic alterations in the cells that drives malignant growth. These alterations are revealed by gene profiling and copy number alteration (CNA) analysis. Moreover, recent evidence suggests that also microRNAs have an important role in PC development. Despite efforts to profile PC, the alterations (gene, CNA, and miRNA) and biological processes that correlate with disease development and progression remain partially elusive. Many gene signatures proposed as diagnostic or prognostic tools in cancer poorly overlap. The identification of co-expressed genes, that are functionally related, can identify a core network of genes associated with PC with a better reproducibility. By combining different approaches, including the integration of mRNA expression profiles, CNAs, and miRNA expression levels, we identified a gene signature of four genes overlapping with other published gene signatures and able to distinguish, in silico, high Gleason-scored PC from normal human tissue, which was further enriched to 19 genes by gene co-expression analysis. From the analysis of miRNAs possibly regulating this network, we found that hsa-miR-153 was highly connected to the genes in the network. Our results identify a four-gene signature with diagnostic and prognostic value in PC and suggest an interesting gene network that could play a key regulatory role in PC development and progression. Furthermore, hsa-miR-153, controlling this network, could be a potential biomarker for theranostics in high Gleason-scored PC. |
Trepo, Eric; Goossens, Nicolas; Fujiwara, Naoto; Song, Won-Min; Colaprico, Antonio; Marot, Astrid; Spahr, Laurent; Demetter, Pieter; Sempoux, Christine; Im, Gene Y; Saldarriaga, Joan; Gustot, Thierry; `e, Jacques Devi; Thung, Swan SN; Minsart, Charlotte; Serste, Thomas; Bontempi, Gianluca; Abdelrahman, Karim; Henrion, Jean; Degré, Delphine; Lucidi, Valerio; Rubbia-Brandt, Laura; Nair, Venugopalan D; Moreno, Christophe; Deltenre, Pierre; Hoshida, Yujin; Franchimont, Denis In: Gastroenterology, 154 (4), pp. 965-975, 2018, (DOI: 10.1053/j.gastro.2017.10.048). @article{info:hdl:2013/269084, title = {Combination of Gene Expression Signature and Model for End-Stage Liver Disease Score Predicts Survival of Patients With Severe Alcoholic Hepatitis}, author = {Eric Trepo and Nicolas Goossens and Naoto Fujiwara and Won-Min Song and Antonio Colaprico and Astrid Marot and Laurent Spahr and Pieter Demetter and Christine Sempoux and Gene Y Im and Joan Saldarriaga and Thierry Gustot and Jacques Devi{`e}re and Swan SN Thung and Charlotte Minsart and Thomas Serste and Gianluca Bontempi and Karim Abdelrahman and Jean Henrion and Delphine Degré and Valerio Lucidi and Laura Rubbia-Brandt and Venugopalan D Nair and Christophe Moreno and Pierre Deltenre and Yujin Hoshida and Denis Franchimont}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/269084}, year = {2018}, date = {2018-01-01}, journal = {Gastroenterology}, volume = {154}, number = {4}, pages = {965-975}, abstract = {Background & Aims: Patients with severe alcoholic hepatitis (AH) have a high risk of death within 90 days. Corticosteroids, which can cause severe adverse events, are the only treatment that increases short-term survival. It is a challenge to predict outcomes of patients with severe AH. Therefore, we developed a scoring system to predict patient survival, integrating baseline molecular and clinical variables. Methods: We obtained fixed liver biopsy samples from 71 consecutive patients diagnosed with severe AH and treated with corticosteroids from July 2006 through December 2013 in Brussels, Belgium (derivation cohort). Gene expression patterns were analyzed by microarrays and clinical data were collected for 180 days. We identified gene expression signatures and clinical data that are associated with survival without liver transplantation at 90 and 180 days after initiation of corticosteroid therapy. Findings were validated using liver biopsies from 48 consecutive patients with severe AH treated with corticosteroids, collected from March 2010 through February 2015 at hospitals in Belgium and Switzerland (validation cohort 1) and in liver biopsies from 20 patients (9 received corticosteroid treatment), collected from January 2012 through May 2015 in the United States (validation cohort 2). Results: We integrated data on expression patterns of 123 genes and the model for end-stage liver disease (MELD) scores to assign patients to groups with poor survival (29% survived 90 days and 26% survived 180 days) and good survival (76% survived 90 days and 65% survived 180 days) (P <.001) in the derivation cohort. We named this assignment system the gene signature--MELD (gs-MELD) score. In validation cohort 1, the gs-MELD score discriminated patients with poor survival (43% survived 90 days) from those with good survival (96% survived 90 days) (P <.001). The gs-MELD score also discriminated between patients with a poor survival at 180 days (34% survived) and a good survival at 180 days (84% survived) (P <.001). The time-dependent area under the receiver operator characteristic curve for the score was 0.86 (95% confidence interval 0.73--0.99) for survival at 90 days, and 0.83 (95% confidence interval 0.71--0.96) for survival at 180 days. This score outperformed other clinical models to predict survival of patients with severe AH in validation cohort 1. In validation cohort 2, the gs-MELD discriminated patients with a poor survival at 90 days (12% survived) from those with a good survival at 90 days (100%) (P <.001). Conclusions: We integrated data on baseline liver gene expression pattern and the MELD score to create the gs-MELD scoring system, which identifies patients with severe AH, treated or not with corticosteroids, most and least likely to survive for 90 and 180 days.}, note = {DOI: 10.1053/j.gastro.2017.10.048}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background & Aims: Patients with severe alcoholic hepatitis (AH) have a high risk of death within 90 days. Corticosteroids, which can cause severe adverse events, are the only treatment that increases short-term survival. It is a challenge to predict outcomes of patients with severe AH. Therefore, we developed a scoring system to predict patient survival, integrating baseline molecular and clinical variables. Methods: We obtained fixed liver biopsy samples from 71 consecutive patients diagnosed with severe AH and treated with corticosteroids from July 2006 through December 2013 in Brussels, Belgium (derivation cohort). Gene expression patterns were analyzed by microarrays and clinical data were collected for 180 days. We identified gene expression signatures and clinical data that are associated with survival without liver transplantation at 90 and 180 days after initiation of corticosteroid therapy. Findings were validated using liver biopsies from 48 consecutive patients with severe AH treated with corticosteroids, collected from March 2010 through February 2015 at hospitals in Belgium and Switzerland (validation cohort 1) and in liver biopsies from 20 patients (9 received corticosteroid treatment), collected from January 2012 through May 2015 in the United States (validation cohort 2). Results: We integrated data on expression patterns of 123 genes and the model for end-stage liver disease (MELD) scores to assign patients to groups with poor survival (29% survived 90 days and 26% survived 180 days) and good survival (76% survived 90 days and 65% survived 180 days) (P <.001) in the derivation cohort. We named this assignment system the gene signature--MELD (gs-MELD) score. In validation cohort 1, the gs-MELD score discriminated patients with poor survival (43% survived 90 days) from those with good survival (96% survived 90 days) (P <.001). The gs-MELD score also discriminated between patients with a poor survival at 180 days (34% survived) and a good survival at 180 days (84% survived) (P <.001). The time-dependent area under the receiver operator characteristic curve for the score was 0.86 (95% confidence interval 0.73--0.99) for survival at 90 days, and 0.83 (95% confidence interval 0.71--0.96) for survival at 180 days. This score outperformed other clinical models to predict survival of patients with severe AH in validation cohort 1. In validation cohort 2, the gs-MELD discriminated patients with a poor survival at 90 days (12% survived) from those with a good survival at 90 days (100%) (P <.001). Conclusions: We integrated data on baseline liver gene expression pattern and the MELD score to create the gs-MELD scoring system, which identifies patients with severe AH, treated or not with corticosteroids, most and least likely to survive for 90 and 180 days. |
Reggiani, Claudio; "e, Yann-A; Bontempi, Gianluca Feature selection in high-dimensional dataset using MapReduce Journal Article In: Communications in computer and information science, 823 , pp. 101-115, 2018, (DOI: 10.1007/978-3-319-76892-2_8). @article{info:hdl:2013/269455, title = {Feature selection in high-dimensional dataset using MapReduce}, author = {Claudio Reggiani and Yann-A{"e}l Le Borgne and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/269455}, year = {2018}, date = {2018-01-01}, journal = {Communications in computer and information science}, volume = {823}, pages = {101-115}, abstract = {This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open source implementation based on Hadoop/Spark, and illustrate its scalability on datasets involving millions of observations or features.}, note = {DOI: 10.1007/978-3-319-76892-2_8}, keywords = {}, pubstate = {published}, tppubtype = {article} } This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open source implementation based on Hadoop/Spark, and illustrate its scalability on datasets involving millions of observations or features. |
Cava, Claudia; Bertoli, Gloria; Colaprico, Antonio; Olsen, Catharina; Bontempi, Gianluca; Castiglioni, Isabella Integration of multiple networks and pathways identifies cancer driver genes in pan-cancer analysis Journal Article In: BMC genomics, 19 (1), 2018, (DOI: 10.1186/s12864-017-4423-x). @article{info:hdl:2013/268430, title = {Integration of multiple networks and pathways identifies cancer driver genes in pan-cancer analysis}, author = {Claudia Cava and Gloria Bertoli and Antonio Colaprico and Catharina Olsen and Gianluca Bontempi and Isabella Castiglioni}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/268430/1/doi_252057.pdf}, year = {2018}, date = {2018-01-01}, journal = {BMC genomics}, volume = {19}, number = {1}, abstract = {Background: Modern high-throughput genomic technologies represent a comprehensive hallmark of molecular changes in pan-cancer studies. Although different cancer gene signatures have been revealed, the mechanism of tumourigenesis has yet to be completely understood. Pathways and networks are important tools to explain the role of genes in functional genomic studies. However, few methods consider the functional non-equal roles of genes in pathways and the complex gene-gene interactions in a network. Results: We present a novel method in pan-cancer analysis that identifies de-regulated genes with a functional role by integrating pathway and network data. A pan-cancer analysis of 7158 tumour/normal samples from 16 cancer types identified 895 genes with a central role in pathways and de-regulated in cancer. Comparing our approach with 15 current tools that identify cancer driver genes, we found that 35.6% of the 895 genes identified by our method have been found as cancer driver genes with at least 2/15 tools. Finally, we applied a machine learning algorithm on 16 independent GEO cancer datasets to validate the diagnostic role of cancer driver genes for each cancer. We obtained a list of the top-ten cancer driver genes for each cancer considered in this study. Conclusions: Our analysis 1) confirmed that there are several known cancer driver genes in common among different types of cancer, 2) highlighted that cancer driver genes are able to regulate crucial pathways.}, note = {DOI: 10.1186/s12864-017-4423-x}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Modern high-throughput genomic technologies represent a comprehensive hallmark of molecular changes in pan-cancer studies. Although different cancer gene signatures have been revealed, the mechanism of tumourigenesis has yet to be completely understood. Pathways and networks are important tools to explain the role of genes in functional genomic studies. However, few methods consider the functional non-equal roles of genes in pathways and the complex gene-gene interactions in a network. Results: We present a novel method in pan-cancer analysis that identifies de-regulated genes with a functional role by integrating pathway and network data. A pan-cancer analysis of 7158 tumour/normal samples from 16 cancer types identified 895 genes with a central role in pathways and de-regulated in cancer. Comparing our approach with 15 current tools that identify cancer driver genes, we found that 35.6% of the 895 genes identified by our method have been found as cancer driver genes with at least 2/15 tools. Finally, we applied a machine learning algorithm on 16 independent GEO cancer datasets to validate the diagnostic role of cancer driver genes for each cancer. We obtained a list of the top-ten cancer driver genes for each cancer considered in this study. Conclusions: Our analysis 1) confirmed that there are several known cancer driver genes in common among different types of cancer, 2) highlighted that cancer driver genes are able to regulate crucial pathways. |
Silva, Tiago Chedraoui; Colaprico, Antonio; Olsen, Catharina; Malta, Tathiane Maistro Aistro T M; Bontempi, Gianluca; Ceccarelli, Michele; Berman, Benjamin B P; Noushmehr, Houtan In: F1000Research, 7 , 2018, (DOI: 10.12688/F1000RESEARCH.14197.1). @article{info:hdl:2013/311579, title = {TCGAbiolinksGUI: A graphical user interface to analyze cancer molecular and clinical data [version 1; peer review: 1 approved, 1 approved with reservations]}, author = {Tiago Chedraoui Silva and Antonio Colaprico and Catharina Olsen and Tathiane Maistro Aistro T M Malta and Gianluca Bontempi and Michele Ceccarelli and Benjamin B P Berman and Houtan Noushmehr}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/311579/1/doi_295223.pdf}, year = {2018}, date = {2018-01-01}, journal = {F1000Research}, volume = {7}, abstract = {The GDC (Genomic Data Commons) data portal provides users with data from cancer genomics studies. Recently, we developed the R/Bioconductor TCGAbiolinks package, which allows users to search, download and prepare cancer genomics data for integrative data analysis. The use of this package requires users to have advanced knowledge of R thus limiting the number of users. To overcome this obstacle and improve the accessibility of the package by a wider range of users, we developed a graphical user interface (GUI) using Shiny available through the package TCGAbiolinksGUI. The TCGAbiolinksGUI package is freely available within the Bioconductor project at http://bioconductor.org/packages/TCGAbiolinksGUI/. Links to the GitHub repository, a demo version of the tool, a docker image and PDF/video tutorials are available from the TCGAbiolinksGUI site.}, note = {DOI: 10.12688/F1000RESEARCH.14197.1}, keywords = {}, pubstate = {published}, tppubtype = {article} } The GDC (Genomic Data Commons) data portal provides users with data from cancer genomics studies. Recently, we developed the R/Bioconductor TCGAbiolinks package, which allows users to search, download and prepare cancer genomics data for integrative data analysis. The use of this package requires users to have advanced knowledge of R thus limiting the number of users. To overcome this obstacle and improve the accessibility of the package by a wider range of users, we developed a graphical user interface (GUI) using Shiny available through the package TCGAbiolinksGUI. The TCGAbiolinksGUI package is freely available within the Bioconductor project at http://bioconductor.org/packages/TCGAbiolinksGUI/. Links to the GitHub repository, a demo version of the tool, a docker image and PDF/video tutorials are available from the TCGAbiolinksGUI site. |
Bogeas, Alexandra; Morvan-Dubois, Ghislaine; El-Habr, Elias E A; c Xavier c, Fran; Defrance, Matthieu; Narayanan, Ashwin; Kuranda, Klaudia; Burel-Vandenbos, Fanny; Sayd, Salwa; Delaunay, Virgile; Dubois, Luiz Gustavo Feijó L G; Parrinello, Hugues; Rialle, Stéphanie; Fabrega, Sylvie; Idbaih, Ahmed; Haiech, Jacques; Bieche, Ivan; Virolle, Thierry; Goodhardt, Michele; Chneiweiss, Hervé; Junier, Marie Pierre Changes in chromatin state reveal ARNT2 at a node of a tumorigenic transcription factor signature driving glioblastoma cell aggressiveness Journal Article In: Acta Neuropathologica, 135 (2), pp. 267-283, 2018, (DOI: 10.1007/s00401-017-1783-x). @article{info:hdl:2013/272529, title = {Changes in chromatin state reveal ARNT2 at a node of a tumorigenic transcription factor signature driving glioblastoma cell aggressiveness}, author = {Alexandra Bogeas and Ghislaine Morvan-Dubois and Elias E A El-Habr and Fran{c Xavier c}ois Lejeune and Matthieu Defrance and Ashwin Narayanan and Klaudia Kuranda and Fanny Burel-Vandenbos and Salwa Sayd and Virgile Delaunay and Luiz Gustavo Feijó L G Dubois and Hugues Parrinello and Stéphanie Rialle and Sylvie Fabrega and Ahmed Idbaih and Jacques Haiech and Ivan Bieche and Thierry Virolle and Michele Goodhardt and Hervé Chneiweiss and Marie Pierre Junier}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/272529/1/doi_256156.pdf}, year = {2018}, date = {2018-01-01}, journal = {Acta Neuropathologica}, volume = {135}, number = {2}, pages = {267-283}, abstract = {Although a growing body of evidence indicates that phenotypic plasticity exhibited by glioblastoma cells plays a central role in tumor development and post-therapy recurrence, the master drivers of their aggressiveness remain elusive. Here we mapped the changes in active (H3K4me3) and repressive (H3K27me3) histone modifications accompanying the repression of glioblastoma stem-like cells tumorigenicity. Genes with changing histone marks delineated a network of transcription factors related to cancerous behavior, stem state, and neural development, highlighting a previously unsuspected association between repression of ARNT2 and loss of cell tumorigenicity. Immunohistochemistry confirmed ARNT2 expression in cell sub-populations within proliferative zones of patients' glioblastoma. Decreased ARNT2 expression was consistently observed in non-tumorigenic glioblastoma cells, compared to tumorigenic cells. Moreover, ARNT2 expression correlated with a tumorigenic molecular signature at both the tissue level within the tumor core and at the single cell level in the patients' tumors. We found that ARNT2 knockdown decreased the expression of SOX9, POU3F2 and OLIG2, transcription factors implicated in glioblastoma cell tumorigenicity, and repressed glioblastoma stem-like cell tumorigenic properties in vivo. Our results reveal ARNT2 as a pivotal component of the glioblastoma cell tumorigenic signature, located at a node of a transcription factor network controlling glioblastoma cell aggressiveness.}, note = {DOI: 10.1007/s00401-017-1783-x}, keywords = {}, pubstate = {published}, tppubtype = {article} } Although a growing body of evidence indicates that phenotypic plasticity exhibited by glioblastoma cells plays a central role in tumor development and post-therapy recurrence, the master drivers of their aggressiveness remain elusive. Here we mapped the changes in active (H3K4me3) and repressive (H3K27me3) histone modifications accompanying the repression of glioblastoma stem-like cells tumorigenicity. Genes with changing histone marks delineated a network of transcription factors related to cancerous behavior, stem state, and neural development, highlighting a previously unsuspected association between repression of ARNT2 and loss of cell tumorigenicity. Immunohistochemistry confirmed ARNT2 expression in cell sub-populations within proliferative zones of patients' glioblastoma. Decreased ARNT2 expression was consistently observed in non-tumorigenic glioblastoma cells, compared to tumorigenic cells. Moreover, ARNT2 expression correlated with a tumorigenic molecular signature at both the tissue level within the tumor core and at the single cell level in the patients' tumors. We found that ARNT2 knockdown decreased the expression of SOX9, POU3F2 and OLIG2, transcription factors implicated in glioblastoma cell tumorigenicity, and repressed glioblastoma stem-like cell tumorigenic properties in vivo. Our results reveal ARNT2 as a pivotal component of the glioblastoma cell tumorigenic signature, located at a node of a transcription factor network controlling glioblastoma cell aggressiveness. |
Saykali, Bechara; Nahaboo, Wallis; Mathiah, Navrita; Racu, Marie-Lucie; Defrance, Matthieu; Migeotte, Isabelle Distinct mesoderm migration phenotypes in extra-embryonic and embryonic regions of the early mouse embryo Journal Article In: BioRxiv, 2018, (Language of publication: en). @article{info:hdl:2013/282216, title = {Distinct mesoderm migration phenotypes in extra-embryonic and embryonic regions of the early mouse embryo}, author = {Bechara Saykali and Wallis Nahaboo and Navrita Mathiah and Marie-Lucie Racu and Matthieu Defrance and Isabelle Migeotte}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/282216/4/438721v1.full.pdf}, year = {2018}, date = {2018-01-01}, journal = {BioRxiv}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Serroukh, Yasmina; Gu-Trantien, Chunyan; Kashani, Baharak Hooshiar; Defrance, Matthieu; Manh, Thien-Phong Vu; Azouz, Abdulkader; Detavernier, Aurélie; Hoyois, Alice; Das, Jishnu; Bizet, Martin; Pollet, Emeline; Tabbuso, Tressy; Calonne, Emilie; van Gisbergen, Klaas; Dalod, Marc; c c, Fran; Goriely, Stanislas; Marchant, Arnaud The transcription factors Runx3 and ThPOK cross-regulate acquisition of cytotoxic function by human Th1 lymphocytes. Journal Article In: eLife, 7 , 2018, (DOI: 10.7554/eLife.30496). @article{info:hdl:2013/268207, title = {The transcription factors Runx3 and ThPOK cross-regulate acquisition of cytotoxic function by human Th1 lymphocytes.}, author = {Yasmina Serroukh and Chunyan Gu-Trantien and Baharak Hooshiar Kashani and Matthieu Defrance and Thien-Phong Vu Manh and Abdulkader Azouz and Aurélie Detavernier and Alice Hoyois and Jishnu Das and Martin Bizet and Emeline Pollet and Tressy Tabbuso and Emilie Calonne and Klaas van Gisbergen and Marc Dalod and Fran{c c}ois Fuks and Stanislas Goriely and Arnaud Marchant}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/268207/1/doi_251834.pdf}, year = {2018}, date = {2018-01-01}, journal = {eLife}, volume = {7}, abstract = {Cytotoxic CD4 (CD4CTX) T cells are emerging as an important component of anti-viral and anti-tumor immunity but the molecular basis of their development remains poorly understood. In the context of human cytomegalovirus infection, a significant proportion of CD4 T cells displays cytotoxic functions. We observed that the transcriptional program of these cells was enriched in CD8 T cell lineage genes despite the absence of ThPOK downregulation. We further show that establishment of CD4CTX-specific transcriptional and epigenetic programs occurred in a stepwise fashion along the Th1-differentiation pathway. In vitro, prolonged activation of naive CD4 T cells in presence of Th1 polarizing cytokines led to the acquisition of perforin-dependent cytotoxic activity. This process was dependent on the Th1 transcription factor Runx3 and was limited by the sustained expression of ThPOK. This work elucidates the molecular program of human CD4CTXT cells and identifies potential targets for immunotherapy against viral infections and cancer.}, note = {DOI: 10.7554/eLife.30496}, keywords = {}, pubstate = {published}, tppubtype = {article} } Cytotoxic CD4 (CD4CTX) T cells are emerging as an important component of anti-viral and anti-tumor immunity but the molecular basis of their development remains poorly understood. In the context of human cytomegalovirus infection, a significant proportion of CD4 T cells displays cytotoxic functions. We observed that the transcriptional program of these cells was enriched in CD8 T cell lineage genes despite the absence of ThPOK downregulation. We further show that establishment of CD4CTX-specific transcriptional and epigenetic programs occurred in a stepwise fashion along the Th1-differentiation pathway. In vitro, prolonged activation of naive CD4 T cells in presence of Th1 polarizing cytokines led to the acquisition of perforin-dependent cytotoxic activity. This process was dependent on the Th1 transcription factor Runx3 and was limited by the sustained expression of ThPOK. This work elucidates the molecular program of human CD4CTXT cells and identifies potential targets for immunotherapy against viral infections and cancer. |
Willot, Quentin; Mardulyn, Patrick; Defrance, Matthieu; Gueydan, Cyril; Aron, Serge Molecular chaperoning helps safeguarding mitochondrial integrity and motor functions in the Sahara silver ant Cataglyphis bombycina Journal Article In: Scientific reports, 8 , 2018, (DOI: 10.1038/s41598-018-27628-2). @article{info:hdl:2013/272668, title = {Molecular chaperoning helps safeguarding mitochondrial integrity and motor functions in the Sahara silver ant Cataglyphis bombycina}, author = {Quentin Willot and Patrick Mardulyn and Matthieu Defrance and Cyril Gueydan and Serge Aron}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/272668}, year = {2018}, date = {2018-01-01}, journal = {Scientific reports}, volume = {8}, abstract = {The Sahara silver ant Cataglyphis bombycina is one of the world's most thermotolerant animals. Workers forage for heat-stricken arthropods during the hottest part of the day, when temperatures exceed 50 $,^circ$C. However, the physiological adaptations needed to cope with such harsh conditions remain poorly studied in this desert species. Using transcriptomics, we screened for the most heat-responsive transcripts of C. bombycina with aim to better characterize the molecular mechanisms involved with macromolecular stability and cell survival to heat-stress. We identified 67 strongly and consistently expressed transcripts, and we show evidences of both evolutionary selection and specific heat-induction of mitochondrial-related molecular chaperones that have not been documented in Formicidae so far. This indicates clear focus of the silver ant's heat-shock response in preserving mitochondrial integrity and energy production. The joined induction of small heat-shock proteins likely depicts the higher requirement of this insect for proper motor function in response to extreme burst of heat-stresses. We discuss how those physiological adaptations may effectively help workers resist and survive the scorching heat and burning ground of the midday Sahara Desert.}, note = {DOI: 10.1038/s41598-018-27628-2}, keywords = {}, pubstate = {published}, tppubtype = {article} } The Sahara silver ant Cataglyphis bombycina is one of the world's most thermotolerant animals. Workers forage for heat-stricken arthropods during the hottest part of the day, when temperatures exceed 50 $,^circ$C. However, the physiological adaptations needed to cope with such harsh conditions remain poorly studied in this desert species. Using transcriptomics, we screened for the most heat-responsive transcripts of C. bombycina with aim to better characterize the molecular mechanisms involved with macromolecular stability and cell survival to heat-stress. We identified 67 strongly and consistently expressed transcripts, and we show evidences of both evolutionary selection and specific heat-induction of mitochondrial-related molecular chaperones that have not been documented in Formicidae so far. This indicates clear focus of the silver ant's heat-shock response in preserving mitochondrial integrity and energy production. The joined induction of small heat-shock proteins likely depicts the higher requirement of this insect for proper motor function in response to extreme burst of heat-stresses. We discuss how those physiological adaptations may effectively help workers resist and survive the scorching heat and burning ground of the midday Sahara Desert. |
Bizet, Martin Bioinformatic inference of a prognostic epigenetic signature of immunity in breast cancers PhD Thesis 2018, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/265092, title = {Bioinformatic inference of a prognostic epigenetic signature of immunity in breast cancers}, author = {Martin Bizet}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/265092/7/ContratDiBizet.pdf}, year = {2018}, date = {2018-01-01}, abstract = {L'altération des marques épigénétiques est de plus en plus reconnue comme une caractéristique fondamentale des cancers. Dans cette th`ese, nous avons utilisé des profils de méthylation de l'ADN en vue d'améliorer la classification des patients atteints du cancer du sein gr^ace `a une approche basée sur l'apprentissage automatique. L'objectif `a long terme est le développement d'outils cliniques de médecine personnalisée. Les données de méthylation de l'ADN furent acquises `a l'aide d'une puce `a ADN dédiée `a la méthylation, appelée Infinium. Cette technologie est récente comparée, par exemple, aux puces d'expression génique et son prétraitement n'est pas encore standardisé. La premi`ere partie de cette th`ese fut donc consacrée `a l'évaluation des méthodes de normalisation par comparaison des données normalisées avec d'autres technologies (pyroséquenc cage et RRBS) pour les deux technologies Infinium les plus récentes (450k et 850k). Nous avons également évalué la couverture de régions biologiquement relevantes (promoteurs et amplificateurs) par les deux technologies. Ensuite, nous avons utilisé les données Infinium (correctement prétraitées) pour développer un score, appelé MeTIL score, qui présente une valeur pronostique et prédictive dans les cancers du sein. Nous avons profité de la capacité de la méthylation de l'ADN `a refléter la composition cellulaire pour extraire une signature de méthylation (c'est-`a-dire un ensemble de positions de l'ADN o`u la méthylation varie) qui refl`ete la présence de lymphocytes dans l'échantillon tumoral. Apr`es une sélection de sites présentant une méthylation spécifique aux lymphocytes, nous avons développé une approche basée sur l'apprentissage automatique pour obtenir une signature d'une tailleoptimale réduite `a cinq sites permettant potentiellement une utilisation en clinique. Apr`es conversion de cette signature en un score, nous avons montré sa spécificité pour les lymphocytes `a l'aide de données externes et de simulations informatiques. Puis, nous avons montré la capacité du MeTIL score `a prédire la réponse `a la chimiothérapie ainsi que son pouvoir pronostique dans des cohortes indépendantes de cancer du sein et, m^eme, dans d'autres cancers.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } L'altération des marques épigénétiques est de plus en plus reconnue comme une caractéristique fondamentale des cancers. Dans cette th`ese, nous avons utilisé des profils de méthylation de l'ADN en vue d'améliorer la classification des patients atteints du cancer du sein gr^ace `a une approche basée sur l'apprentissage automatique. L'objectif `a long terme est le développement d'outils cliniques de médecine personnalisée. Les données de méthylation de l'ADN furent acquises `a l'aide d'une puce `a ADN dédiée `a la méthylation, appelée Infinium. Cette technologie est récente comparée, par exemple, aux puces d'expression génique et son prétraitement n'est pas encore standardisé. La premi`ere partie de cette th`ese fut donc consacrée `a l'évaluation des méthodes de normalisation par comparaison des données normalisées avec d'autres technologies (pyroséquenc cage et RRBS) pour les deux technologies Infinium les plus récentes (450k et 850k). Nous avons également évalué la couverture de régions biologiquement relevantes (promoteurs et amplificateurs) par les deux technologies. Ensuite, nous avons utilisé les données Infinium (correctement prétraitées) pour développer un score, appelé MeTIL score, qui présente une valeur pronostique et prédictive dans les cancers du sein. Nous avons profité de la capacité de la méthylation de l'ADN `a refléter la composition cellulaire pour extraire une signature de méthylation (c'est-`a-dire un ensemble de positions de l'ADN o`u la méthylation varie) qui refl`ete la présence de lymphocytes dans l'échantillon tumoral. Apr`es une sélection de sites présentant une méthylation spécifique aux lymphocytes, nous avons développé une approche basée sur l'apprentissage automatique pour obtenir une signature d'une tailleoptimale réduite `a cinq sites permettant potentiellement une utilisation en clinique. Apr`es conversion de cette signature en un score, nous avons montré sa spécificité pour les lymphocytes `a l'aide de données externes et de simulations informatiques. Puis, nous avons montré la capacité du MeTIL score `a prédire la réponse `a la chimiothérapie ainsi que son pouvoir pronostique dans des cohortes indépendantes de cancer du sein et, m^eme, dans d'autres cancers. |
Reggiani, Claudio 2018, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/270994, title = {Bioinformatic discovery of novel exons expressed in human brain and their association with neurodevelopmental disorders}, author = {Claudio Reggiani}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/270994/5/ContratDiReggiani.pdf}, year = {2018}, date = {2018-01-01}, abstract = {An important quest in genomics since the publication of the first complete human genome in 2003 has been its functional annotation. DNA holds the instructions to the production of the components necessary for the life of cells and organisms. A complete functional catalog of genomic regions will help the understanding of the cell body and its dynamics, thus creating links between genotype and phenotypic traits. The need for annotations prompted the development of several bioinformatic methods. In the context of promoter and first exon predictors, the majority of models relies principally on structural and chemical properties of the DNA sequence. Some of them integrate information from epigenomic and transcriptomic data as secondary features. Current genomic research asserts that reference genome annotations are far from being fully annotated (human organism included).Physicians rely on reference genome annotations and functional databases to understand disorders with genetic basis, and missing annotations may lead to unresolved cases. Because of their complexity, neurodevelopmental disorders are under study to figure out all genetic regions that are involved. Besides functional validation on model organisms, the search for genotype-phenotype association is supported by statistical analysis, which is typically biased towards known functional regions.This thesis addresses the use of an in-silico integrative analysis to improve reference genome annotations and discover novel functional regions associated with neurodevelopemental disorders. The contributions outlined in this document have practical applications in clinical settings. The presented bioinformatic method is based on epigenomic and transcriptomic data, thus excluding features from DNA sequence. Such integrative approach applied on brain data allowed the discovery of two novel promoters and coding first exons in the human DLG2 gene, which were also found to be statistically associated with neurodevelopmental disorders and intellectual disability in particular. The application of the same methodology to the whole genome resulted in the discovery of other novel exons expressed in brain. Concerning the in-silico method itself, the research demanded a high number of functional and clinical datasets to properly support and validate our discoveries.This work describes a bioinformatic method for genome annotation, in the specific area of promoter and first exons. So far the method has been applied on brain data, and the extension to the whole body data would be a logical by-product. We will leverage distributed frameworks to tackle the even higher amount of data to analyse, a task that has already begun. Another interesting research direction that came up from this work is the temporal enrichment analysis of epigenomics data across different developmental stages, in which changes of epigenomic enrichment suggest time-specific and tissue-specific functional gene and gene isoforms regulation.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } An important quest in genomics since the publication of the first complete human genome in 2003 has been its functional annotation. DNA holds the instructions to the production of the components necessary for the life of cells and organisms. A complete functional catalog of genomic regions will help the understanding of the cell body and its dynamics, thus creating links between genotype and phenotypic traits. The need for annotations prompted the development of several bioinformatic methods. In the context of promoter and first exon predictors, the majority of models relies principally on structural and chemical properties of the DNA sequence. Some of them integrate information from epigenomic and transcriptomic data as secondary features. Current genomic research asserts that reference genome annotations are far from being fully annotated (human organism included).Physicians rely on reference genome annotations and functional databases to understand disorders with genetic basis, and missing annotations may lead to unresolved cases. Because of their complexity, neurodevelopmental disorders are under study to figure out all genetic regions that are involved. Besides functional validation on model organisms, the search for genotype-phenotype association is supported by statistical analysis, which is typically biased towards known functional regions.This thesis addresses the use of an in-silico integrative analysis to improve reference genome annotations and discover novel functional regions associated with neurodevelopemental disorders. The contributions outlined in this document have practical applications in clinical settings. The presented bioinformatic method is based on epigenomic and transcriptomic data, thus excluding features from DNA sequence. Such integrative approach applied on brain data allowed the discovery of two novel promoters and coding first exons in the human DLG2 gene, which were also found to be statistically associated with neurodevelopmental disorders and intellectual disability in particular. The application of the same methodology to the whole genome resulted in the discovery of other novel exons expressed in brain. Concerning the in-silico method itself, the research demanded a high number of functional and clinical datasets to properly support and validate our discoveries.This work describes a bioinformatic method for genome annotation, in the specific area of promoter and first exons. So far the method has been applied on brain data, and the extension to the whole body data would be a logical by-product. We will leverage distributed frameworks to tackle the even higher amount of data to analyse, a task that has already begun. Another interesting research direction that came up from this work is the temporal enrichment analysis of epigenomics data across different developmental stages, in which changes of epigenomic enrichment suggest time-specific and tissue-specific functional gene and gene isoforms regulation. |
Abels, Axel; Roijers, Diederik D M; Lenaerts, Tom Dynamic weights in multi-objective deep reinforcement learning Journal Article In: BNAIC, pp. 1-2, 2018, (Language of publication: en). @article{info:hdl:2013/296973, title = {Dynamic weights in multi-objective deep reinforcement learning}, author = {Axel Abels and Diederik D M Roijers and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/296973/3/abels2018bnaic.pdf}, year = {2018}, date = {2018-01-01}, journal = {BNAIC}, pages = {1-2}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2017 |
Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Commitment and participation in public goods games Journal Article In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 3 , pp. 1431-1432, 2017, (Language of publication: en). @article{info:hdl:2013/290973, title = {Commitment and participation in public goods games}, author = {The Anh T A H Han and Lu{'i}s Marcelo Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/290973}, year = {2017}, date = {2017-01-01}, journal = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS}, volume = {3}, pages = {1431-1432}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
'i, Lu; Lenaerts, Tom; Martinez-Vaquero, Luis L A; Han, The Anh T A H Social manifestation of guilt leads to stable cooperation in multi-agent systems Journal Article In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 3 , pp. 1421-1430, 2017, (Language of publication: en). @article{info:hdl:2013/271395, title = {Social manifestation of guilt leads to stable cooperation in multi-agent systems}, author = {Lu{'i}s Moniz Pereira and Tom Lenaerts and Luis L A Martinez-Vaquero and The Anh T A H Han}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/271395}, year = {2017}, date = {2017-01-01}, journal = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS}, volume = {3}, pages = {1421-1430}, abstract = {Inspired by psychological and evolutionary studies, we present here theoretical models wherein agents have the potential to express guilt with the ambition to study the role of this emotion in the promotion of pro-social behaviour. To achieve this goal, analytical and numerical methods from evolutionary game theory are employed to identify the conditions for which enhanced cooperation emerges within the context of the iterated prisoners dilemma. Guilt is modelled explicitly as two features, i.e. A counter that keeps track of the number of transgressions and a threshold that dictates when alleviation (through for instance apology and self-punishment) is required for an emotional agent. Such an alleviation introduces an effect on the payoff of the agent experiencing guilt. We show that when the system consists of agents that resolve their guilt without considering the co-player's attitude towards guilt alleviation then cooperation does not emerge. In that case those guilt prone agents are easily dominated by agents expressing no guilt or having no incentive to alleviate the guilt they experience. When, on the other hand, the guilt prone focal agent requires that guilt only needs to be alleviated when guilt alleviation is also manifested by a defecting co-player, then cooperation may thrive. This observation remains consistent for a generalised model as is discussed in this article. In summary, our analysis provides important insights into the design of multi-agent and cognitive agent systems where the inclusion of guilt modelling can improve agents' cooperative behaviour and overall benefit.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } Inspired by psychological and evolutionary studies, we present here theoretical models wherein agents have the potential to express guilt with the ambition to study the role of this emotion in the promotion of pro-social behaviour. To achieve this goal, analytical and numerical methods from evolutionary game theory are employed to identify the conditions for which enhanced cooperation emerges within the context of the iterated prisoners dilemma. Guilt is modelled explicitly as two features, i.e. A counter that keeps track of the number of transgressions and a threshold that dictates when alleviation (through for instance apology and self-punishment) is required for an emotional agent. Such an alleviation introduces an effect on the payoff of the agent experiencing guilt. We show that when the system consists of agents that resolve their guilt without considering the co-player's attitude towards guilt alleviation then cooperation does not emerge. In that case those guilt prone agents are easily dominated by agents expressing no guilt or having no incentive to alleviate the guilt they experience. When, on the other hand, the guilt prone focal agent requires that guilt only needs to be alleviated when guilt alleviation is also manifested by a defecting co-player, then cooperation may thrive. This observation remains consistent for a generalised model as is discussed in this article. In summary, our analysis provides important insights into the design of multi-agent and cognitive agent systems where the inclusion of guilt modelling can improve agents' cooperative behaviour and overall benefit. |
Kieken, Fabien; Loth, Karine; van Nuland, Nico A J; Tompa, Peter; Lenaerts, Tom Chemical shift assignments of the partially deuterated Fyn SH2-SH3 domain. Journal Article In: Biomolecular NMR assignments, 2017, (DOI: 10.1007/s12104-017-9792-1). @article{info:hdl:2013/262899, title = {Chemical shift assignments of the partially deuterated Fyn SH2-SH3 domain.}, author = {Fabien Kieken and Karine Loth and Nico A J van Nuland and Peter Tompa and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/262899}, year = {2017}, date = {2017-01-01}, journal = {Biomolecular NMR assignments}, abstract = {Src Homology 2 and 3 (SH2 and SH3) are two key protein interaction modules involved in regulating the activity of many proteins such as tyrosine kinases and phosphatases by respective recognition of phosphotyrosine and proline-rich regions. In the Src family kinases, the inactive state of the protein is the direct result of the interaction of the SH2 and the SH3 domain with intra-molecular regions, leading to a closed structure incompetent with substrate modification. Here, we report the 1H, 15N and 13C backbone- and side-chain chemical shift assignments of the partially deuterated Fyn SH3-SH2 domain and structural differences between tandem and single domains. The BMRB accession number is 27165.}, note = {DOI: 10.1007/s12104-017-9792-1}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src Homology 2 and 3 (SH2 and SH3) are two key protein interaction modules involved in regulating the activity of many proteins such as tyrosine kinases and phosphatases by respective recognition of phosphotyrosine and proline-rich regions. In the Src family kinases, the inactive state of the protein is the direct result of the interaction of the SH2 and the SH3 domain with intra-molecular regions, leading to a closed structure incompetent with substrate modification. Here, we report the 1H, 15N and 13C backbone- and side-chain chemical shift assignments of the partially deuterated Fyn SH3-SH2 domain and structural differences between tandem and single domains. The BMRB accession number is 27165. |
Gazzo, Andrea; Raimondi, Daniele; Daneels, Dorien; Moreau, Yves; Smits, Guillaume; Dooren, Sonia Van; Lenaerts, Tom Understanding mutational effects in digenic diseases Journal Article In: Nucleic acids research, 45 (15), 2017, (DOI: 10.1093/nar/gkx557). @article{info:hdl:2013/261811, title = {Understanding mutational effects in digenic diseases}, author = {Andrea Gazzo and Daniele Raimondi and Dorien Daneels and Yves Moreau and Guillaume Smits and Sonia Van Dooren and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/261811/4/doi_245438.pdf}, year = {2017}, date = {2017-01-01}, journal = {Nucleic acids research}, volume = {45}, number = {15}, abstract = {To further our understanding of the complexity and genetic heterogeneity of rare diseases, it has become essential to shed light on how combinations of variants in different genes are responsible for a disease phenotype. With the appearance of a resource on digenic diseases, it has become possible to evaluate how digenic combinations differ in terms of the phenotypes they produce. All instances in this resource were assigned to two classes of digenic effects, annotated as true digenic and composite classes. Whereas in the true digenic class variants in both genes are required for developing the disease, in the composite class, a variant in one gene is sufficient to produce the phenotype, but an additional variant in a second gene impacts the disease phenotype or alters the age of onset. We show that a combination of variant, gene and higher-level features can differentiate between these two classes with high accuracy. Moreover, we show via the analysis of three digenic disorders that a digenic effect decision profile, extracted from the predictive model, motivates why an instance was assigned to either of the two classes. Together, our results show that digenic disease data generates novel insights, providing a glimpse into the oligogenic realm.}, note = {DOI: 10.1093/nar/gkx557}, keywords = {}, pubstate = {published}, tppubtype = {article} } To further our understanding of the complexity and genetic heterogeneity of rare diseases, it has become essential to shed light on how combinations of variants in different genes are responsible for a disease phenotype. With the appearance of a resource on digenic diseases, it has become possible to evaluate how digenic combinations differ in terms of the phenotypes they produce. All instances in this resource were assigned to two classes of digenic effects, annotated as true digenic and composite classes. Whereas in the true digenic class variants in both genes are required for developing the disease, in the composite class, a variant in one gene is sufficient to produce the phenotype, but an additional variant in a second gene impacts the disease phenotype or alters the age of onset. We show that a combination of variant, gene and higher-level features can differentiate between these two classes with high accuracy. Moreover, we show via the analysis of three digenic disorders that a digenic effect decision profile, extracted from the predictive model, motivates why an instance was assigned to either of the two classes. Together, our results show that digenic disease data generates novel insights, providing a glimpse into the oligogenic realm. |
Reggiani, Claudio; Coppens, Sandra; Sekhara, Tayeb; Dimov, Ivan; Pichon, Bruno; Lufin, Nicolas; Addor, Marie Claude; Belligni, Elga Fabia; Digilio, Maria Cristina; Faletra, Flavio; Ferrero, Giovanni Battista; Gerard, Marion; Isidor, Bertrand; Joss, Shelagh; Niel-Bütschi, Florence; Perrone, Maria Dolores; Petit, Florence; Renieri, Alessandra; Romana, Serge; Topa, Alexandra; Vermeesch, Joris Robert; Lenaerts, Tom; Casimir, Georges; Abramowicz, Marc; Bontempi, Gianluca; Vilain, Catheline; Deconinck, Nicolas; Smits, Guillaume Novel promoters and coding first exons in DLG2 linked to developmental disorders and intellectual disability. Journal Article In: Genome medicine, 9 (1), pp. 67, 2017, (DOI: 10.1186/s13073-017-0452-y). @article{info:hdl:2013/258564, title = {Novel promoters and coding first exons in DLG2 linked to developmental disorders and intellectual disability.}, author = {Claudio Reggiani and Sandra Coppens and Tayeb Sekhara and Ivan Dimov and Bruno Pichon and Nicolas Lufin and Marie Claude Addor and Elga Fabia Belligni and Maria Cristina Digilio and Flavio Faletra and Giovanni Battista Ferrero and Marion Gerard and Bertrand Isidor and Shelagh Joss and Florence Niel-Bütschi and Maria Dolores Perrone and Florence Petit and Alessandra Renieri and Serge Romana and Alexandra Topa and Joris Robert Vermeesch and Tom Lenaerts and Georges Casimir and Marc Abramowicz and Gianluca Bontempi and Catheline Vilain and Nicolas Deconinck and Guillaume Smits}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/258564/1/doi_242191.pdf}, year = {2017}, date = {2017-01-01}, journal = {Genome medicine}, volume = {9}, number = {1}, pages = {67}, abstract = {Tissue-specific integrative omics has the potential to reveal new genic elements important for developmental disorders.}, note = {DOI: 10.1186/s13073-017-0452-y}, keywords = {}, pubstate = {published}, tppubtype = {article} } Tissue-specific integrative omics has the potential to reveal new genic elements important for developmental disorders. |
Byrski, Aleksander; 'S, Ewelina ; Ł, Jakub ; Kisiel-Dorohinicki, Marek; Lenaerts, Tom; Samson, Dana; Indurkhya, Bipin; Nowe, Ann Socio-cognitively inspired ant colony optimization Journal Article In: Journal of Computational Science, 21 , pp. 397-406, 2017, (DOI: 10.1016/j.jocs.2016.10.010). @article{info:hdl:2013/256822, title = {Socio-cognitively inspired ant colony optimization}, author = {Aleksander Byrski and Ewelina {'S}widerska and Jakub {Ł}asisz and Marek Kisiel-Dorohinicki and Tom Lenaerts and Dana Samson and Bipin Indurkhya and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/256822/1/Elsevier_240449.pdf}, year = {2017}, date = {2017-01-01}, journal = {Journal of Computational Science}, volume = {21}, pages = {397-406}, abstract = {Recently we proposed an application of ant colony optimization (ACO) to simulate socio-cognitive features of a population, incorporating perspective-taking ability to generate differently acting ant colonies. Although our main goal was simulation, we took advantage of the fact that the quality of the constructed system was evaluated based on selected traveling salesman problem instances, and the resulting computing system became a metaheuristic, which turned out to be a promising method for solving discrete problems. In this paper, we extend the initial sets of populations driven by different perspective-taking inspirations, seeking both optimal configuration for solving a number of TSP benchmarks, at the same time constituting a tool for analyzing socio-cognitive features of the individuals involved. The proposed algorithms are compared against classic ACO, and are found to prevail in most of the benchmark functions tested.}, note = {DOI: 10.1016/j.jocs.2016.10.010}, keywords = {}, pubstate = {published}, tppubtype = {article} } Recently we proposed an application of ant colony optimization (ACO) to simulate socio-cognitive features of a population, incorporating perspective-taking ability to generate differently acting ant colonies. Although our main goal was simulation, we took advantage of the fact that the quality of the constructed system was evaluated based on selected traveling salesman problem instances, and the resulting computing system became a metaheuristic, which turned out to be a promising method for solving discrete problems. In this paper, we extend the initial sets of populations driven by different perspective-taking inspirations, seeking both optimal configuration for solving a number of TSP benchmarks, at the same time constituting a tool for analyzing socio-cognitive features of the individuals involved. The proposed algorithms are compared against classic ACO, and are found to prevail in most of the benchmark functions tested. |
Martinez-Vaquero, Luis L A; Han, The Anh T A H; 'i, Lu; Lenaerts, Tom When agreement-accepting free-riders are a necessary evil for the evolution of cooperation. Journal Article In: Scientific reports, 7 (1), pp. 2478, 2017, (DOI: 10.1038/s41598-017-02625-z). @article{info:hdl:2013/256610, title = {When agreement-accepting free-riders are a necessary evil for the evolution of cooperation.}, author = {Luis L A Martinez-Vaquero and The Anh T A H Han and Lu{'i}s Moniz Pereira and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/256610/4/doi_240237.pdf}, year = {2017}, date = {2017-01-01}, journal = {Scientific reports}, volume = {7}, number = {1}, pages = {2478}, abstract = {Agreements and commitments have provided a novel mechanism to promote cooperation in social dilemmas in both one-shot and repeated games. Individuals requesting others to commit to cooperate (proposers) incur a cost, while their co-players are not necessarily required to pay any, allowing them to free-ride on the proposal investment cost (acceptors). Although there is a clear complementarity in these behaviours, no dynamic evidence is currently available that proves that they coexist in different forms of commitment creation. Using a stochastic evolutionary model allowing for mixed population states, we identify non-trivial roles of acceptors as well as the importance of intention recognition in commitments. In the one-shot prisoner's dilemma, alliances between proposers and acceptors are necessary to isolate defectors when proposers do not know the acceptance intentions of the others. However, when the intentions are clear beforehand, the proposers can emerge by themselves. In repeated games with noise, the incapacity of proposers and acceptors to set up alliances makes the emergence of the first harder whenever the latter are present. As a result, acceptors will exploit proposers and take over the population when an apology-forgiveness mechanism with too low apology cost is introduced, and hence reduce the overall cooperation level.}, note = {DOI: 10.1038/s41598-017-02625-z}, keywords = {}, pubstate = {published}, tppubtype = {article} } Agreements and commitments have provided a novel mechanism to promote cooperation in social dilemmas in both one-shot and repeated games. Individuals requesting others to commit to cooperate (proposers) incur a cost, while their co-players are not necessarily required to pay any, allowing them to free-ride on the proposal investment cost (acceptors). Although there is a clear complementarity in these behaviours, no dynamic evidence is currently available that proves that they coexist in different forms of commitment creation. Using a stochastic evolutionary model allowing for mixed population states, we identify non-trivial roles of acceptors as well as the importance of intention recognition in commitments. In the one-shot prisoner's dilemma, alliances between proposers and acceptors are necessary to isolate defectors when proposers do not know the acceptance intentions of the others. However, when the intentions are clear beforehand, the proposers can emerge by themselves. In repeated games with noise, the incapacity of proposers and acceptors to set up alliances makes the emergence of the first harder whenever the latter are present. As a result, acceptors will exploit proposers and take over the population when an apology-forgiveness mechanism with too low apology cost is introduced, and hence reduce the overall cooperation level. |
Orlando, Gabriele; Raimondi, Daniele; Khanna, T; Lenaerts, Tom; Vranken, Wim F SVM-dependent pairwise HMM: an application to Protein pairwise alignments. Journal Article In: Bioinformatics, 2017, (DOI: 10.1093/bioinformatics/btx391). @article{info:hdl:2013/254251, title = {SVM-dependent pairwise HMM: an application to Protein pairwise alignments.}, author = {Gabriele Orlando and Daniele Raimondi and T Khanna and Tom Lenaerts and Wim F Vranken}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/254251}, year = {2017}, date = {2017-01-01}, journal = {Bioinformatics}, abstract = {Methods able to provide reliable protein alignments are crucial for many bioinformatics applications. In the last years many different algorithms have been developed and various kinds of information, from sequence conservation to secondary structure, have been used to improve the alignment performances. This is especially relevant for proteins with highly divergent sequences. However, recent works suggest that different features may have different importance in diverse protein classes and it would be an advantage to have more customizable approaches, capable to deal with different alignment definitions.}, note = {DOI: 10.1093/bioinformatics/btx391}, keywords = {}, pubstate = {published}, tppubtype = {article} } Methods able to provide reliable protein alignments are crucial for many bioinformatics applications. In the last years many different algorithms have been developed and various kinds of information, from sequence conservation to secondary structure, have been used to improve the alignment performances. This is especially relevant for proteins with highly divergent sequences. However, recent works suggest that different features may have different importance in diverse protein classes and it would be an advantage to have more customizable approaches, capable to deal with different alignment definitions. |
Raimondi, Daniele; c c, Ibrahim Tanyal; Ferte, Julien; Gazzo, Andrea; Orlando, Gabriele; Lenaerts, Tom; Rooman, Marianne; Vranken, Wim F DEOGEN2: prediction and interactive visualization of single amino acid variant deleteriousness in human proteins. Journal Article In: Nucleic acids research, 45 (W1), pp. W201-W206, 2017, (DOI: 10.1093/nar/gkx390). @article{info:hdl:2013/254250, title = {DEOGEN2: prediction and interactive visualization of single amino acid variant deleteriousness in human proteins.}, author = {Daniele Raimondi and Ibrahim Tanyal{c c}in and Julien Ferte and Andrea Gazzo and Gabriele Orlando and Tom Lenaerts and Marianne Rooman and Wim F Vranken}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/254250}, year = {2017}, date = {2017-01-01}, journal = {Nucleic acids research}, volume = {45}, number = {W1}, pages = {W201-W206}, abstract = {High-throughput sequencing methods are generating enormous amounts of genomic data, giving unprecedented insights into human genetic variation and its relation to disease. An individual human genome contains millions of Single Nucleotide Variants: to discriminate the deleterious from the benign ones, a variety of methods have been developed that predict whether a protein-coding variant likely affects the carrier individual's health. We present such a method, DEOGEN2, which incorporates heterogeneous information about the molecular effects of the variants, the domains involved, the relevance of the gene and the interactions in which it participates. This extensive contextual information is non-linearly mapped into one single deleteriousness score for each variant. Since for the non-expert user it is sometimes still difficult to assess what this score means, how it relates to the encoded protein, and where it originates from, we developed an interactive online framework (http://deogen2.mutaframe.com/) to better present the DEOGEN2 deleteriousness predictions of all possible variants in all human proteins. The prediction is visualized so both expert and non-expert users can gain insights into the meaning, protein context and origins of each prediction.}, note = {DOI: 10.1093/nar/gkx390}, keywords = {}, pubstate = {published}, tppubtype = {article} } High-throughput sequencing methods are generating enormous amounts of genomic data, giving unprecedented insights into human genetic variation and its relation to disease. An individual human genome contains millions of Single Nucleotide Variants: to discriminate the deleterious from the benign ones, a variety of methods have been developed that predict whether a protein-coding variant likely affects the carrier individual's health. We present such a method, DEOGEN2, which incorporates heterogeneous information about the molecular effects of the variants, the domains involved, the relevance of the gene and the interactions in which it participates. This extensive contextual information is non-linearly mapped into one single deleteriousness score for each variant. Since for the non-expert user it is sometimes still difficult to assess what this score means, how it relates to the encoded protein, and where it originates from, we developed an interactive online framework (http://deogen2.mutaframe.com/) to better present the DEOGEN2 deleteriousness predictions of all possible variants in all human proteins. The prediction is visualized so both expert and non-expert users can gain insights into the meaning, protein context and origins of each prediction. |
Bontempi, Gianluca; "e, Yann-A; Stefani, Jacopo De A Dynamic Factor Machine Learning Method for Multi-variate and Multi-step-Ahead Forecasting Inproceedings In: 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 222-231, 2017, (DOI: 10.1109/DSAA.2017.1). @inproceedings{info:hdl:2013/283239, title = {A Dynamic Factor Machine Learning Method for Multi-variate and Multi-step-Ahead Forecasting}, author = {Gianluca Bontempi and Yann-A{"e}l Le Borgne and Jacopo De Stefani}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/283239}, year = {2017}, date = {2017-01-01}, booktitle = {2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA)}, pages = {222-231}, abstract = {Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g. issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizon. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine learning version of the Dynamic Factor Model (DFM), a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will show that DFML can consistently outperform state-of-the-art methods in a number of synthetic and real forecasting tasks.}, note = {DOI: 10.1109/DSAA.2017.1}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g. issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizon. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine learning version of the Dynamic Factor Model (DFM), a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will show that DFML can consistently outperform state-of-the-art methods in a number of synthetic and real forecasting tasks. |
Stefani, Jacopo De; Caelen, Olivier; Hattab, Dalila; Bontempi, Gianluca Machine Learning for Multi-step Ahead Forecasting of Volatility Proxies Inproceedings In: 2nd Workshop on MIning DAta for financial applicationS (MIDAS), pp. 17-28, 2017, (Conference: MIDAS 2017(Skopje, Macedonia)). @inproceedings{info:hdl:2013/283252, title = {Machine Learning for Multi-step Ahead Forecasting of Volatility Proxies}, author = {Jacopo De Stefani and Olivier Caelen and Dalila Hattab and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/283252/1/MIDAS2017_paper3.pdf}, year = {2017}, date = {2017-01-01}, booktitle = {2nd Workshop on MIning DAta for financial applicationS (MIDAS)}, pages = {17-28}, series = {CEUR Workshop Proceedings}, abstract = {In finance, volatility is defined as a measure of variation ofa trading price series over time. As volatility is a latent variable, several measures, named proxies, have been proposed in the literature to represent such quantity. The purpose of our work is twofold. On one hand, weaim to perform a statistical assessment of the relationships among themost used proxies in the volatility literature. On the other hand, while the majority of the reviewed studies in the literature focuses on a univariate time series model (NAR), using a single proxy, we propose here a NARX model, combining two proxies to predict one of them, showing that it is possible to improve the prediction of the future value of some proxies by using the information provided by the others. Our results, employing artificial neural networks (ANN), k-Nearest Neighbours(kNN) and support vector regression (SVR), show that the supplementary information carried by the additional proxy could be used to reduce the forecasting error of the aforementioned methods. We conclude by explaining how we wish to further investigate such relationship.}, note = {Conference: MIDAS 2017(Skopje, Macedonia)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In finance, volatility is defined as a measure of variation ofa trading price series over time. As volatility is a latent variable, several measures, named proxies, have been proposed in the literature to represent such quantity. The purpose of our work is twofold. On one hand, weaim to perform a statistical assessment of the relationships among themost used proxies in the volatility literature. On the other hand, while the majority of the reviewed studies in the literature focuses on a univariate time series model (NAR), using a single proxy, we propose here a NARX model, combining two proxies to predict one of them, showing that it is possible to improve the prediction of the future value of some proxies by using the information provided by the others. Our results, employing artificial neural networks (ANN), k-Nearest Neighbours(kNN) and support vector regression (SVR), show that the supplementary information carried by the additional proxy could be used to reduce the forecasting error of the aforementioned methods. We conclude by explaining how we wish to further investigate such relationship. |
Huculeci, Radu Ion; Kieken, Fabien; Garcia-Pino, Abel; Buts, Lieven; van Nuland, Nico A J; Lenaerts, Tom Structural characterization of monomeric/dimeric state of p59fyn SH2 domain Book Chapter In: 1555 , pp. 555, Humana Press, 2017, (Language of publication: fr). @inbook{info:hdl:2013/243589, title = {Structural characterization of monomeric/dimeric state of p59fyn SH2 domain}, author = {Radu Ion Huculeci and Fabien Kieken and Abel Garcia-Pino and Lieven Buts and Nico A J van Nuland and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243589}, year = {2017}, date = {2017-01-01}, volume = {1555}, pages = {555}, publisher = {Humana Press}, note = {Language of publication: fr}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
Pereira, Luis Moniz; Lenaerts, Tom; Han, The Anh T A H; Martinez-Vaquero, Luis A Evolutionary Game Theory Modelling of Guilt Inproceedings In: Proceedings of the AISB Annual Convention, Symposium on Computational Modelling of Emotion: Theory and Applications, pp. 189-192, 2017, (Language of publication: en). @inproceedings{info:hdl:2013/262905, title = {Evolutionary Game Theory Modelling of Guilt}, author = {Luis Moniz Pereira and Tom Lenaerts and The Anh T A H Han and Luis A Martinez-Vaquero}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/262905}, year = {2017}, date = {2017-01-01}, booktitle = {Proceedings of the AISB Annual Convention, Symposium on Computational Modelling of Emotion: Theory and Applications}, pages = {189-192}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Lenaerts, Tom; Han, The Anh T A H; Pereira, Luis Moniz; Martinez-Vaquero, Luis A When apology is sincere, cooperation evolves, even when mistakes occur frequently Inproceedings In: Proceedings of the AISB Annual Convention, Symposium on Computational Modelling of Emotion: Theory and Applications, pp. 193-195, 2017, (Language of publication: en). @inproceedings{info:hdl:2013/262904, title = {When apology is sincere, cooperation evolves, even when mistakes occur frequently}, author = {Tom Lenaerts and The Anh T A H Han and Luis Moniz Pereira and Luis A Martinez-Vaquero}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/262904}, year = {2017}, date = {2017-01-01}, booktitle = {Proceedings of the AISB Annual Convention, Symposium on Computational Modelling of Emotion: Theory and Applications}, pages = {193-195}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Pereira, Luis Moniz; Lenaerts, Tom; Martinez-Vaquero, Luis A; others, Social manifestation of guilt leads to stable cooperation in multi-agent systems Inproceedings In: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems(AAMAS), pp. 1422-1430, 2017, (Language of publication: en). @inproceedings{info:hdl:2013/262903, title = {Social manifestation of guilt leads to stable cooperation in multi-agent systems}, author = {Luis Moniz Pereira and Tom Lenaerts and Luis A Martinez-Vaquero and others}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/262903}, year = {2017}, date = {2017-01-01}, booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems(AAMAS)}, pages = {1422-1430}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Han, The Anh T A H; 'i, Lu; Martinez-Vaquero, Luis A; Lenaerts, Tom Evolution of commitment and level of participation in public goods games. Inproceedings In: Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 1431-1432, 2017, (Language of publication: en). @inproceedings{info:hdl:2013/262902, title = {Evolution of commitment and level of participation in public goods games.}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Luis A Martinez-Vaquero and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/262902}, year = {2017}, date = {2017-01-01}, booktitle = {Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)}, pages = {1431-1432}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Cava, Claudia; Colaprico, Antonio; Bertoli, Gloria; Graudenzi, Alex; Silva, Tiago C; Olsen, Catharina; Noushmehr, Houtan; Bontempi, Gianluca; Mauri, Giancarlo; Castiglioni, Isabella SpidermiR: an R/Bioconductor package for integrative analysis with miRNA data Journal Article In: International journal of molecular sciences, 2017, (DOI: 10.3390/ijms18020274). @article{info:hdl:2013/245105, title = {SpidermiR: an R/Bioconductor package for integrative analysis with miRNA data}, author = {Claudia Cava and Antonio Colaprico and Gloria Bertoli and Alex Graudenzi and Tiago C Silva and Catharina Olsen and Houtan Noushmehr and Gianluca Bontempi and Giancarlo Mauri and Isabella Castiglioni}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/245105/3/doi_228732.pdf}, year = {2017}, date = {2017-01-01}, journal = {International journal of molecular sciences}, abstract = {Gene Regulatory Networks (GRNs) control many biological systems, but how such network coordination is shaped is still unknown. GRNs can be subdivided into basic connections that describe how the network members interact e.g., co-expression, physical interaction, co-localization, genetic influence, pathways, and shared protein domains. The important regulatory mechanisms of these networks involve miRNAs. We developed an R/Bioconductor package, namely SpidermiR, which offers an easy access to both GRNs and miRNAs to the end user, and integrates this information with differentially expressed genes obtained from The Cancer Genome Atlas. Specifically, SpidermiR allows the users to: (i) query and download GRNs and miRNAs from validated and predicted repositories; (ii) integrate miRNAs with GRNs in order to obtain miRNA--gene--gene and miRNA--protein--protein interactions, and to analyze miRNA GRNs in order to identify miRNA--gene communities; and (iii) graphically visualize the results of the analyses. These analyses can be performed through a single interface and without the need for any downloads. The full data sets are then rapidly integrated and processed locally.}, note = {DOI: 10.3390/ijms18020274}, keywords = {}, pubstate = {published}, tppubtype = {article} } Gene Regulatory Networks (GRNs) control many biological systems, but how such network coordination is shaped is still unknown. GRNs can be subdivided into basic connections that describe how the network members interact e.g., co-expression, physical interaction, co-localization, genetic influence, pathways, and shared protein domains. The important regulatory mechanisms of these networks involve miRNAs. We developed an R/Bioconductor package, namely SpidermiR, which offers an easy access to both GRNs and miRNAs to the end user, and integrates this information with differentially expressed genes obtained from The Cancer Genome Atlas. Specifically, SpidermiR allows the users to: (i) query and download GRNs and miRNAs from validated and predicted repositories; (ii) integrate miRNAs with GRNs in order to obtain miRNA--gene--gene and miRNA--protein--protein interactions, and to analyze miRNA GRNs in order to identify miRNA--gene communities; and (iii) graphically visualize the results of the analyses. These analyses can be performed through a single interface and without the need for any downloads. The full data sets are then rapidly integrated and processed locally. |
Carcillo, Fabrizio; Pozzolo, Andrea Dal; "e, Yann-A; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca SCARFF: a Scalable Framework for Streaming Credit Card Fraud Detection with Spark Journal Article In: Information fusion, 2017, (DOI: 10.1016/j.inffus.2017.09.005). @article{info:hdl:2013/258226, title = {SCARFF: a Scalable Framework for Streaming Credit Card Fraud Detection with Spark}, author = {Fabrizio Carcillo and Andrea Dal Pozzolo and Yann-A{"e}l Le Borgne and Olivier Caelen and Yannis Mazzer and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/258226/4/Elsevier_241853.pdf}, year = {2017}, date = {2017-01-01}, journal = {Information fusion}, abstract = {The expansion of the electronic commerce, together with an increasing confidence of customers in electronic payments, makes of fraud detection a critical factor. Detecting frauds in (nearly) real time setting demands the design and the implementation of scalable learning techniques able to ingest and analyse massive amounts of streaming data. Recent advances in analytics and the availability of open source solutions for Big Data storage and processing open new perspectives to the fraud detection field. In this paper we present a SCAlable Real-time Fraud Finder (SCARFF) which integrates Big Data tools (Kafka, Spark and Cassandra) with a machine learning approach which deals with imbalance, nonstationarity and feedback latency. Experimental results on a massive dataset of real credit card transactions show that this framework is scalable, efficient and accurate over a big stream of transactions.}, note = {DOI: 10.1016/j.inffus.2017.09.005}, keywords = {}, pubstate = {published}, tppubtype = {article} } The expansion of the electronic commerce, together with an increasing confidence of customers in electronic payments, makes of fraud detection a critical factor. Detecting frauds in (nearly) real time setting demands the design and the implementation of scalable learning techniques able to ingest and analyse massive amounts of streaming data. Recent advances in analytics and the availability of open source solutions for Big Data storage and processing open new perspectives to the fraud detection field. In this paper we present a SCAlable Real-time Fraud Finder (SCARFF) which integrates Big Data tools (Kafka, Spark and Cassandra) with a machine learning approach which deals with imbalance, nonstationarity and feedback latency. Experimental results on a massive dataset of real credit card transactions show that this framework is scalable, efficient and accurate over a big stream of transactions. |
Pham, Ngoc Cam; Haibe-Kains, Benjamin; Bellot, Pau; Bontempi, Gianluca; Meyer, Patrick E Study of Meta-analysis strategies for network inference using information-theoretic approaches Journal Article In: BioData Mining, 10 (1), 2017, (DOI: 10.1186/s13040-017-0136-6). @article{info:hdl:2013/259607, title = {Study of Meta-analysis strategies for network inference using information-theoretic approaches}, author = {Ngoc Cam Pham and Benjamin Haibe-Kains and Pau Bellot and Gianluca Bontempi and Patrick E Meyer}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/259607/3/doi_243234.pdf}, year = {2017}, date = {2017-01-01}, journal = {BioData Mining}, volume = {10}, number = {1}, abstract = {Background: Reverse engineering of gene regulatory networks (GRNs) from gene expression data is a classical challenge in systems biology. Thanks to high-throughput technologies, a massive amount of gene-expression data has been accumulated in the public repositories. Modelling GRNs from multiple experiments (also called integrative analysis) has; therefore, naturally become a standard procedure in modern computational biology. Indeed, such analysis is usually more robust than the traditional approaches, which suffer from experimental biases and the low number of samples by analysing individual datasets. To date, there are mainly two strategies for the problem of interest: the first one (``data merging'') merges all datasets together and then infers a GRN whereas the other (``networks ensemble'') infers GRNs from every dataset separately and then aggregates them using some ensemble rules (such as ranksum or weightsum). Unfortunately, a thorough comparison of these two approaches is lacking. Results: In this work, we are going to present another meta-analysis approach for inferring GRNs from multiple studies. Our proposed meta-analysis approach, adapted to methods based on pairwise measures such as correlation or mutual information, consists of two steps: aggregating matrices of the pairwise measures from every dataset followed by extracting the network from the meta-matrix. Afterwards, we evaluate the performance of the two commonly used approaches mentioned above and our presented approach with a systematic set of experiments based on in silico benchmarks. Conclusions: We proposed a first systematic evaluation of different strategies for reverse engineering GRNs from multiple datasets. Experiment results strongly suggest that assembling matrices of pairwise dependencies is a better strategy for network inference than the two commonly used ones.}, note = {DOI: 10.1186/s13040-017-0136-6}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Reverse engineering of gene regulatory networks (GRNs) from gene expression data is a classical challenge in systems biology. Thanks to high-throughput technologies, a massive amount of gene-expression data has been accumulated in the public repositories. Modelling GRNs from multiple experiments (also called integrative analysis) has; therefore, naturally become a standard procedure in modern computational biology. Indeed, such analysis is usually more robust than the traditional approaches, which suffer from experimental biases and the low number of samples by analysing individual datasets. To date, there are mainly two strategies for the problem of interest: the first one (``data merging'') merges all datasets together and then infers a GRN whereas the other (``networks ensemble'') infers GRNs from every dataset separately and then aggregates them using some ensemble rules (such as ranksum or weightsum). Unfortunately, a thorough comparison of these two approaches is lacking. Results: In this work, we are going to present another meta-analysis approach for inferring GRNs from multiple studies. Our proposed meta-analysis approach, adapted to methods based on pairwise measures such as correlation or mutual information, consists of two steps: aggregating matrices of the pairwise measures from every dataset followed by extracting the network from the meta-matrix. Afterwards, we evaluate the performance of the two commonly used approaches mentioned above and our presented approach with a systematic set of experiments based on in silico benchmarks. Conclusions: We proposed a first systematic evaluation of different strategies for reverse engineering GRNs from multiple datasets. Experiment results strongly suggest that assembling matrices of pairwise dependencies is a better strategy for network inference than the two commonly used ones. |
Pham, Ngoc Cam; Haibe-Kains, Benjamin; Bellot, Pau; Bontempi, Gianluca; Meyer, Patrick E Study of Meta-analysis Strategies for Network Inference Using Information-Theoretic Approaches Journal Article In: Proceedings - International Workshop on Database and Expert Systems Applications, pp. 76-83, 2017, (DOI: 10.1109/DEXA.2016.030). @article{info:hdl:2013/247710, title = {Study of Meta-analysis Strategies for Network Inference Using Information-Theoretic Approaches}, author = {Ngoc Cam Pham and Benjamin Haibe-Kains and Pau Bellot and Gianluca Bontempi and Patrick E Meyer}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/247710}, year = {2017}, date = {2017-01-01}, journal = {Proceedings - International Workshop on Database and Expert Systems Applications}, pages = {76-83}, abstract = {Reverse engineering of gene regulatory networks (GRNs) from gene expression data is a classical challenge insystems biology. Thanks to high-throughput technologies, amassive amount of gene-expression data has been accumulatedin the public repositories. Modelling GRNs from multipleexperiments (also called integrative analysis) has, therefore, naturally become a standard procedure in modern computational biology. Indeed, such analysis is usually more robustthan the traditional approaches focused on individual datasets, which typically suffer from some experimental bias and a smallnumber of samples. To date, there are mainly two strategies for the problemof interest: the first one ('data merging') merges all datasetstogether and then infers a GRN whereas the other ('networksensemble') infers GRNs from every dataset separately and thenaggregates them using some ensemble rules (such as ranksumor weightsum). Unfortunately, a thorough comparison of thesetwo approaches is lacking. In this paper, we evaluate the performances of various metaanalysis approaches mentioned above with a systematic set ofexperiments based on in silico benchmarks. Furthermore, wepresent a new meta-analysis approach for inferring GRNs frommultiple studies. Our proposed approach, adapted to methodsbased on pairwise measures such as correlation or mutualinformation, consists of two steps: aggregating matrices of thepairwise measures from every dataset followed by extractingthe network from the meta-matrix.}, note = {DOI: 10.1109/DEXA.2016.030}, keywords = {}, pubstate = {published}, tppubtype = {article} } Reverse engineering of gene regulatory networks (GRNs) from gene expression data is a classical challenge insystems biology. Thanks to high-throughput technologies, amassive amount of gene-expression data has been accumulatedin the public repositories. Modelling GRNs from multipleexperiments (also called integrative analysis) has, therefore, naturally become a standard procedure in modern computational biology. Indeed, such analysis is usually more robustthan the traditional approaches focused on individual datasets, which typically suffer from some experimental bias and a smallnumber of samples. To date, there are mainly two strategies for the problemof interest: the first one ('data merging') merges all datasetstogether and then infers a GRN whereas the other ('networksensemble') infers GRNs from every dataset separately and thenaggregates them using some ensemble rules (such as ranksumor weightsum). Unfortunately, a thorough comparison of thesetwo approaches is lacking. In this paper, we evaluate the performances of various metaanalysis approaches mentioned above with a systematic set ofexperiments based on in silico benchmarks. Furthermore, wepresent a new meta-analysis approach for inferring GRNs frommultiple studies. Our proposed approach, adapted to methodsbased on pairwise measures such as correlation or mutualinformation, consists of two steps: aggregating matrices of thepairwise measures from every dataset followed by extractingthe network from the meta-matrix. |
Pozzolo, Andrea Dal; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy Journal Article In: IEEE Transactions on Neural Networks and Learning Systems, 99 , 2017, (DOI: 10.1109/TNNLS.2017.2736643). @article{info:hdl:2013/258224, title = {Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy}, author = {Andrea Dal Pozzolo and Giacomo Boracchi and Olivier Caelen and Cesare Alippi and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/258224}, year = {2017}, date = {2017-01-01}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, volume = {99}, abstract = {Detecting frauds in credit card transactions is perhaps one of the best testbeds for computational intelligence algorithms. In fact, this problem involves a number of relevant challenges, namely: concept drift (customers' habits evolve and fraudsters change their strategies over time), class imbalance (genuine transactions far outnumber frauds), and verification latency (only a small set of transactions are timely checked by investigators). However, the vast majority of learning algorithms that have been proposed for fraud detection rely on assumptions that hardly hold in a real-world fraud-detection system (FDS). This lack of realism concerns two main aspects: 1) the way and timing with which supervised information is provided and 2) the measures used to assess fraud-detection performance. This paper has three major contributions. First, we propose, with the help of our industrial partner, a formalization of the fraud-detection problem that realistically describes the operating conditions of FDSs that everyday analyze massive streams of credit card transactions. We also illustrate the most appropriate performance measures to be used for fraud-detection purposes. Second, we design and assess a novel learning strategy that effectively addresses class imbalance, concept drift, and verification latency. Third, in our experiments, we demonstrate the impact of class unbalance and concept drift in a real-world data stream containing more than 75 million transactions, authorized over a time window of three years.}, note = {DOI: 10.1109/TNNLS.2017.2736643}, keywords = {}, pubstate = {published}, tppubtype = {article} } Detecting frauds in credit card transactions is perhaps one of the best testbeds for computational intelligence algorithms. In fact, this problem involves a number of relevant challenges, namely: concept drift (customers' habits evolve and fraudsters change their strategies over time), class imbalance (genuine transactions far outnumber frauds), and verification latency (only a small set of transactions are timely checked by investigators). However, the vast majority of learning algorithms that have been proposed for fraud detection rely on assumptions that hardly hold in a real-world fraud-detection system (FDS). This lack of realism concerns two main aspects: 1) the way and timing with which supervised information is provided and 2) the measures used to assess fraud-detection performance. This paper has three major contributions. First, we propose, with the help of our industrial partner, a formalization of the fraud-detection problem that realistically describes the operating conditions of FDSs that everyday analyze massive streams of credit card transactions. We also illustrate the most appropriate performance measures to be used for fraud-detection purposes. Second, we design and assess a novel learning strategy that effectively addresses class imbalance, concept drift, and verification latency. Third, in our experiments, we demonstrate the impact of class unbalance and concept drift in a real-world data stream containing more than 75 million transactions, authorized over a time window of three years. |
Xu, Taosheng; Le, Thuc Duy; Liu, Lin; Su, Ning; Wang, Rujing; Sun, Bingyu; Colaprico, Antonio; Bontempi, Gianluca; Li, Jiuyong CancerSubtypes: An R/Bioconductor package for molecular cancer subtype identification, validation and visualization Journal Article In: Bioinformatics, 33 (19), pp. 3131-3133, 2017, (DOI: 10.1093/bioinformatics/btx378). @article{info:hdl:2013/260704, title = {CancerSubtypes: An R/Bioconductor package for molecular cancer subtype identification, validation and visualization}, author = {Taosheng Xu and Thuc Duy Le and Lin Liu and Ning Su and Rujing Wang and Bingyu Sun and Antonio Colaprico and Gianluca Bontempi and Jiuyong Li}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/260704/1/doi_244331.pdf}, year = {2017}, date = {2017-01-01}, journal = {Bioinformatics}, volume = {33}, number = {19}, pages = {3131-3133}, abstract = {Summary Identifying molecular cancer subtypes from multi-omics data is an important step in the personalized medicine. We introduce CancerSubtypes, an R package for identifying cancer subtypes using multi-omics data, including gene expression, miRNA expression and DNA methylation data. CancerSubtypes integrates four main computational methods which are highly cited for cancer subtype identification and provides a standardized framework for data pre-processing, feature selection, and result follow-up analyses, including results computing, biology validation and visualization. The input and output of each step in the framework are packaged in the same data format, making it convenience to compare different methods. The package is useful for inferring cancer subtypes from an input genomic dataset, comparing the predictions from different well-known methods and testing new subtype discovery methods, as shown with different application scenarios in theSupplementary Material.}, note = {DOI: 10.1093/bioinformatics/btx378}, keywords = {}, pubstate = {published}, tppubtype = {article} } Summary Identifying molecular cancer subtypes from multi-omics data is an important step in the personalized medicine. We introduce CancerSubtypes, an R package for identifying cancer subtypes using multi-omics data, including gene expression, miRNA expression and DNA methylation data. CancerSubtypes integrates four main computational methods which are highly cited for cancer subtype identification and provides a standardized framework for data pre-processing, feature selection, and result follow-up analyses, including results computing, biology validation and visualization. The input and output of each step in the framework are packaged in the same data format, making it convenience to compare different methods. The package is useful for inferring cancer subtypes from an input genomic dataset, comparing the predictions from different well-known methods and testing new subtype discovery methods, as shown with different application scenarios in theSupplementary Material. |
Garaud, Soizic; Roufosse, Florence; Silva, Pushpamali De; Gu-Trantien, Chunyan; Lodewyckx, Jean Nicolas; Duvillier, Hugues; Dedeurwaerder, Sarah; Bizet, Martin; Defrance, Matthieu; c c, Fran; c c, Fran; Willard-Gallo, Karen In: European Journal of Immunology, 47 (1), pp. 168-179, 2017, (DOI: 10.1002/eji.201646373). @article{info:hdl:2013/244657, title = {FOXP1 is a regulator of quiescence in healthy human CD4+ T cells and is constitutively repressed in T cells from patients with lymphoproliferative disorders}, author = {Soizic Garaud and Florence Roufosse and Pushpamali De Silva and Chunyan Gu-Trantien and Jean Nicolas Lodewyckx and Hugues Duvillier and Sarah Dedeurwaerder and Martin Bizet and Matthieu Defrance and Fran{c c}ois Fuks and Fran{c c}oise Bex and Karen Willard-Gallo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/244657/3/244657.pdf}, year = {2017}, date = {2017-01-01}, journal = {European Journal of Immunology}, volume = {47}, number = {1}, pages = {168-179}, abstract = {The forkhead box P1 (FOXP1) transcription factor has been shown to regulate the generation and maintenance of quiescent na"ive murine T cells. In humans, FOXP1 expression has been correlated with overall survival in patients with peripheral T-cell lymphoma (PTCL), although its regulatory role in T-cell function is currently unknown. We found that FOXP1 is normally expressed in all human leukocyte subpopulations. Focusing on primary human CD4+ T cells, we show that nuclear expression of FOXP1 predominates in na"ive cells with significant downregulation detected in memory cells from blood and tonsils. FOXP1 is repressed following in vitro T-cell activation of na"ive T cells, and later re-established in memory CD4+ T cells, albeit at lower levels. DNA methylation analysis revealed that epigenetic mechanisms participate in regulating the human FOXP1 gene. ShRNA-mediated FOXP1 repression induces CD4+ T cells to enter the cell cycle, acquire memory-like markers and upregulate helper T-cell differentiation genes. In patients with lymphoproliferative disorders, FOXP1 expression is constitutionally repressed in the clonal T cells in parallel with overexpression of helper T-cell differentiation genes. Collectively, these data identify FOXP1 as an essential transcriptional regulator for primary human CD4+ T cells and suggest its potential important role in the development of PTCL.}, note = {DOI: 10.1002/eji.201646373}, keywords = {}, pubstate = {published}, tppubtype = {article} } The forkhead box P1 (FOXP1) transcription factor has been shown to regulate the generation and maintenance of quiescent na"ive murine T cells. In humans, FOXP1 expression has been correlated with overall survival in patients with peripheral T-cell lymphoma (PTCL), although its regulatory role in T-cell function is currently unknown. We found that FOXP1 is normally expressed in all human leukocyte subpopulations. Focusing on primary human CD4+ T cells, we show that nuclear expression of FOXP1 predominates in na"ive cells with significant downregulation detected in memory cells from blood and tonsils. FOXP1 is repressed following in vitro T-cell activation of na"ive T cells, and later re-established in memory CD4+ T cells, albeit at lower levels. DNA methylation analysis revealed that epigenetic mechanisms participate in regulating the human FOXP1 gene. ShRNA-mediated FOXP1 repression induces CD4+ T cells to enter the cell cycle, acquire memory-like markers and upregulate helper T-cell differentiation genes. In patients with lymphoproliferative disorders, FOXP1 expression is constitutionally repressed in the clonal T cells in parallel with overexpression of helper T-cell differentiation genes. Collectively, these data identify FOXP1 as an essential transcriptional regulator for primary human CD4+ T cells and suggest its potential important role in the development of PTCL. |
Jeschke, Jana; Bizet, Martin; Desmedt, Christine; Calonne, Emilie; Dedeurwaerder, Sarah; Garaud, Soizic; Koch, Alexander; Larsimont, Denis; Salgado, Roberto; den Eynden, Gert Van; Willard-Gallo, Karen; Bontempi, Gianluca; Defrance, Matthieu; Sotiriou, Christos; c c, Fran DNA methylation-based immune response signature improves patient diagnosis in multiple cancers. Journal Article In: The Journal of clinical investigation, 127 (8), pp. 3090-3102, 2017, (DOI: 10.1172/JCI91095). @article{info:hdl:2013/265312, title = {DNA methylation-based immune response signature improves patient diagnosis in multiple cancers.}, author = {Jana Jeschke and Martin Bizet and Christine Desmedt and Emilie Calonne and Sarah Dedeurwaerder and Soizic Garaud and Alexander Koch and Denis Larsimont and Roberto Salgado and Gert Van den Eynden and Karen Willard-Gallo and Gianluca Bontempi and Matthieu Defrance and Christos Sotiriou and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/265312/6/doi_248939.pdf}, year = {2017}, date = {2017-01-01}, journal = {The Journal of clinical investigation}, volume = {127}, number = {8}, pages = {3090-3102}, abstract = {The tumor immune response is increasingly associated with better clinical outcomes in breast and other cancers. However, the evaluation of tumor-infiltrating lymphocytes (TILs) relies on histopathological measurements with limited accuracy and reproducibility. Here, we profiled DNA methylation markers to identify a methylation of TIL (MeTIL) signature that recapitulates TIL evaluations and their prognostic value for long-term outcomes in breast cancer (BC).}, note = {DOI: 10.1172/JCI91095}, keywords = {}, pubstate = {published}, tppubtype = {article} } The tumor immune response is increasingly associated with better clinical outcomes in breast and other cancers. However, the evaluation of tumor-infiltrating lymphocytes (TILs) relies on histopathological measurements with limited accuracy and reproducibility. Here, we profiled DNA methylation markers to identify a methylation of TIL (MeTIL) signature that recapitulates TIL evaluations and their prognostic value for long-term outcomes in breast cancer (BC). |
Lipski, D; Dewispelaere, Remi; Foucart, Vincent; Caspers, Laure; Defrance, Matthieu; Bruyns, Catherine; Willermain, Francois MHC class II expression and potential antigen-presenting cells in the retina during experimental autoimmune uveitis Journal Article In: Journal of neuroinflammation, 14 (1), 2017, (DOI: 10.1186/s12974-017-0915-5). @article{info:hdl:2013/258861, title = {MHC class II expression and potential antigen-presenting cells in the retina during experimental autoimmune uveitis}, author = {D Lipski and Remi Dewispelaere and Vincent Foucart and Laure Caspers and Matthieu Defrance and Catherine Bruyns and Francois Willermain}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/258861/1/doi_242488.pdf}, year = {2017}, date = {2017-01-01}, journal = {Journal of neuroinflammation}, volume = {14}, number = {1}, abstract = {Background: Controversy exists regarding which cell types are responsible for autoantigen presentation in the retina during experimental autoimmune uveitis (EAU) development. In this study, we aimed to identify and characterize the retinal resident and infiltrating cells susceptible to express major histocompatibility complex (MHC) class II during EAU. Methods: EAU was induced in C57BL/6 mice by adoptive transfer of autoreactive lymphocytes from IRBP1-20-immunized animals. MHC class II expression was studied by immunostainings on eye cryosections. For flow cytometry (FC) analysis, retinas were dissected and enzymatically digested into single-cell suspensions. Three MHC class II+ retinal cell populations were sorted by FC, and their RNA processed for RNA-Seq. Results: Immunostainings demonstrate strong induction of MHC class II expression in EAU, especially in the inner retina at the level of inflamed vessels, extending to the outer retinal layers and the subretinal space in severely inflamed eyes. Most MHC class II+ cells express the hematopoietic marker IBA1. FC quantitative analyses demonstrate that MHC class II induction significantly correlates with disease severity and is associated with upregulation of co-stimulatory molecule expression. In particular, most MHC class IIhi cells express co-stimulatory molecules during EAU. Further phenotyping identified three MHC class II+ retinal cell populations: CD45-CD11b- non-hematopoietic cells with low MHC class II expression and CD45+CD11b+ hematopoietic cells with higher MHC class II expression, which can be further separated into Ly6C+ and Ly6C- cells, possibly corresponding to infiltrating macrophages and resident microglia. Transcriptome analysis of the three sorted populations leads to a clear sample clustering with some enrichment in macrophage markers and microglial cell markers in Ly6C+ and Ly6C- cells, respectively. Functional annotation analysis reveals that both hematopoietic cell populations are more competent in MHC class II-associated antigen presentation and in T cell activation than non-hematopoietic cells. Conclusion: Our results highlight the potential of cells of hematopoietic origin in local antigen presentation, whatever their Ly6C expression. Our work further provides a first transcriptomic study of MHC class II-expressing retinal cells during EAU and delivers a series of new candidate genes possibly implicated in the pathogenesis of retinal autoimmunity.}, note = {DOI: 10.1186/s12974-017-0915-5}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Controversy exists regarding which cell types are responsible for autoantigen presentation in the retina during experimental autoimmune uveitis (EAU) development. In this study, we aimed to identify and characterize the retinal resident and infiltrating cells susceptible to express major histocompatibility complex (MHC) class II during EAU. Methods: EAU was induced in C57BL/6 mice by adoptive transfer of autoreactive lymphocytes from IRBP1-20-immunized animals. MHC class II expression was studied by immunostainings on eye cryosections. For flow cytometry (FC) analysis, retinas were dissected and enzymatically digested into single-cell suspensions. Three MHC class II+ retinal cell populations were sorted by FC, and their RNA processed for RNA-Seq. Results: Immunostainings demonstrate strong induction of MHC class II expression in EAU, especially in the inner retina at the level of inflamed vessels, extending to the outer retinal layers and the subretinal space in severely inflamed eyes. Most MHC class II+ cells express the hematopoietic marker IBA1. FC quantitative analyses demonstrate that MHC class II induction significantly correlates with disease severity and is associated with upregulation of co-stimulatory molecule expression. In particular, most MHC class IIhi cells express co-stimulatory molecules during EAU. Further phenotyping identified three MHC class II+ retinal cell populations: CD45-CD11b- non-hematopoietic cells with low MHC class II expression and CD45+CD11b+ hematopoietic cells with higher MHC class II expression, which can be further separated into Ly6C+ and Ly6C- cells, possibly corresponding to infiltrating macrophages and resident microglia. Transcriptome analysis of the three sorted populations leads to a clear sample clustering with some enrichment in macrophage markers and microglial cell markers in Ly6C+ and Ly6C- cells, respectively. Functional annotation analysis reveals that both hematopoietic cell populations are more competent in MHC class II-associated antigen presentation and in T cell activation than non-hematopoietic cells. Conclusion: Our results highlight the potential of cells of hematopoietic origin in local antigen presentation, whatever their Ly6C expression. Our work further provides a first transcriptomic study of MHC class II-expressing retinal cells during EAU and delivers a series of new candidate genes possibly implicated in the pathogenesis of retinal autoimmunity. |
2016 |
Bugajski, Iwan; Byrski, Aleksander; Kisiel-Dorohinicki, Marek; Lenaerts, Tom; Samson, Dana; Indurkhya, Bipin Adaptation of Population Structure in Socio-cognitive Particle Swarm Optimization Journal Article In: Procedia Computer Science, 101 , pp. 177-186, 2016, (DOI: 10.1016/j.procs.2016.11.022). @article{info:hdl:2013/247231, title = {Adaptation of Population Structure in Socio-cognitive Particle Swarm Optimization}, author = {Iwan Bugajski and Aleksander Byrski and Marek Kisiel-Dorohinicki and Tom Lenaerts and Dana Samson and Bipin Indurkhya}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/247231/1/Elsevier_230858.pdf}, year = {2016}, date = {2016-01-01}, journal = {Procedia Computer Science}, volume = {101}, pages = {177-186}, abstract = {In the paper a modification of a Socio-cognitive Particle Swarm Optimization algorithm, recently proposed by the authors, is presented. This modification consists in devising a mechanism for dynamic adaptation of the population structure of the swarm. Besides the design and rationale for the approach, referring to the state-of-the-art PSO original algorithm and several of its modifications, experimental results tackling popular benchmark functions are presented and discussed in detail.}, note = {DOI: 10.1016/j.procs.2016.11.022}, keywords = {}, pubstate = {published}, tppubtype = {article} } In the paper a modification of a Socio-cognitive Particle Swarm Optimization algorithm, recently proposed by the authors, is presented. This modification consists in devising a mechanism for dynamic adaptation of the population structure of the swarm. Besides the design and rationale for the approach, referring to the state-of-the-art PSO original algorithm and several of its modifications, experimental results tackling popular benchmark functions are presented and discussed in detail. |
Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Evolution of commitment and level of participation in public goods games Journal Article In: Autonomous agents and multi-agent systems, pp. 24, 2016, (DOI: 10.1007/s10458-016-9338-4). @article{info:hdl:2013/243591, title = {Evolution of commitment and level of participation in public goods games}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243591}, year = {2016}, date = {2016-01-01}, journal = {Autonomous agents and multi-agent systems}, pages = {24}, abstract = {Before engaging in a group venture agents may require commitments from other members in the group, and based on the level of acceptance (participation) they can then decide whether it is worthwhile joining the group effort. Here, we show in the context of public goods games and using stochastic evolutionary game theory modelling, which implies imitation and mutation dynamics, that arranging prior commitments while imposing a minimal participation when interacting in groups induces agents to behave cooperatively. Our analytical and numerical results show that if the cost of arranging the commitment is sufficiently small compared to the cost of cooperation, commitment arranging behavior is frequent, leading to a high level of cooperation in the population. Moreover, an optimal participation level emerges depending both on the dilemma at stake and on the cost of arranging the commitment. Namely, the harsher the common good dilemma is, and the costlier it becomes to arrange the commitment, the more participants should explicitly commit to the agreement to ensure the success of the joint venture. Furthermore, considering that commitment deals may last for more than one encounter, we show that commitment proposers can be lenient in case of short-term agreements, yet should be strict in case of long-term interactions.}, note = {DOI: 10.1007/s10458-016-9338-4}, keywords = {}, pubstate = {published}, tppubtype = {article} } Before engaging in a group venture agents may require commitments from other members in the group, and based on the level of acceptance (participation) they can then decide whether it is worthwhile joining the group effort. Here, we show in the context of public goods games and using stochastic evolutionary game theory modelling, which implies imitation and mutation dynamics, that arranging prior commitments while imposing a minimal participation when interacting in groups induces agents to behave cooperatively. Our analytical and numerical results show that if the cost of arranging the commitment is sufficiently small compared to the cost of cooperation, commitment arranging behavior is frequent, leading to a high level of cooperation in the population. Moreover, an optimal participation level emerges depending both on the dilemma at stake and on the cost of arranging the commitment. Namely, the harsher the common good dilemma is, and the costlier it becomes to arrange the commitment, the more participants should explicitly commit to the agreement to ensure the success of the joint venture. Furthermore, considering that commitment deals may last for more than one encounter, we show that commitment proposers can be lenient in case of short-term agreements, yet should be strict in case of long-term interactions. |
Martinez-Vaquero, Luis L A; Gruji'c, Jelena; Lenaerts, Tom Equivalence of cooperation indexes: Comment on Universal scaling for the dilemma strength in evolutionary games by Z. Wang et al. Journal Article In: Physics of life reviews, 16 , pp. 196-197, 2016, (DOI: 10.1016/j.plrev.2015.07.005). @article{info:hdl:2013/243586, title = {Equivalence of cooperation indexes: Comment on Universal scaling for the dilemma strength in evolutionary games by Z. Wang et al.}, author = {Luis L A Martinez-Vaquero and Jelena Gruji'c and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243586}, year = {2016}, date = {2016-01-01}, journal = {Physics of life reviews}, volume = {16}, pages = {196-197}, note = {DOI: 10.1016/j.plrev.2015.07.005}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Bugajski, Iwan; Listkiewicz, Piotr; Byrski, Aleksander; Kisiel-Dorohinicki, Marek; Korczynski, Wojciech; Lenaerts, Tom; Samson, Dana; Indurkhya, Bipin; Nowe, Ann Enhancing particle swarm optimization with socio-cognitive inspirations Journal Article In: Procedia Computer Science, 80 , pp. 804-813, 2016, (DOI: 10.1016/j.procs.2016.05.370). @article{info:hdl:2013/240085, title = {Enhancing particle swarm optimization with socio-cognitive inspirations}, author = {Iwan Bugajski and Piotr Listkiewicz and Aleksander Byrski and Marek Kisiel-Dorohinicki and Wojciech Korczynski and Tom Lenaerts and Dana Samson and Bipin Indurkhya and Ann Nowe}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/240085/4/doi_223712.pdf}, year = {2016}, date = {2016-01-01}, journal = {Procedia Computer Science}, volume = {80}, pages = {804-813}, abstract = {We incorporate socio-cognitively inspired metaheuristics, which we have used successfully in the ACO algorithms in our past research, into the classical particle swarm optimization algorithms. The swarm is divided into species and the particles get inspired not only by the global and local optima, but share their knowledge of the optima with neighboring agents belonging to other species. Our experimental research gathered for common benchmark functions tackled in 100 dimensions show that the metaheuristics are effective and perform better than the classic PSO. We experimented with various proportions of different species in the swarm population to find the best mix of population.}, note = {DOI: 10.1016/j.procs.2016.05.370}, keywords = {}, pubstate = {published}, tppubtype = {article} } We incorporate socio-cognitively inspired metaheuristics, which we have used successfully in the ACO algorithms in our past research, into the classical particle swarm optimization algorithms. The swarm is divided into species and the particles get inspired not only by the global and local optima, but share their knowledge of the optima with neighboring agents belonging to other species. Our experimental research gathered for common benchmark functions tackled in 100 dimensions show that the metaheuristics are effective and perform better than the classic PSO. We experimented with various proportions of different species in the swarm population to find the best mix of population. |
Huculeci, Radu Ion; Cilia, Elisa; Lyczek, Agatha; Buts, Lieven; Houben, Klaartje; Seeliger, Markus MA; van Nuland, Nico A J; Lenaerts, Tom Dynamically Coupled Residues within the SH2 Domain of FYN Are Key to Unlocking Its Activity. Journal Article In: Structure, 24 (11), pp. 1947-1959, 2016, (DOI: 10.1016/j.str.2016.08.016). @article{info:hdl:2013/239815, title = {Dynamically Coupled Residues within the SH2 Domain of FYN Are Key to Unlocking Its Activity.}, author = {Radu Ion Huculeci and Elisa Cilia and Agatha Lyczek and Lieven Buts and Klaartje Houben and Markus MA Seeliger and Nico A J van Nuland and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/239815/4/elsevier_223442.pdf}, year = {2016}, date = {2016-01-01}, journal = {Structure}, volume = {24}, number = {11}, pages = {1947-1959}, abstract = {Src kinase activity is controlled by various mechanisms involving a coordinated movement of kinase and regulatory domains. Notwithstanding the extensive knowledge related to the backbone dynamics, little is known about the more subtle side-chain dynamics within the regulatory domains and their role in the activation process. Here, we show through experimental methyl dynamic results and predicted changes in side-chain conformational couplings that the SH2 structure of Fyn contains a dynamic network capable of propagating binding information. We reveal that binding the phosphorylated tail of Fyn perturbs a residue cluster near the linker connecting the SH2 and SH3 domains of Fyn, which is known to be relevant in the regulation of the activity of Fyn. Biochemical perturbation experiments validate that those residues are essential for inhibition of Fyn, leading to a gain of function upon mutation. These findings reveal how side-chain dynamics may facilitate the allosteric regulation of the different members of the Src kinase family.}, note = {DOI: 10.1016/j.str.2016.08.016}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src kinase activity is controlled by various mechanisms involving a coordinated movement of kinase and regulatory domains. Notwithstanding the extensive knowledge related to the backbone dynamics, little is known about the more subtle side-chain dynamics within the regulatory domains and their role in the activation process. Here, we show through experimental methyl dynamic results and predicted changes in side-chain conformational couplings that the SH2 structure of Fyn contains a dynamic network capable of propagating binding information. We reveal that binding the phosphorylated tail of Fyn perturbs a residue cluster near the linker connecting the SH2 and SH3 domains of Fyn, which is known to be relevant in the regulation of the activity of Fyn. Biochemical perturbation experiments validate that those residues are essential for inhibition of Fyn, leading to a gain of function upon mutation. These findings reveal how side-chain dynamics may facilitate the allosteric regulation of the different members of the Src kinase family. |
Han, The Anh T A H; Lenaerts, Tom A synergy of costly punishment and commitment in cooperation dilemmas Journal Article In: Adaptive behavior, 24 (4), pp. 237-248, 2016, (DOI: 10.1177/1059712316653451). @article{info:hdl:2013/236713, title = {A synergy of costly punishment and commitment in cooperation dilemmas}, author = {The Anh T A H Han and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/236713}, year = {2016}, date = {2016-01-01}, journal = {Adaptive behavior}, volume = {24}, number = {4}, pages = {237-248}, abstract = {To ensure cooperation in the Prisoner's Dilemma, individuals may require prior commitments from others, subject to compensations when agreements to cooperate are violated. Alternatively, individuals may prefer to behave reactively, without arranging prior commitments, by simply punishing those who misbehave. These two mechanisms have been shown to promote the emergence of cooperation, yet are complementary in the way they aim to promote cooperation. Although both mechanisms have their specific limitations, either one of them can overcome the problems of the other. On one hand, costly punishment requires an excessive effect-to-cost ratio to be successful, and this ratio can be significantly reduced by arranging a prior commitment with a more limited compensation. On the other hand, commitment-proposing strategies can be suppressed by free-riding strategies that commit only when someone else is paying the cost to arrange the deal, whom in turn can be dealt with more effectively by reactive punishers. Using methods from Evolutionary Game Theory, we present here an analytical model showing that there is a wide range of settings for which the combined strategy outperforms either strategy by itself, leading to significantly higher levels of cooperation. Interestingly, the improvement is most significant when the cost of arranging commitments is sufficiently high and the penalty reaches a certain threshold, thereby overcoming the weaknesses of both mechanisms.}, note = {DOI: 10.1177/1059712316653451}, keywords = {}, pubstate = {published}, tppubtype = {article} } To ensure cooperation in the Prisoner's Dilemma, individuals may require prior commitments from others, subject to compensations when agreements to cooperate are violated. Alternatively, individuals may prefer to behave reactively, without arranging prior commitments, by simply punishing those who misbehave. These two mechanisms have been shown to promote the emergence of cooperation, yet are complementary in the way they aim to promote cooperation. Although both mechanisms have their specific limitations, either one of them can overcome the problems of the other. On one hand, costly punishment requires an excessive effect-to-cost ratio to be successful, and this ratio can be significantly reduced by arranging a prior commitment with a more limited compensation. On the other hand, commitment-proposing strategies can be suppressed by free-riding strategies that commit only when someone else is paying the cost to arrange the deal, whom in turn can be dealt with more effectively by reactive punishers. Using methods from Evolutionary Game Theory, we present here an analytical model showing that there is a wide range of settings for which the combined strategy outperforms either strategy by itself, leading to significantly higher levels of cooperation. Interestingly, the improvement is most significant when the cost of arranging commitments is sufficiently high and the penalty reaches a certain threshold, thereby overcoming the weaknesses of both mechanisms. |
Raimondi, Daniele; Gazzo, Andrea; Rooman, Marianne; Lenaerts, Tom; Vranken, Wim In: Bioinformatics, 32 (12), pp. 1797-1804, 2016, (DOI: 10.1093/bioinformatics/btw094). @article{info:hdl:2013/236692, title = {Multilevel biological characterization of exomic variants at the protein level significantly improves the identification of their deleterious effects}, author = {Daniele Raimondi and Andrea Gazzo and Marianne Rooman and Tom Lenaerts and Wim Vranken}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/236692}, year = {2016}, date = {2016-01-01}, journal = {Bioinformatics}, volume = {32}, number = {12}, pages = {1797-1804}, abstract = {Motivation: There are now many predictors capable of identifying the likely phenotypic effects of single nucleotide variants (SNVs) or short in-frame Insertions or Deletions (INDELs) on the increasing amount of genome sequence data. Most of these predictors focus on SNVs and use a combination of features related to sequence conservation, biophysical, and/or structural properties to link the observed variant to either neutral or disease phenotype. Despite notable successes, the mapping between genetic variants and their phenotypic effects is riddled with levels of complexity that are not yet fully understood and that are often not taken into account in the predictions, despite their promise of significantly improving the prediction of deleterious mutants. Results: We present DEOGEN, a novel variant effect predictor that can handle both missense SNVs and in-frame INDELs. By integrating information from different biological scales and mimicking the complex mixture of effects that lead from the variant to the phenotype, we obtain significant improvements in the variant-effect prediction results. Next to the typical variant-oriented features based on the evolutionary conservation of the mutated positions, we added a collection of protein-oriented features that are based on functional aspects of the gene affected. We cross-validated DEOGEN on 36 825 polymorphisms, 20 821 deleterious SNVs, and 1038 INDELs from SwissProt. The multilevel contextualization of each (variant, protein) pair in DEOGEN provides a 10% improvement of MCC with respect to current state-of-the-art tools.}, note = {DOI: 10.1093/bioinformatics/btw094}, keywords = {}, pubstate = {published}, tppubtype = {article} } Motivation: There are now many predictors capable of identifying the likely phenotypic effects of single nucleotide variants (SNVs) or short in-frame Insertions or Deletions (INDELs) on the increasing amount of genome sequence data. Most of these predictors focus on SNVs and use a combination of features related to sequence conservation, biophysical, and/or structural properties to link the observed variant to either neutral or disease phenotype. Despite notable successes, the mapping between genetic variants and their phenotypic effects is riddled with levels of complexity that are not yet fully understood and that are often not taken into account in the predictions, despite their promise of significantly improving the prediction of deleterious mutants. Results: We present DEOGEN, a novel variant effect predictor that can handle both missense SNVs and in-frame INDELs. By integrating information from different biological scales and mimicking the complex mixture of effects that lead from the variant to the phenotype, we obtain significant improvements in the variant-effect prediction results. Next to the typical variant-oriented features based on the evolutionary conservation of the mutated positions, we added a collection of protein-oriented features that are based on functional aspects of the gene affected. We cross-validated DEOGEN on 36 825 polymorphisms, 20 821 deleterious SNVs, and 1038 INDELs from SwissProt. The multilevel contextualization of each (variant, protein) pair in DEOGEN provides a 10% improvement of MCC with respect to current state-of-the-art tools. |
Ruano, Ana Zafra; Cilia, Elisa; Couceiro, José JR; Sanz, Javier Ruiz; Schymkowitz, Joost J; Rousseau, Frédéric; Luque, Irene; Lenaerts, Tom From Binding-Induced Dynamic Effects in SH3 Structures to Evolutionary Conserved Sectors. Journal Article In: PLoS computational biology, 12 (5), pp. e1004938, 2016, (DOI: 10.1371/journal.pcbi.1004938). @article{info:hdl:2013/232621, title = {From Binding-Induced Dynamic Effects in SH3 Structures to Evolutionary Conserved Sectors.}, author = {Ana Zafra Ruano and Elisa Cilia and José JR Couceiro and Javier Ruiz Sanz and Joost J Schymkowitz and Frédéric Rousseau and Irene Luque and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/232621/4/doi_216248.pdf}, year = {2016}, date = {2016-01-01}, journal = {PLoS computational biology}, volume = {12}, number = {5}, pages = {e1004938}, abstract = {Src Homology 3 domains are ubiquitous small interaction modules known to act as docking sites and regulatory elements in a wide range of proteins. Prior experimental NMR work on the SH3 domain of Src showed that ligand binding induces long-range dynamic changes consistent with an induced fit mechanism. The identification of the residues that participate in this mechanism produces a chart that allows for the exploration of the regulatory role of such domains in the activity of the encompassing protein. Here we show that a computational approach focusing on the changes in side chain dynamics through ligand binding identifies equivalent long-range effects in the Src SH3 domain. Mutation of a subset of the predicted residues elicits long-range effects on the binding energetics, emphasizing the relevance of these positions in the definition of intramolecular cooperative networks of signal transduction in this domain. We find further support for this mechanism through the analysis of seven other publically available SH3 domain structures of which the sequences represent diverse SH3 classes. By comparing the eight predictions, we find that, in addition to a dynamic pathway that is relatively conserved throughout all SH3 domains, there are dynamic aspects specific to each domain and homologous subgroups. Our work shows for the first time from a structural perspective, which transduction mechanisms are common between a subset of closely related and distal SH3 domains, while at the same time highlighting the differences in signal transduction that make each family member unique. These results resolve the missing link between structural predictions of dynamic changes and the domain sectors recently identified for SH3 domains through sequence analysis.}, note = {DOI: 10.1371/journal.pcbi.1004938}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src Homology 3 domains are ubiquitous small interaction modules known to act as docking sites and regulatory elements in a wide range of proteins. Prior experimental NMR work on the SH3 domain of Src showed that ligand binding induces long-range dynamic changes consistent with an induced fit mechanism. The identification of the residues that participate in this mechanism produces a chart that allows for the exploration of the regulatory role of such domains in the activity of the encompassing protein. Here we show that a computational approach focusing on the changes in side chain dynamics through ligand binding identifies equivalent long-range effects in the Src SH3 domain. Mutation of a subset of the predicted residues elicits long-range effects on the binding energetics, emphasizing the relevance of these positions in the definition of intramolecular cooperative networks of signal transduction in this domain. We find further support for this mechanism through the analysis of seven other publically available SH3 domain structures of which the sequences represent diverse SH3 classes. By comparing the eight predictions, we find that, in addition to a dynamic pathway that is relatively conserved throughout all SH3 domains, there are dynamic aspects specific to each domain and homologous subgroups. Our work shows for the first time from a structural perspective, which transduction mechanisms are common between a subset of closely related and distal SH3 domains, while at the same time highlighting the differences in signal transduction that make each family member unique. These results resolve the missing link between structural predictions of dynamic changes and the domain sectors recently identified for SH3 domains through sequence analysis. |
'S, Ewelina ; Ł, Jakub ; Byrski, Aleksander; Lenaerts, Tom; Samson, Dana; Indurkhya, Bipin; Nowe, Ann; Kisiel-Dorohinicki, Marek Measuring diversity of socio-cognitively inspired ACO search Journal Article In: Lecture notes in computer science, 9597 , pp. 393-408, 2016, (DOI: 10.1007/978-3-319-31204-0_26). @article{info:hdl:2013/231238, title = {Measuring diversity of socio-cognitively inspired ACO search}, author = {Ewelina {'S}widerska and Jakub {Ł}asisz and Aleksander Byrski and Tom Lenaerts and Dana Samson and Bipin Indurkhya and Ann Nowe and Marek Kisiel-Dorohinicki}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/231238}, year = {2016}, date = {2016-01-01}, journal = {Lecture notes in computer science}, volume = {9597}, pages = {393-408}, abstract = {In our recent research, we implemented an enhancement of Ant Colony Optimization incorporating the socio-cognitive dimension of perspective taking. Our initial results suggested that increasing the diversity of ant population --- introducing different pheromones, different species and dedicated inter-species relations --- yielded better results. In this paper, we explore the diversity issue by introducing novel diversity measurement strategies for ACO. Based on these strategies we compare both classic ACO and its socio-cognitive variation.}, note = {DOI: 10.1007/978-3-319-31204-0_26}, keywords = {}, pubstate = {published}, tppubtype = {article} } In our recent research, we implemented an enhancement of Ant Colony Optimization incorporating the socio-cognitive dimension of perspective taking. Our initial results suggested that increasing the diversity of ant population --- introducing different pheromones, different species and dedicated inter-species relations --- yielded better results. In this paper, we explore the diversity issue by introducing novel diversity measurement strategies for ACO. Based on these strategies we compare both classic ACO and its socio-cognitive variation. |
Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Emergence of Cooperation in Group Interactions: Avoidance versus Restriction Inproceedings In: The 2016 AAAI Spring Symposium Series: Technical Reports, 2016, (Conference: AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''(21-23 March 2016: Stanford, USA)). @inproceedings{info:hdl:2013/243792, title = {Emergence of Cooperation in Group Interactions: Avoidance versus Restriction}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243792}, year = {2016}, date = {2016-01-01}, booktitle = {The 2016 AAAI Spring Symposium Series: Technical Reports}, note = {Conference: AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''(21-23 March 2016: Stanford, USA)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
'i, Lu; Han, The Anh T A H; Martinez-Vaquero, Luis L A; Lenaerts, Tom Guilt for non-humans Inproceedings In: The 2016 AAAI Spring Symposium Series: Technical reports, 2016, (Conference: The 2016 AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''(21-23 March 2016: Stanford, USA)). @inproceedings{info:hdl:2013/243750, title = {Guilt for non-humans}, author = {Lu{'i}s Moniz Pereira and The Anh T A H Han and Luis L A Martinez-Vaquero and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243750}, year = {2016}, date = {2016-01-01}, booktitle = {The 2016 AAAI Spring Symposium Series: Technical reports}, note = {Conference: The 2016 AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''(21-23 March 2016: Stanford, USA)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Lenaerts, Tom Conditions for the evolution of apology and forgiveness in populations of autonomous agents Inproceedings In: The 2016 AAAI Spring Symposium Series: Technical Reports, 2016, (Conference: AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''.(Stanford, USA)). @inproceedings{info:hdl:2013/243723, title = {Conditions for the evolution of apology and forgiveness in populations of autonomous agents}, author = {Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243723}, year = {2016}, date = {2016-01-01}, booktitle = {The 2016 AAAI Spring Symposium Series: Technical Reports}, note = {Conference: AAAI Spring Symposium on ``Ethical and Moral Considerations in Non-Human Agents''.(Stanford, USA)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Cava, Claudia; Colaprico, Antonio; Bertoli, Gloria; Bontempi, Gianluca; Mauri, Giancarlo; Castiglioni, Isabella How interacting pathways are regulated by miRNAs in breast cancer subtypes Journal Article In: BMC bioinformatics, 17 , 2016, (DOI: 10.1186/s12859-016-1196-1). @article{info:hdl:2013/247204, title = {How interacting pathways are regulated by miRNAs in breast cancer subtypes}, author = {Claudia Cava and Antonio Colaprico and Gloria Bertoli and Gianluca Bontempi and Giancarlo Mauri and Isabella Castiglioni}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/247204}, year = {2016}, date = {2016-01-01}, journal = {BMC bioinformatics}, volume = {17}, abstract = {Background: An important challenge in cancer biology is to understand the complex aspects of the disease. It is increasingly evident that genes are not isolated from each other and the comprehension of how different genes are related to each other could explain biological mechanisms causing diseases. Biological pathways are important tools to reveal gene interaction and reduce the large number of genes to be studied by partitioning it into smaller paths. Furthermore, recent scientific evidence has proven that a combination of pathways, instead than a single element of the pathway or a single pathway, could be responsible for pathological changes in a cell. Results: In this paper we develop a new method that can reveal miRNAs able to regulate, in a coordinated way, networks of gene pathways. We applied the method to subtypes of breast cancer. The basic idea is the identification of pathways significantly enriched with differentially expressed genes among the different breast cancer subtypes and normal tissue. Looking at the pairs of pathways that were found to be functionally related, we created a network of dependent pathways and we focused on identifying miRNAs that could act as miRNA drivers in a coordinated regulation process. Conclusions: Our approach enables miRNAs identification that could have an important role in the development of breast cancer.}, note = {DOI: 10.1186/s12859-016-1196-1}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: An important challenge in cancer biology is to understand the complex aspects of the disease. It is increasingly evident that genes are not isolated from each other and the comprehension of how different genes are related to each other could explain biological mechanisms causing diseases. Biological pathways are important tools to reveal gene interaction and reduce the large number of genes to be studied by partitioning it into smaller paths. Furthermore, recent scientific evidence has proven that a combination of pathways, instead than a single element of the pathway or a single pathway, could be responsible for pathological changes in a cell. Results: In this paper we develop a new method that can reveal miRNAs able to regulate, in a coordinated way, networks of gene pathways. We applied the method to subtypes of breast cancer. The basic idea is the identification of pathways significantly enriched with differentially expressed genes among the different breast cancer subtypes and normal tissue. Looking at the pairs of pathways that were found to be functionally related, we created a network of dependent pathways and we focused on identifying miRNAs that could act as miRNA drivers in a coordinated regulation process. Conclusions: Our approach enables miRNAs identification that could have an important role in the development of breast cancer. |
"e, Yann-A; Homolova, Adriana; Bontempi, Gianluca OpenTED browser: Insights into European Public Spendings Journal Article In: CEUR Workshop Proceedings, 1831 , 2016, (Language of publication: en). @article{info:hdl:2013/253331, title = {OpenTED browser: Insights into European Public Spendings}, author = {Yann-A{"e}l Le Borgne and Adriana Homolova and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/253331}, year = {2016}, date = {2016-01-01}, journal = {CEUR Workshop Proceedings}, volume = {1831}, abstract = {We present the OpenTED browser, a Web application allowing to interactively browse public spending data related to public procurements in the European Union. The application relies on Open Data recently published by the European Commission and the Publications Office of the European Union, from which we imported a curated dataset of 4.2 million contract award notices spanning the period 2006-2015. The application is designed to easily filter notices and visualise relationships between public contracting authorities and private contractors. The simple design allows for example to quickly find information about who the biggest suppliers of local governments are, and the nature of the contracted goods and services. We believe the tool, which we make Open Source, is a valuable source of information for journalists, NGOs, analysts and citizens for getting information on public procurement data, from large scale trends to local municipal developments.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } We present the OpenTED browser, a Web application allowing to interactively browse public spending data related to public procurements in the European Union. The application relies on Open Data recently published by the European Commission and the Publications Office of the European Union, from which we imported a curated dataset of 4.2 million contract award notices spanning the period 2006-2015. The application is designed to easily filter notices and visualise relationships between public contracting authorities and private contractors. The simple design allows for example to quickly find information about who the biggest suppliers of local governments are, and the nature of the contracted goods and services. We believe the tool, which we make Open Source, is a valuable source of information for journalists, NGOs, analysts and citizens for getting information on public procurement data, from large scale trends to local municipal developments. |
Bontempi, Gianluca A blocking strategy for ranking features according to probabilistic relevance Journal Article In: Lecture notes in computer science, 10122 LNCS , pp. 59-69, 2016, (DOI: 10.1007/978-3-319-51469-7_5). @article{info:hdl:2013/247751, title = {A blocking strategy for ranking features according to probabilistic relevance}, author = {Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/247751}, year = {2016}, date = {2016-01-01}, journal = {Lecture notes in computer science}, volume = {10122 LNCS}, pages = {59-69}, abstract = {The paper presents an algorithm to rank features in ``small number of samples, large dimensionality'' problems according to probabilistic feature relevance, a novel definition of feature relevance. Probabilistic feature relevance, intended as expected weak relevance, is introduced in order to address the problem of estimating conventional feature relevance in data settings where the number of samples is much smaller than the number of features. The resulting ranking algorithm relies on a blocking approach for estimation and consists in creating a large number of identical configurations to measure the conditional information of each feature in a paired manner. Its implementation can be made embarrassingly parallel in the case of very large n. A number of experiments on simulated and real data confirms the interest of the approach.}, note = {DOI: 10.1007/978-3-319-51469-7_5}, keywords = {}, pubstate = {published}, tppubtype = {article} } The paper presents an algorithm to rank features in ``small number of samples, large dimensionality'' problems according to probabilistic feature relevance, a novel definition of feature relevance. Probabilistic feature relevance, intended as expected weak relevance, is introduced in order to address the problem of estimating conventional feature relevance in data settings where the number of samples is much smaller than the number of features. The resulting ranking algorithm relies on a blocking approach for estimation and consists in creating a large number of identical configurations to measure the conditional information of each feature in a paired manner. Its implementation can be made embarrassingly parallel in the case of very large n. A number of experiments on simulated and real data confirms the interest of the approach. |
Silva, Tiago T C; Colaprico, Antonio; Olsen, Catharina; D'Angelo, Fulvio; Bontempi, Gianluca; Ceccarelli, Michele; Noushmehr, Houtan In: F1000Research, 5 , 2016, (DOI: 10.12688/F1000RESEARCH.8923.1). @article{info:hdl:2013/247761, title = {TCGA Workflow: Analyze cancer genomics and epigenomics data using Bioconductor packages [version 1; referees: 1 approved, 1 approved with reservations]}, author = {Tiago T C Silva and Antonio Colaprico and Catharina Olsen and Fulvio D'Angelo and Gianluca Bontempi and Michele Ceccarelli and Houtan Noushmehr}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/247761}, year = {2016}, date = {2016-01-01}, journal = {F1000Research}, volume = {5}, abstract = {Biotechnological advances in sequencing have led to an explosion of publicly available data via large international consortia such as The Cancer Genome Atlas (TCGA), The Encyclopedia of DNA Elements (ENCODE), and The NIH Roadmap Epigenomics Mapping Consortium (Roadmap). These projects have provided unprecedented opportunities to interrogate the epigenome of cultured cancer cell lines as well as normal and tumor tissues with high genomic resolution. The bioconductor project offers more than 1,000 open-source software and statistical packages to analyze high-throughput genomic data. However, most packages are designed for specific data types (e.g. expression, epigenetics, genomics) and there is no comprehensive tool that provides a complete integrative analysis harnessing the resources and data provided by all three public projects. A need to create an integration of these different analyses was recently proposed. In this workflow, we provide a series of biologically focused integrative downstream analyses of different molecular data. We describe how to download, process and prepare TCGA data and by harnessing several key bioconductor packages, we describe how to extract biologically meaningful genomic and epigenomic data and by using Roadmap and ENCODE data, we provide a workplan to identify candidate biologically relevant functional epigenomic elements associated with cancer. To illustrate our workflow, we analyzed two types of brain tumors: low-grade glioma (LGG) versus high-grade glioma (glioblastoma multiform or GBM). This workflow introduces the following Bioconductor packages: AnnotationHub, ChIPSeeker, ComplexHeatmap, pathview, ELMER, GAIA, MINET, RTCGAtoolbox, TCGAbiolinks.}, note = {DOI: 10.12688/F1000RESEARCH.8923.1}, keywords = {}, pubstate = {published}, tppubtype = {article} } Biotechnological advances in sequencing have led to an explosion of publicly available data via large international consortia such as The Cancer Genome Atlas (TCGA), The Encyclopedia of DNA Elements (ENCODE), and The NIH Roadmap Epigenomics Mapping Consortium (Roadmap). These projects have provided unprecedented opportunities to interrogate the epigenome of cultured cancer cell lines as well as normal and tumor tissues with high genomic resolution. The bioconductor project offers more than 1,000 open-source software and statistical packages to analyze high-throughput genomic data. However, most packages are designed for specific data types (e.g. expression, epigenetics, genomics) and there is no comprehensive tool that provides a complete integrative analysis harnessing the resources and data provided by all three public projects. A need to create an integration of these different analyses was recently proposed. In this workflow, we provide a series of biologically focused integrative downstream analyses of different molecular data. We describe how to download, process and prepare TCGA data and by harnessing several key bioconductor packages, we describe how to extract biologically meaningful genomic and epigenomic data and by using Roadmap and ENCODE data, we provide a workplan to identify candidate biologically relevant functional epigenomic elements associated with cancer. To illustrate our workflow, we analyzed two types of brain tumors: low-grade glioma (LGG) versus high-grade glioma (glioblastoma multiform or GBM). This workflow introduces the following Bioconductor packages: AnnotationHub, ChIPSeeker, ComplexHeatmap, pathview, ELMER, GAIA, MINET, RTCGAtoolbox, TCGAbiolinks. |
Brenner, Carmen; Luciani, Judith; Bizet, Martin; Ndlovu, Matladi N; Josseaux, Eléonore; Dedeurwaerder, Sarah; Calonne, Emilie; Putmans, Pascale; Cartron, Pierre Francois; Defrance, Matthieu; c c, Fran; Deplus, Rachel The interplay between the lysine demethylase KDM1A and DNA methyltransferases in cancer cells is cell cycle dependent Journal Article In: Oncotarget, 7 (37), pp. 58939-58952, 2016, (DOI: 10.18632/oncotarget.10624). @article{info:hdl:2013/243793, title = {The interplay between the lysine demethylase KDM1A and DNA methyltransferases in cancer cells is cell cycle dependent}, author = {Carmen Brenner and Judith Luciani and Martin Bizet and Matladi N Ndlovu and Eléonore Josseaux and Sarah Dedeurwaerder and Emilie Calonne and Pascale Putmans and Pierre Francois Cartron and Matthieu Defrance and Fran{c c}ois Fuks and Rachel Deplus}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/243793}, year = {2016}, date = {2016-01-01}, journal = {Oncotarget}, volume = {7}, number = {37}, pages = {58939-58952}, abstract = {DNA methylation and histone modifications are key epigenetic regulators of gene expression, and tight connections are known between the two. DNA methyltransferases are upregulated in several tumors and aberrant DNA methylation profiles are a cancer hallmark. On the other hand, histone demethylases are upregulated in cancer cells. Previous work on ES cells has shown that the lysine demethylase KDM1A binds to DNMT1, thereby affecting DNA methylation. In cancer cells, the occurrence of this interaction has not been explored. Here we demonstrate in several tumor cell lines an interaction between KDM1A and both DNMT1 and DNMT3B. Intriguingly and in contrast to what is observed in ES cells, KDM1A depletion in cancer cells was found not to trigger any reduction in the DNMT1 or DNMT3B protein level or any change in DNA methylation. In the S-phase, furthermore, KDM1A and DNMT1 were found, to colocalize within the heterochromatin. Using P-LISA, we revealed substantially increased binding of KDM1A to DNMT1 during the S-phase. Together, our findings propose a mechanistic link between KDM1A and DNA methyltransferases in cancer cells and suggest that the KDM1A/DNMT1 interaction may play a role during replication. Our work also strengthens the idea that DNMTs can exert functions unrelated to act on DNA methylation.}, note = {DOI: 10.18632/oncotarget.10624}, keywords = {}, pubstate = {published}, tppubtype = {article} } DNA methylation and histone modifications are key epigenetic regulators of gene expression, and tight connections are known between the two. DNA methyltransferases are upregulated in several tumors and aberrant DNA methylation profiles are a cancer hallmark. On the other hand, histone demethylases are upregulated in cancer cells. Previous work on ES cells has shown that the lysine demethylase KDM1A binds to DNMT1, thereby affecting DNA methylation. In cancer cells, the occurrence of this interaction has not been explored. Here we demonstrate in several tumor cell lines an interaction between KDM1A and both DNMT1 and DNMT3B. Intriguingly and in contrast to what is observed in ES cells, KDM1A depletion in cancer cells was found not to trigger any reduction in the DNMT1 or DNMT3B protein level or any change in DNA methylation. In the S-phase, furthermore, KDM1A and DNMT1 were found, to colocalize within the heterochromatin. Using P-LISA, we revealed substantially increased binding of KDM1A to DNMT1 during the S-phase. Together, our findings propose a mechanistic link between KDM1A and DNA methyltransferases in cancer cells and suggest that the KDM1A/DNMT1 interaction may play a role during replication. Our work also strengthens the idea that DNMTs can exert functions unrelated to act on DNA methylation. |
Delatte, Benjamin; Wang, Feifei; Ngoc, Long Vo; Collignon, Evelyne; Bonvin, Elise; Deplus, Rachel; Calonne, Emilie; Hassabi, Bouchra; Putmans, Pascale; Awe, Stephan; Wetzel, Collin; Kreher, Judith; Soin, Romuald; Creppe, Catherine; Limbach, Patrick A; Gueydan, Cyril; Kruys, Véronique; Brehm, A; Minakhina, Svetlana; Defrance, Matthieu; Steward, Ruth; c c, Fran Transcriptome-wide distribution and function of RNA hydroxymethylcytosine Journal Article In: Science, 351 (6270), pp. 282-285, 2016, (DOI: 10.1126/science.aac5253). @article{info:hdl:2013/224506, title = {Transcriptome-wide distribution and function of RNA hydroxymethylcytosine}, author = {Benjamin Delatte and Feifei Wang and Long Vo Ngoc and Evelyne Collignon and Elise Bonvin and Rachel Deplus and Emilie Calonne and Bouchra Hassabi and Pascale Putmans and Stephan Awe and Collin Wetzel and Judith Kreher and Romuald Soin and Catherine Creppe and Patrick A Limbach and Cyril Gueydan and Véronique Kruys and A Brehm and Svetlana Minakhina and Matthieu Defrance and Ruth Steward and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/224506/3/doi_208133.pdf}, year = {2016}, date = {2016-01-01}, journal = {Science}, volume = {351}, number = {6270}, pages = {282-285}, abstract = {Hydroxymethylcytosine, well described in DNA, occurs also in RNA. Here, we show that hydroxymethylcytosine preferentially marks polyadenylated RNAs and is deposited by Tet in Drosophila. We map the transcriptome-wide hydroxymethylation landscape, revealing hydroxymethylcytosine in the transcripts ofmany genes, notably in coding sequences, and identify consensus sites for hydroxymethylation.We found that RNA hydroxymethylation can favor mRNA translation.Tet and hydroxymethylated RNA are found to be most abundant in the Drosophila brain, and Tet-deficient fruitflies suffer impaired brain development, accompanied by decreased RNA hydroxymethylation. This study highlights the distribution, localization, and function of cytosine hydroxymethylation and identifies central roles for this modification in Drosophila.}, note = {DOI: 10.1126/science.aac5253}, keywords = {}, pubstate = {published}, tppubtype = {article} } Hydroxymethylcytosine, well described in DNA, occurs also in RNA. Here, we show that hydroxymethylcytosine preferentially marks polyadenylated RNAs and is deposited by Tet in Drosophila. We map the transcriptome-wide hydroxymethylation landscape, revealing hydroxymethylcytosine in the transcripts ofmany genes, notably in coding sequences, and identify consensus sites for hydroxymethylation.We found that RNA hydroxymethylation can favor mRNA translation.Tet and hydroxymethylated RNA are found to be most abundant in the Drosophila brain, and Tet-deficient fruitflies suffer impaired brain development, accompanied by decreased RNA hydroxymethylation. This study highlights the distribution, localization, and function of cytosine hydroxymethylation and identifies central roles for this modification in Drosophila. |
Grembergen, Olivier Van; Bizet, Martin; de Bony, Eric James; Calonne, Emilie; Putmans, Pascale; Brohée, Sylvain; Olsen, Catharina; Guo, Mingzhou; Bontempi, Gianluca; Sotiriou, Christos; Defrance, Matthieu; c c, Fran Portraying breast cancers with long noncoding RNAs Journal Article In: Science advances, 2 (9), 2016, (DOI: 10.1126/sciadv.1600220). @article{info:hdl:2013/236112, title = {Portraying breast cancers with long noncoding RNAs}, author = {Olivier Van Grembergen and Martin Bizet and Eric James de Bony and Emilie Calonne and Pascale Putmans and Sylvain Brohée and Catharina Olsen and Mingzhou Guo and Gianluca Bontempi and Christos Sotiriou and Matthieu Defrance and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/236112/1/doi_219739.pdf}, year = {2016}, date = {2016-01-01}, journal = {Science advances}, volume = {2}, number = {9}, abstract = {Evidence is emerging that long noncoding RNAs (lncRNAs) may play a role in cancer development, but this role is not yet clear. We performed a genome-wide transcriptional survey to explore the lncRNA landscape across 995 breast tissue samples. We identified 215 lncRNAs whose genes are aberrantly expressed in breast tumors, as compared to normal samples. Unsupervised hierarchical clustering of breast tumors on the basis of their lncRNAs revealed four breast cancer subgroups that correlate tightly with PAM50-defined mRNA-based subtypes. Using multivariate analysis, we identified no less than 210 lncRNAs prognostic of clinical outcome. By analyzing the coexpression of lncRNA genes and protein-coding genes, we inferred potential functions of the 215 dysregulated lncRNAs. We then associated subtype-specific lncRNAs with key molecular processes involved in cancer. A correlation was observed, on the one hand, between luminal A--specific lncRNAs and the activation of phosphatidylinositol 3-kinase, fibroblast growth factor, and transforming growth factor--β pathways and, on the other hand, between basal-like--specific lncRNAs and the activation of epidermal growth factor receptor (EGFR)--dependent pathways and of the epithelial-to-mesenchymal transition. Finally, we showed that a specific lncRNA, which we called CYTOR, plays a role in breast cancer. We confirmed its predicted functions, showing that it regulates genes involved in the EGFR/mammalian target of rapamycin pathway and is required for cell proliferation, cell migration, and cytoskeleton organization. Overall, our work provides the most comprehensive analyses for lncRNA in breast cancers. Our findings suggest a wide range of biological functions associated with lncRNAs in breast cancer and provide a foundation for functional investigations that could lead to new therapeutic approaches.}, note = {DOI: 10.1126/sciadv.1600220}, keywords = {}, pubstate = {published}, tppubtype = {article} } Evidence is emerging that long noncoding RNAs (lncRNAs) may play a role in cancer development, but this role is not yet clear. We performed a genome-wide transcriptional survey to explore the lncRNA landscape across 995 breast tissue samples. We identified 215 lncRNAs whose genes are aberrantly expressed in breast tumors, as compared to normal samples. Unsupervised hierarchical clustering of breast tumors on the basis of their lncRNAs revealed four breast cancer subgroups that correlate tightly with PAM50-defined mRNA-based subtypes. Using multivariate analysis, we identified no less than 210 lncRNAs prognostic of clinical outcome. By analyzing the coexpression of lncRNA genes and protein-coding genes, we inferred potential functions of the 215 dysregulated lncRNAs. We then associated subtype-specific lncRNAs with key molecular processes involved in cancer. A correlation was observed, on the one hand, between luminal A--specific lncRNAs and the activation of phosphatidylinositol 3-kinase, fibroblast growth factor, and transforming growth factor--β pathways and, on the other hand, between basal-like--specific lncRNAs and the activation of epidermal growth factor receptor (EGFR)--dependent pathways and of the epithelial-to-mesenchymal transition. Finally, we showed that a specific lncRNA, which we called CYTOR, plays a role in breast cancer. We confirmed its predicted functions, showing that it regulates genes involved in the EGFR/mammalian target of rapamycin pathway and is required for cell proliferation, cell migration, and cytoskeleton organization. Overall, our work provides the most comprehensive analyses for lncRNA in breast cancers. Our findings suggest a wide range of biological functions associated with lncRNAs in breast cancer and provide a foundation for functional investigations that could lead to new therapeutic approaches. |
2015 |
Zisis, Ioannis; Guida, Sibilla Di; Han, The Anh T A H; Kirchsteiger, Georg; Lenaerts, Tom Generocity motivated by acceptance - evolutionary analysis of an anticipation game Journal Article In: Scientific Reports, 5 , 2015, (Language of publication: en). @article{info:hdl:2013/228071, title = {Generocity motivated by acceptance - evolutionary analysis of an anticipation game}, author = {Ioannis Zisis and Sibilla Di Guida and The Anh T A H Han and Georg Kirchsteiger and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/228071/3/2015SR-Pair-formation-dictator.pdf}, year = {2015}, date = {2015-01-01}, journal = {Scientific Reports}, volume = {5}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Faust, Karoline; Mendez, Gipsi Lima; Lerat, Jean-Sébastien; Sathirapongsasuti, Jarupon Fah; Knight, Rob; Huttenhower, Curtis; Lenaerts, Tom; Raes, Jeroen JR Cross-biome comparison of microbial association networks Journal Article In: Frontiers in microbiology, 6 (OCT), 2015, (DOI: 10.3389/fmicb.2015.01200). @article{info:hdl:2013/226810, title = {Cross-biome comparison of microbial association networks}, author = {Karoline Faust and Gipsi Lima Mendez and Jean-Sébastien Lerat and Jarupon Fah Sathirapongsasuti and Rob Knight and Curtis Huttenhower and Tom Lenaerts and Jeroen JR Raes}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/226810/4/doi_210437.pdf}, year = {2015}, date = {2015-01-01}, journal = {Frontiers in microbiology}, volume = {6}, number = {OCT}, abstract = {Clinical and environmental meta-omics studies are accumulating an ever-growing amount of microbial abundance data over a wide range of ecosystems. With a sufficiently large sample number, these microbial communities can be explored by constructing and analyzing co-occurrence networks, which detect taxon associations from abundance data and can give insights into community structure. Here, we investigate how co-occurrence networks differ across biomes and which other factors influence their properties. For this, we inferred microbial association networks from 20 different 16S rDNA sequencing data sets and observed that soil microbial networks harbor proportionally fewer positive associations and are less densely interconnected than host-associated networks. After excluding sample number, sequencing depth and beta-diversity as possible drivers, we found a negative correlation between community evenness and positive edge percentage. This correlation likely results from a skewed distribution of negative interactions, which take place preferentially between less prevalent taxa. Overall, our results suggest an under-appreciated role of evenness in shaping microbial association networks.}, note = {DOI: 10.3389/fmicb.2015.01200}, keywords = {}, pubstate = {published}, tppubtype = {article} } Clinical and environmental meta-omics studies are accumulating an ever-growing amount of microbial abundance data over a wide range of ecosystems. With a sufficiently large sample number, these microbial communities can be explored by constructing and analyzing co-occurrence networks, which detect taxon associations from abundance data and can give insights into community structure. Here, we investigate how co-occurrence networks differ across biomes and which other factors influence their properties. For this, we inferred microbial association networks from 20 different 16S rDNA sequencing data sets and observed that soil microbial networks harbor proportionally fewer positive associations and are less densely interconnected than host-associated networks. After excluding sample number, sequencing depth and beta-diversity as possible drivers, we found a negative correlation between community evenness and positive edge percentage. This correlation likely results from a skewed distribution of negative interactions, which take place preferentially between less prevalent taxa. Overall, our results suggest an under-appreciated role of evenness in shaping microbial association networks. |
Pozzolo, Andrea Dal; Caelen, Olivier; Johnson, Reid; Bontempi, Gianluca Calibrating Probability with Undersampling for Unbalanced Classification Inproceedings In: 2015 IEEE Symposium on Computational Intelligence and Data Mining, 2015, (Language of publication: en). @inproceedings{info:hdl:2013/221670, title = {Calibrating Probability with Undersampling for Unbalanced Classification}, author = {Andrea Dal Pozzolo and Olivier Caelen and Reid Johnson and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/221670}, year = {2015}, date = {2015-01-01}, booktitle = {2015 IEEE Symposium on Computational Intelligence and Data Mining}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Huculeci, Radu; Garcia-Pino, Abel; Buts, Lieven; Lenaerts, Tom; van Nuland, Nico A J Structural insights into the intertwined dimer of fyn SH2. Journal Article In: Protein science, 24 (12), pp. 1964-1978, 2015, (DOI: 10.1002/pro.2806). @article{info:hdl:2013/225650, title = {Structural insights into the intertwined dimer of fyn SH2.}, author = {Radu Huculeci and Abel Garcia-Pino and Lieven Buts and Tom Lenaerts and Nico A J van Nuland}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/225650/3/225650.pdf}, year = {2015}, date = {2015-01-01}, journal = {Protein science}, volume = {24}, number = {12}, pages = {1964-1978}, abstract = {Src homology 2 domains are interaction modules dedicated to the recognition of phosphotyrosine sites incorporated in numerous proteins found in intracellular signaling pathways. Here we provide for the first time structural insight into the dimerization of Fyn SH2 both in solution and in crystalline conditions, providing novel crystal structures of both the dimer and peptide-bound structures of Fyn SH2. Using nuclear magnetic resonance chemical shift analysis, we show how the peptide is able to eradicate the dimerization, leading to monomeric SH2 in its bound state. Furthermore, we show that Fyn SH2's dimer form differs from other SH2 dimers reported earlier. Interestingly, the Fyn dimer can be used to construct a completed dimer model of Fyn without any steric clashes. Together these results extend our understanding of SH2 dimerization, giving structural details, on one hand, and suggesting a possible physiological relevance of such behavior, on the other hand.}, note = {DOI: 10.1002/pro.2806}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src homology 2 domains are interaction modules dedicated to the recognition of phosphotyrosine sites incorporated in numerous proteins found in intracellular signaling pathways. Here we provide for the first time structural insight into the dimerization of Fyn SH2 both in solution and in crystalline conditions, providing novel crystal structures of both the dimer and peptide-bound structures of Fyn SH2. Using nuclear magnetic resonance chemical shift analysis, we show how the peptide is able to eradicate the dimerization, leading to monomeric SH2 in its bound state. Furthermore, we show that Fyn SH2's dimer form differs from other SH2 dimers reported earlier. Interestingly, the Fyn dimer can be used to construct a completed dimer model of Fyn without any steric clashes. Together these results extend our understanding of SH2 dimerization, giving structural details, on one hand, and suggesting a possible physiological relevance of such behavior, on the other hand. |
Pozzolo, Andrea Dal; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca Credit Card Fraud Detection and Concept-Drift Adaptation with Delayed Supervised Information Inproceedings In: Neural Networks (IJCNN), 2015 International Joint Conference on, 2015, (DOI: 10.1109/IJCNN.2015.7280527). @inproceedings{info:hdl:2013/221668, title = {Credit Card Fraud Detection and Concept-Drift Adaptation with Delayed Supervised Information}, author = {Andrea Dal Pozzolo and Giacomo Boracchi and Olivier Caelen and Cesare Alippi and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/221668}, year = {2015}, date = {2015-01-01}, booktitle = {Neural Networks (IJCNN), 2015 International Joint Conference on}, abstract = {Most fraud-detection systems (FDSs) monitor streams of credit card transactions by means of classifiers returning alerts for the riskiest payments. Fraud detection is notably a challenging problem because of concept drift (i.e. customers' habits evolve) and class unbalance (i.e. genuine transactions far outnumber frauds). Also, FDSs differ from conventional classification because, in a first phase, only a small set of supervised samples is provided by human investigators who have time to assess only a reduced number of alerts. Labels of the vast majority of transactions are made available only several days later, when customers have possibly reported unauthorized transactions. The delay in obtaining accurate labels and the interaction between alerts and supervised information have to be carefully taken into consideration when learning in a concept-drifting environment. In this paper we address a realistic fraud-detection setting and we show that investigator's feedbacks and delayed labels have to be handled separately. We design two FDSs on the basis of an ensemble and a sliding-window approach and we show that the winning strategy consists in training two separate classifiers (on feedbacks and delayed labels, respectively), and then aggregating the outcomes. Experiments on large dataset of real-world transactions show that the alert precision, which is the primary concern of investigators, can be substantially improved by the proposed approach.}, note = {DOI: 10.1109/IJCNN.2015.7280527}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Most fraud-detection systems (FDSs) monitor streams of credit card transactions by means of classifiers returning alerts for the riskiest payments. Fraud detection is notably a challenging problem because of concept drift (i.e. customers' habits evolve) and class unbalance (i.e. genuine transactions far outnumber frauds). Also, FDSs differ from conventional classification because, in a first phase, only a small set of supervised samples is provided by human investigators who have time to assess only a reduced number of alerts. Labels of the vast majority of transactions are made available only several days later, when customers have possibly reported unauthorized transactions. The delay in obtaining accurate labels and the interaction between alerts and supervised information have to be carefully taken into consideration when learning in a concept-drifting environment. In this paper we address a realistic fraud-detection setting and we show that investigator's feedbacks and delayed labels have to be handled separately. We design two FDSs on the basis of an ensemble and a sliding-window approach and we show that the winning strategy consists in training two separate classifiers (on feedbacks and delayed labels, respectively), and then aggregating the outcomes. Experiments on large dataset of real-world transactions show that the alert precision, which is the primary concern of investigators, can be substantially improved by the proposed approach. |
Han, The Anh T A H; Lenaerts, Tom The efficient interaction of costly punishment and commitment Journal Article In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 3 , pp. 1657-1658, 2015, (Language of publication: en). @article{info:hdl:2013/220750, title = {The efficient interaction of costly punishment and commitment}, author = {The Anh T A H Han and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/220750}, year = {2015}, date = {2015-01-01}, journal = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS}, volume = {3}, pages = {1657-1658}, abstract = {To ensure cooperation in the Prisoner's Dilemma, agents may require prior commitments from others, subject to compensations when defecting after agreeing to commit. Alternatively, agents may prefer to behave reactively, without arranging prior commitments, by simply punishing those who misbehave. These two mechanisms have been shown to promote the emergence of cooperation, yet are complementary in the way they aim to instigate cooperation. In this work, using Evolutionary Game Theory, we describe a computational model showing that there is a wide range of parameters where the combined strategy is better than either strategy by itself, leading to a significantly higher level of cooperation. Interestingly, the improvement is most significant when the cost of arranging commitments is sufficiently high and the penalty reaches a certain threshold, thereby overcoming the weaknesses of both strategies.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } To ensure cooperation in the Prisoner's Dilemma, agents may require prior commitments from others, subject to compensations when defecting after agreeing to commit. Alternatively, agents may prefer to behave reactively, without arranging prior commitments, by simply punishing those who misbehave. These two mechanisms have been shown to promote the emergence of cooperation, yet are complementary in the way they aim to instigate cooperation. In this work, using Evolutionary Game Theory, we describe a computational model showing that there is a wide range of parameters where the combined strategy is better than either strategy by itself, leading to a significantly higher level of cooperation. Interestingly, the improvement is most significant when the cost of arranging commitments is sufficiently high and the penalty reaches a certain threshold, thereby overcoming the weaknesses of both strategies. |
Han, The Anh T A H; 'i, Lu; Santos, Francisco C; Lenaerts, Tom Emergence of cooperation via intention recognition, commitment and apology-A research summary Journal Article In: AI communications, 28 (4), pp. 709-715, 2015, (DOI: 10.3233/AIC-150672). @article{info:hdl:2013/220724, title = {Emergence of cooperation via intention recognition, commitment and apology-A research summary}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Francisco C Santos and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/220724}, year = {2015}, date = {2015-01-01}, journal = {AI communications}, volume = {28}, number = {4}, pages = {709-715}, abstract = {The mechanisms of emergence and evolution of cooperation in populations of abstract individuals, with diverse behavioral strategies in co-presence, have been undergoing mathematical study via evolutionary game theory, inspired in part on evolutionary psychology. Their systematic study resorts to simulation techniques, thus enabling the study of aforesaid mechanisms under a variety of conditions, parameters and alternative virtual games. The theoretical and experimental results have continually been surprising, rewarding and promising. In our recent work, we initiated the introduction, in such groups of individuals, of cognitive abilities inspired on techniques and theories of Artificial Intelligence, namely those pertaining to Intention Recognition, Commitment and Apology (separately and jointly), encompassing errors in decision-making and communication noise. As a result, both the emergence and stability of cooperation become reinforced comparatively to the absence of such cognitive abilities. This holds separately for Intention Recognition, for Commitment and for Apology, and even more so when they are jointly engaged. Our presentation aims to sensitize the reader to these evolutionary game theory based issues, results and prospects, which are accruing in importance for the modeling of minds with machines, with impact on our understanding of the evolution of mutual tolerance and cooperation. Recognition of someone's intentions, which may include imagining the recognition others have of our own intentions, and may comprise not just some error tolerance, but also a penalty for unfulfilled commitment though allowing for apology, can lead to evolutionary stable win/win equilibriums within groups of individuals, and perhaps amongst groups. The recognition and the manifestation of intentions, plus the assumption of commitment-even whilst paying a cost for putting it in place-and the acceptance of apology, are all facilitators in that respect, each of them singly and, above all, in collusion.}, note = {DOI: 10.3233/AIC-150672}, keywords = {}, pubstate = {published}, tppubtype = {article} } The mechanisms of emergence and evolution of cooperation in populations of abstract individuals, with diverse behavioral strategies in co-presence, have been undergoing mathematical study via evolutionary game theory, inspired in part on evolutionary psychology. Their systematic study resorts to simulation techniques, thus enabling the study of aforesaid mechanisms under a variety of conditions, parameters and alternative virtual games. The theoretical and experimental results have continually been surprising, rewarding and promising. In our recent work, we initiated the introduction, in such groups of individuals, of cognitive abilities inspired on techniques and theories of Artificial Intelligence, namely those pertaining to Intention Recognition, Commitment and Apology (separately and jointly), encompassing errors in decision-making and communication noise. As a result, both the emergence and stability of cooperation become reinforced comparatively to the absence of such cognitive abilities. This holds separately for Intention Recognition, for Commitment and for Apology, and even more so when they are jointly engaged. Our presentation aims to sensitize the reader to these evolutionary game theory based issues, results and prospects, which are accruing in importance for the modeling of minds with machines, with impact on our understanding of the evolution of mutual tolerance and cooperation. Recognition of someone's intentions, which may include imagining the recognition others have of our own intentions, and may comprise not just some error tolerance, but also a penalty for unfulfilled commitment though allowing for apology, can lead to evolutionary stable win/win equilibriums within groups of individuals, and perhaps amongst groups. The recognition and the manifestation of intentions, plus the assumption of commitment-even whilst paying a cost for putting it in place-and the acceptance of apology, are all facilitators in that respect, each of them singly and, above all, in collusion. |
Gazzo, Andrea; Daneels, Dorien; Cilia, Elisa; Bonduelle, Maryse; Abramowicz, Marc; Dooren, Sonia Van; Smits, Guillaume; Lenaerts, Tom DIDA: A curated and annotated digenic diseases database. Journal Article In: Nucleic acids research, 2015, (DOI: 10.1093/nar/gkv1068). @article{info:hdl:2013/220549, title = {DIDA: A curated and annotated digenic diseases database.}, author = {Andrea Gazzo and Dorien Daneels and Elisa Cilia and Maryse Bonduelle and Marc Abramowicz and Sonia Van Dooren and Guillaume Smits and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/220549/3/doi_204176.pdf}, year = {2015}, date = {2015-01-01}, journal = {Nucleic acids research}, abstract = {DIDA (DIgenic diseases DAtabase) is a novel database that provides for the first time detailed information on genes and associated genetic variants involved in digenic diseases, the simplest form of oligogenic inheritance. The database is accessible via http://dida.ibsquare.be and currently includes 213 digenic combinations involved in 44 different digenic diseases. These combinations are composed of 364 distinct variants, which are distributed over 136 distinct genes. The web interface provides browsing and search functionalities, as well as documentation and help pages, general database statistics and references to the original publications from which the data have been collected. The possibility to submit novel digenic data to DIDA is also provided. Creating this new repository was essential as current databases do not allow one to retrieve detailed records regarding digenic combinations. Genes, variants, diseases and digenic combinations in DIDA are annotated with manually curated information and information mined from other online resources. Next to providing a unique resource for the development of new analysis methods, DIDA gives clinical and molecular geneticists a tool to find the most comprehensive information on the digenic nature of their diseases of interest.}, note = {DOI: 10.1093/nar/gkv1068}, keywords = {}, pubstate = {published}, tppubtype = {article} } DIDA (DIgenic diseases DAtabase) is a novel database that provides for the first time detailed information on genes and associated genetic variants involved in digenic diseases, the simplest form of oligogenic inheritance. The database is accessible via http://dida.ibsquare.be and currently includes 213 digenic combinations involved in 44 different digenic diseases. These combinations are composed of 364 distinct variants, which are distributed over 136 distinct genes. The web interface provides browsing and search functionalities, as well as documentation and help pages, general database statistics and references to the original publications from which the data have been collected. The possibility to submit novel digenic data to DIDA is also provided. Creating this new repository was essential as current databases do not allow one to retrieve detailed records regarding digenic combinations. Genes, variants, diseases and digenic combinations in DIDA are annotated with manually curated information and information mined from other online resources. Next to providing a unique resource for the development of new analysis methods, DIDA gives clinical and molecular geneticists a tool to find the most comprehensive information on the digenic nature of their diseases of interest. |
Sekara, Mateusz; Kowalski, Michael; Byrski, Aleksander; Indurkhya, Bipin; Kisiel-Dorohinicki, Marek; Samson, Dana; Lenaerts, Tom Multi-pheromone ant Colony Optimization for Socio-cognitive Simulation Purposes Journal Article In: Procedia Computer Science, 51 , pp. 954-963, 2015, (DOI: 10.1016/j.procs.2015.05.234). @article{info:hdl:2013/206321, title = {Multi-pheromone ant Colony Optimization for Socio-cognitive Simulation Purposes}, author = {Mateusz Sekara and Michael Kowalski and Aleksander Byrski and Bipin Indurkhya and Marek Kisiel-Dorohinicki and Dana Samson and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/206321/1/Elsevier_189948.pdf}, year = {2015}, date = {2015-01-01}, journal = {Procedia Computer Science}, volume = {51}, pages = {954-963}, abstract = {We present an application of Ant Colony Optimisation (ACO) to simulate socio-cognitive features of a population. We incorporated perspective taking ability to generate three different proportions of ant colonies: Control Sample, High Altercentricity Sample, and Low Altercentricity Sample. We simulated their performances on the Travelling Salesman Problem and compared them with the classic ACO. Results show that all three 'cognitively enabled' ant colonies require less time than the classic ACO. Also, though the best solution is found by the classic ACO, the Control Sample finds almost as good a solution but much faster. This study is offered as an example to illustrate an easy way of defining inter-individual interactions based on stigmergic features of the environment.}, note = {DOI: 10.1016/j.procs.2015.05.234}, keywords = {}, pubstate = {published}, tppubtype = {article} } We present an application of Ant Colony Optimisation (ACO) to simulate socio-cognitive features of a population. We incorporated perspective taking ability to generate three different proportions of ant colonies: Control Sample, High Altercentricity Sample, and Low Altercentricity Sample. We simulated their performances on the Travelling Salesman Problem and compared them with the classic ACO. Results show that all three 'cognitively enabled' ant colonies require less time than the classic ACO. Also, though the best solution is found by the classic ACO, the Control Sample finds almost as good a solution but much faster. This study is offered as an example to illustrate an easy way of defining inter-individual interactions based on stigmergic features of the environment. |
Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Avoiding or restricting defectors in public goods games? Journal Article In: Journal of the Royal Society interface, 12 (103), pp. 20141203, 2015, (DOI: 10.1098/rsif.2014.1203). @article{info:hdl:2013/205981, title = {Avoiding or restricting defectors in public goods games?}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/205981}, year = {2015}, date = {2015-01-01}, journal = {Journal of the Royal Society interface}, volume = {12}, number = {103}, pages = {20141203}, abstract = {When creating a public good, strategies or mechanisms are required to handle defectors. We first show mathematically and numerically that prior agreements with posterior compensations provide a strategic solution that leads to substantial levels of cooperation in the context of public goods games, results that are corroborated by available experimental data. Notwithstanding this success, one cannot, as with other approaches, fully exclude the presence of defectors, raising the question of how they can be dealt with to avoid the demise of the common good. We show that both avoiding creation of the common good, whenever full agreement is not reached, and limiting the benefit that disagreeing defectors can acquire, using costly restriction mechanisms, are relevant choices. Nonetheless, restriction mechanisms are found the more favourable, especially in larger group interactions. Given decreasing restriction costs, introducing restraining measures to cope with public goods free-riding issues is the ultimate advantageous solution for all participants, rather than avoiding its creation.}, note = {DOI: 10.1098/rsif.2014.1203}, keywords = {}, pubstate = {published}, tppubtype = {article} } When creating a public good, strategies or mechanisms are required to handle defectors. We first show mathematically and numerically that prior agreements with posterior compensations provide a strategic solution that leads to substantial levels of cooperation in the context of public goods games, results that are corroborated by available experimental data. Notwithstanding this success, one cannot, as with other approaches, fully exclude the presence of defectors, raising the question of how they can be dealt with to avoid the demise of the common good. We show that both avoiding creation of the common good, whenever full agreement is not reached, and limiting the benefit that disagreeing defectors can acquire, using costly restriction mechanisms, are relevant choices. Nonetheless, restriction mechanisms are found the more favourable, especially in larger group interactions. Given decreasing restriction costs, introducing restraining measures to cope with public goods free-riding issues is the ultimate advantageous solution for all participants, rather than avoiding its creation. |
Martinez-Vaquero, Luis L A; Han, The Anh T A H; 'i, Lu; Lenaerts, Tom Apology and forgiveness evolve to resolve failures in cooperative agreements Journal Article In: Scientific reports, 5 , 2015, (DOI: 10.1038/srep10639). @article{info:hdl:2013/205370, title = {Apology and forgiveness evolve to resolve failures in cooperative agreements}, author = {Luis L A Martinez-Vaquero and The Anh T A H Han and Lu{'i}s Marcelo Pereira and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/205370}, year = {2015}, date = {2015-01-01}, journal = {Scientific reports}, volume = {5}, abstract = {Making agreements on how to behave has been shown to be an evolutionarily viable strategy in one-shot social dilemmas. However, in many situations agreements aim to establish long-term mutually beneficial interactions. Our analytical and numerical results reveal for the first time under which conditions revenge, apology and forgiveness can evolve and deal with mistakes within ongoing agreements in the context of the Iterated Prisoners Dilemma. We show that, when the agreement fails, participants prefer to take revenge by defecting in the subsisting encounters. Incorporating costly apology and forgiveness reveals that, even when mistakes are frequent, there exists a sincerity threshold for which mistakes will not lead to the destruction of the agreement, inducing even higher levels of cooperation. In short, even when to err is human, revenge, apology and forgiveness are evolutionarily viable strategies which play an important role in inducing cooperation in repeated dilemmas.}, note = {DOI: 10.1038/srep10639}, keywords = {}, pubstate = {published}, tppubtype = {article} } Making agreements on how to behave has been shown to be an evolutionarily viable strategy in one-shot social dilemmas. However, in many situations agreements aim to establish long-term mutually beneficial interactions. Our analytical and numerical results reveal for the first time under which conditions revenge, apology and forgiveness can evolve and deal with mistakes within ongoing agreements in the context of the Iterated Prisoners Dilemma. We show that, when the agreement fails, participants prefer to take revenge by defecting in the subsisting encounters. Incorporating costly apology and forgiveness reveals that, even when mistakes are frequent, there exists a sincerity threshold for which mistakes will not lead to the destruction of the agreement, inducing even higher levels of cooperation. In short, even when to err is human, revenge, apology and forgiveness are evolutionarily viable strategies which play an important role in inducing cooperation in repeated dilemmas. |
Han, The Anh T A H; Santos, Francisco C; Lenaerts, Tom; 'i, Lu Synergy between intention recognition and commitments in cooperation dilemmas Journal Article In: Scientific Reports, 5 , 2015, (DOI: 10.1038/srep09312). @article{info:hdl:2013/197743, title = {Synergy between intention recognition and commitments in cooperation dilemmas}, author = {The Anh T A H Han and Francisco C Santos and Tom Lenaerts and Lu{'i}s Marcelo Pereira}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/197743}, year = {2015}, date = {2015-01-01}, journal = {Scientific Reports}, volume = {5}, abstract = {Commitments have been shown to promote cooperation if, on the one hand, they can be sufficiently enforced, and on the other hand, the cost of arranging them is justified with respect to the benefits of cooperation. When either of these constraints is not met it leads to the prevalence of commitment free-riders, such as those who commit only when someone else pays to arrange the commitments. Here, we show how intention recognition may circumvent such weakness of costly commitments. We describe an evolutionary model, in the context of the one-shot Prisoner's Dilemma, showing that if players first predict the intentions of their co-player and propose a commitment only when they are not confident enough about their prediction, the chances of reaching mutual cooperation are largely enhanced. We find that an advantageous synergy between intention recognition and costly commitments depends strongly on the confidence and accuracy of intention recognition. In general, we observe an intermediate level of confidence threshold leading to the highest evolutionary advantage, showing that neither unconditional use of commitment nor intention recognition can perform optimally. Rather, our results show that arranging commitments is not always desirable, but that they may be also unavoidable depending on the strength of the dilemma.}, note = {DOI: 10.1038/srep09312}, keywords = {}, pubstate = {published}, tppubtype = {article} } Commitments have been shown to promote cooperation if, on the one hand, they can be sufficiently enforced, and on the other hand, the cost of arranging them is justified with respect to the benefits of cooperation. When either of these constraints is not met it leads to the prevalence of commitment free-riders, such as those who commit only when someone else pays to arrange the commitments. Here, we show how intention recognition may circumvent such weakness of costly commitments. We describe an evolutionary model, in the context of the one-shot Prisoner's Dilemma, showing that if players first predict the intentions of their co-player and propose a commitment only when they are not confident enough about their prediction, the chances of reaching mutual cooperation are largely enhanced. We find that an advantageous synergy between intention recognition and costly commitments depends strongly on the confidence and accuracy of intention recognition. In general, we observe an intermediate level of confidence threshold leading to the highest evolutionary advantage, showing that neither unconditional use of commitment nor intention recognition can perform optimally. Rather, our results show that arranging commitments is not always desirable, but that they may be also unavoidable depending on the strength of the dilemma. |
Pozzolo, Andrea Dal; Caelen, Olivier; Bontempi, Gianluca When is undersampling effective in unbalanced classification tasks? Book Chapter In: Springer, 2015, (Language of publication: en). @inbook{info:hdl:2013/221669, title = {When is undersampling effective in unbalanced classification tasks?}, author = {Andrea Dal Pozzolo and Olivier Caelen and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/221669}, year = {2015}, date = {2015-01-01}, publisher = {Springer}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
Pozzolo, Andrea Dal Adaptive Machine Learning for Credit Card Fraud Detection PhD Thesis 2015, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/221654, title = {Adaptive Machine Learning for Credit Card Fraud Detection}, author = {Andrea Dal Pozzolo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/221654/5/contratDalPozzolo.pdf}, year = {2015}, date = {2015-01-01}, abstract = {Billions of dollars of loss are caused every year by fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to the non-stationary distribution of the data, the highly unbalanced classes distributions and the availability of few transactions labeled by fraud investigators. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about what is the best strategy. In this thesis we aim to provide some answers by focusing on crucial issues such as: i) why and how undersampling is useful in the presence of class imbalance (i.e. frauds are a small percentage of the transactions), ii) how to deal with unbalanced and evolving data streams (non-stationarity due to fraud evolution and change of spending behavior), iii) how to assess performances in a way which is relevant for detection and iv) how to use feedbacks provided by investigators on the fraud alerts generated. Finally, we design and assess a prototype of a Fraud Detection System able to meet real-world working conditions and that is able to integrate investigators' feedback to generate accurate alerts.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } Billions of dollars of loss are caused every year by fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to the non-stationary distribution of the data, the highly unbalanced classes distributions and the availability of few transactions labeled by fraud investigators. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about what is the best strategy. In this thesis we aim to provide some answers by focusing on crucial issues such as: i) why and how undersampling is useful in the presence of class imbalance (i.e. frauds are a small percentage of the transactions), ii) how to deal with unbalanced and evolving data streams (non-stationarity due to fraud evolution and change of spending behavior), iii) how to assess performances in a way which is relevant for detection and iv) how to use feedbacks provided by investigators on the fraud alerts generated. Finally, we design and assess a prototype of a Fraud Detection System able to meet real-world working conditions and that is able to integrate investigators' feedback to generate accurate alerts. |
Lopes, Miguel Inference of gene networks from time series expression data and application to type 1 Diabetes PhD Thesis 2015, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/216729, title = {Inference of gene networks from time series expression data and application to type 1 Diabetes}, author = {Miguel Lopes}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/216729/6/contratGasparLopes.pdf}, year = {2015}, date = {2015-01-01}, abstract = {The inference of gene regulatory networks (GRN) is of great importance to medical research, as causal mechanisms responsible for phenotypes are unravelled and potential therapeutical targets identified. In type 1 diabetes, insulin producing pancreatic beta-cells are the target of an auto-immune attack leading to apoptosis (cell suicide). Although key genes and regulations have been identified, a precise characterization of the process leading to beta-cell apoptosis has not been achieved yet. The inference of relevant molecular pathways in type 1 diabetes is then a crucial research topic. GRN inference from gene expression data (obtained from microarrays and RNA-seq technology) is a causal inference problem which may be tackled with well-established statistical and machine learning concepts. In particular, the use of time series facilitates the identification of the causal direction in cause-effect gene pairs. However, inference from gene expression data is a very challenging problem due to the large number of existing genes (in human, over twenty thousand) and the typical low number of samples in gene expression datasets. In this context, it is important to correctly assess the accuracy of network inference methods. The contributions of this thesis are on three distinct aspects. The first is on inference assessment using precision-recall curves, in particular using the area under the curve (AUPRC). The typical approach to assess AUPRC significance is using Monte Carlo, and a parametric alternative is proposed. It consists on deriving the mean and variance of the null AUPRC and then using these parameters to fit a beta distribution approximating the true distribution. The second contribution is an investigation on network inference from time series. Several state of the art strategies are experimentally assessed and novel heuristics are proposed. One is a fast approximation of first order Granger causality scores, suited for GRN inference in the large variable case. Another identifies co-regulated genes (ie. regulated by the same genes). Both are experimentally validated using microarray and simulated time series. The third contribution of this thesis is on the context of type 1 diabetes and is a study on beta cell gene expression after exposure to cytokines, emulating the mechanisms leading to apoptosis. 8 datasets of beta cell gene expression were used to identify differentially expressed genes before and after 24h, which were functionally characterized using bioinformatics tools. The two most differentially expressed genes, previously unknown in the type 1 Diabetes literature (RIPK2 and ELF3) were found to modulate cytokine induced apoptosis. A regulatory network was then inferred using a dynamic adaptation of a state of the art network inference method. Three out of four predicted regulations (involving RIPK2 and ELF3) were experimentally confirmed, providing a proof of concept for the adopted approach.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } The inference of gene regulatory networks (GRN) is of great importance to medical research, as causal mechanisms responsible for phenotypes are unravelled and potential therapeutical targets identified. In type 1 diabetes, insulin producing pancreatic beta-cells are the target of an auto-immune attack leading to apoptosis (cell suicide). Although key genes and regulations have been identified, a precise characterization of the process leading to beta-cell apoptosis has not been achieved yet. The inference of relevant molecular pathways in type 1 diabetes is then a crucial research topic. GRN inference from gene expression data (obtained from microarrays and RNA-seq technology) is a causal inference problem which may be tackled with well-established statistical and machine learning concepts. In particular, the use of time series facilitates the identification of the causal direction in cause-effect gene pairs. However, inference from gene expression data is a very challenging problem due to the large number of existing genes (in human, over twenty thousand) and the typical low number of samples in gene expression datasets. In this context, it is important to correctly assess the accuracy of network inference methods. The contributions of this thesis are on three distinct aspects. The first is on inference assessment using precision-recall curves, in particular using the area under the curve (AUPRC). The typical approach to assess AUPRC significance is using Monte Carlo, and a parametric alternative is proposed. It consists on deriving the mean and variance of the null AUPRC and then using these parameters to fit a beta distribution approximating the true distribution. The second contribution is an investigation on network inference from time series. Several state of the art strategies are experimentally assessed and novel heuristics are proposed. One is a fast approximation of first order Granger causality scores, suited for GRN inference in the large variable case. Another identifies co-regulated genes (ie. regulated by the same genes). Both are experimentally validated using microarray and simulated time series. The third contribution of this thesis is on the context of type 1 diabetes and is a study on beta cell gene expression after exposure to cytokines, emulating the mechanisms leading to apoptosis. 8 datasets of beta cell gene expression were used to identify differentially expressed genes before and after 24h, which were functionally characterized using bioinformatics tools. The two most differentially expressed genes, previously unknown in the type 1 Diabetes literature (RIPK2 and ELF3) were found to modulate cytokine induced apoptosis. A regulatory network was then inferred using a dynamic adaptation of a state of the art network inference method. Three out of four predicted regulations (involving RIPK2 and ELF3) were experimentally confirmed, providing a proof of concept for the adopted approach. |
Lerman, Liran A machine learning approach for automatic and generic side-channel attacks PhD Thesis 2015, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/209070, title = {A machine learning approach for automatic and generic side-channel attacks}, author = {Liran Lerman}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/209070/2/be487c5b-7b94-414c-bf2e-96847aa98284.txt}, year = {2015}, date = {2015-01-01}, abstract = {L'omniprésence de dispositifs interconnectés am`ene `a un intér^et massif pour la sécurité informatique fournie entre autres par le domaine de la cryptographie. Pendant des décennies, les spécialistes en cryptographie estimaient le niveau de sécurité d'un algorithme cryptographique indépendamment de son implantation dans un dispositif. Cependant, depuis la publication des attaques d'implantation en 1996, les attaques physiques sont devenues un domaine de recherche actif en considérant les propriétés physiques de dispositifs cryptographiques. Dans notre dissertation, nous nous concentrons sur les attaques profilées. Traditionnellement, les attaques profilées appliquent des méthodes paramétriques dans lesquelles une information a priori sur les propriétés physiques est supposée. Le domaine de l'apprentissage automatique produit des mod`eles automatiques et génériques ne nécessitant pas une information a priori sur le phénom`ene étudié. Cette dissertation apporte un éclairage nouveau sur les capacités des méthodes d'apprentissage automatique. Nous démontrons d'abord que les attaques profilées paramétriques surpassent les méthodes d'apprentissage automatique lorsqu'il n'y a pas d'erreur d'estimation ni d'hypoth`ese. En revanche, les attaques fondées sur l'apprentissage automatique sont avantageuses dans des scénarios réalistes o`u le nombre de données lors de l'étape d'apprentissage est faible. Par la suite, nous proposons une nouvelle métrique formelle d'évaluation qui permet (1) de comparer des attaques paramétriques et non-paramétriques et (2) d'interpréter les résultats de chaque méthode. La nouvelle mesure fournit les causes d'un taux de réussite élevé ou faible d'une attaque et, par conséquent, donne des pistes pour améliorer l'évaluation d'une implantation. Enfin, nous présentons des résultats expérimentaux sur des appareils non protégés et protégés. La premi`ere étude montre que l'apprentissage automatique a un taux de réussite plus élevé qu'une méthode paramétrique lorsque seules quelques données sont disponibles. La deuxi`eme expérience démontre qu'un dispositif protégé est attaquable avec une approche appartenant `a l'apprentissage automatique. La stratégie basée sur l'apprentissage automatique nécessite le m^eme nombre de données lors de la phase d'apprentissage que lorsque celle-ci attaque un produit non protégé. Nous montrons également que des méthodes paramétriques surestiment ou sous-estiment le niveau de sécurité fourni par l'appareil alors que l'approche basée sur l'apprentissage automatique améliore cette estimation. En résumé, notre th`ese est que les attaques basées sur l'apprentissage automatique sont avantageuses par rapport aux techniques classiques lorsque la quantité d'information a priori sur l'appareil cible et le nombre de données lors de la phase d'apprentissage sont faibles.}, L'omniprésence de dispositifs interconnectés am`ene `a un intér^et massif pour la sécurité informatique fournie entre autres par le domaine de la cryptographie. Pendant des décennies, les spécialistes en cryptographie estimaient le niveau de sécurité d'un algorithme cryptographique indépendamment de son implantation dans un dispositif. Cependant, depuis la publication des attaques d'implantation en 1996, les attaques physiques sont devenues un domaine de recherche actif en considérant les propriétés physiques de dispositifs cryptographiques. Dans notre dissertation, nous nous concentrons sur les attaques profilées. Traditionnellement, les attaques profilées appliquent des méthodes paramétriques dans lesquelles une information a priori sur les propriétés physiques est supposée. Le domaine de l'apprentissage automatique produit des mod`eles automatiques et génériques ne nécessitant pas une information a priori sur le phénom`ene étudié.<p><p>Cette dissertation apporte un éclairage nouveau sur les capacités des méthodes d'apprentissage automatique. Nous démontrons d'abord que les attaques profilées paramétriques surpassent les méthodes d'apprentissage automatique lorsqu'il n'y a pas d'erreur d'estimation ni d'hypoth`ese. En revanche, les attaques fondées sur l'apprentissage automatique sont avantageuses dans des scénarios réalistes o`u le nombre de données lors de l'étape d'apprentissage est faible. Par la suite, nous proposons une nouvelle métrique formelle d'évaluation qui permet (1) de comparer des attaques paramétriques et non-paramétriques et (2) d'interpréter les résultats de chaque méthode. La nouvelle mesure fournit les causes d'un taux de réussite élevé ou faible d'une attaque et, par conséquent, donne des pistes pour améliorer l'évaluation d'une implantation. Enfin, nous présentons des résultats expérimentaux sur des appareils non protégés et protégés. La premi`ere étude montre que l'apprentissage automatique a un taux de réussite plus élevé qu'une méthode paramétrique lorsque seules quelques données sont disponibles. La deuxi`eme expérience démontre qu'un dispositif protégé est attaquable avec une approche appartenant `a l'apprentissage automatique. La stratégie basée sur l'apprentissage automatique nécessite le m^eme nombre de données lors de la phase d'apprentissage que lorsque celle-ci attaque un produit non protégé. Nous montrons également que des méthodes paramétriques surestiment ou sous-estiment le niveau de sécurité fourni par l'appareil alors que l'approche basée sur l'apprentissage automatique améliore cette estimation. <p><p>En résumé, notre th`ese est que les attaques basées sur l'apprentissage automatique sont avantageuses par rapport aux techniques classiques lorsque la quantité d'information a priori sur l'appareil cible et le nombre de données lors de la phase d'apprentissage sont faibles. |
Hajingabo, Leon 2015, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/209126, title = {Analyzing molecular network perturbations in human cancer: application to mutated genes and gene fusions involved in acute lymphoblastic leukemia}, author = {Leon Hajingabo}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/209126/3/d6d6225e-dfa8-46a3-985a-2ef19c71eff1.txt}, year = {2015}, date = {2015-01-01}, abstract = {Le séquenc cage du génome humain et l'émergence de nouvelles technologies de génomique `a haut débit, ont initié de nouveaux mod`eles d'investigation pour l'analyse systématique des maladies humaines. Actuellement, nous pouvons tenter de comprendre les maladies tel que le cancer avec une perspective plus globale, en identifiant des g`enes responsables des cancers et en étudiant la mani`ere dont leurs produits protéiques fonctionnent dans un réseau d'interactions moléculaires. Dans ce contexte, nous avons collecté les g`enes spécifiquement liés `a la Leucémie Lymphoblastique Aigu"e (LLA), et identifié de nouveaux partenaires d'interaction qui relient ces g`enes clés associés `a la LLA tels que NOTCH1, FBW7, KRAS et PTPN11, dans un réseau d'interactions. Nous avons également tenté de prédire l'impact fonctionnel des variations génomiques tel que des fusions de g`enes impliquées dans LLA. En utilisant comme mod`eles trois différentes translocations chromosomiques ETV6-RUNX1 (TEL-AML1), BCR-ABL1, et E2A-PBX1 (TCF3-PBX1) fréquemment identifiées dans des cellules B LLA, nous avons adapté une approche de prédiction d'oncog`enes afin de prédire des perturbations moléculaires dans la LLA. Nous avons montré que les circuits transcriptomiques dépendant de Myc et JunD sont spécifiquement dérégulés suite aux fusions de g`enes TEL-AML1 et TCF3-PBX1, respectivement. Nous avons également identifié le mécanisme de transport des ARNm dépendant du facteur NXF1 comme une cible directe de la protéine de fusion TCF3-PBX1. Gr^ace `a cette approche combinant les données interactomiques et les analyses d'expression génique, nous avons fourni un nouvel aperc cu `a la compréhension moléculaire de la Leucémie Lymphoblastique Aigu"e.}, note = {Funder: Universite Libre de Bruxelles}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } Le séquenc cage du génome humain et l'émergence de nouvelles technologies de génomique `a haut débit, ont initié de nouveaux mod`eles d'investigation pour l'analyse systématique des maladies humaines. Actuellement, nous pouvons tenter de comprendre les maladies tel que le cancer avec une perspective plus globale, en identifiant des g`enes responsables des cancers et en étudiant la mani`ere dont leurs produits protéiques fonctionnent dans un réseau d'interactions moléculaires. Dans ce contexte, nous avons collecté les g`enes spécifiquement liés `a la Leucémie Lymphoblastique Aigu"e (LLA), et identifié de nouveaux partenaires d'interaction qui relient ces g`enes clés associés `a la LLA tels que NOTCH1, FBW7, KRAS et PTPN11, dans un réseau d'interactions. Nous avons également tenté de prédire l'impact fonctionnel des variations génomiques tel que des fusions de g`enes impliquées dans LLA. En utilisant comme mod`eles trois différentes translocations chromosomiques ETV6-RUNX1 (TEL-AML1), BCR-ABL1, et E2A-PBX1 (TCF3-PBX1) fréquemment identifiées dans des cellules B LLA, nous avons adapté une approche de prédiction d'oncog`enes afin de prédire des perturbations moléculaires dans la LLA. Nous avons montré que les circuits transcriptomiques dépendant de Myc et JunD sont spécifiquement dérégulés suite aux fusions de g`enes TEL-AML1 et TCF3-PBX1, respectivement. Nous avons également identifié le mécanisme de transport des ARNm dépendant du facteur NXF1 comme une cible directe de la protéine de fusion TCF3-PBX1. Gr^ace `a cette approche combinant les données interactomiques et les analyses d'expression génique, nous avons fourni un nouvel aperc cu `a la compréhension moléculaire de la Leucémie Lymphoblastique Aigu"e. |
Colaprico, Antonio; Silva, Tiago Da; Olsen, Catharina; Garofano, Luciano; Cava, Claudia; Garolini, Davide; Sabedot, Thais TS; Malta, Tathiane TM; Pagnotta, Stefano SM; Castiglioni, Isabella; Ceccarelli, M; Bontempi, Gianluca; Noushmehr, Houtan TCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data. Journal Article In: Nucleic acids research, 2015, (DOI: 10.1093/nar/gkv1507). @article{info:hdl:2013/222877, title = {TCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data.}, author = {Antonio Colaprico and Tiago Da Silva and Catharina Olsen and Luciano Garofano and Claudia Cava and Davide Garolini and Thais TS Sabedot and Tathiane TM Malta and Stefano SM Pagnotta and Isabella Castiglioni and M Ceccarelli and Gianluca Bontempi and Houtan Noushmehr}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/222877/5/doi_206504.pdf}, year = {2015}, date = {2015-01-01}, journal = {Nucleic acids research}, abstract = {The Cancer Genome Atlas (TCGA) research network has made public a large collection of clinical and molecular phenotypes of more than 10 000 tumor patients across 33 different tumor types. Using this cohort, TCGA has published over 20 marker papers detailing the genomic and epigenomic alterations associated with these tumor types. Although many important discoveries have been made by TCGA's research network, opportunities still exist to implement novel methods, thereby elucidating new biological pathways and diagnostic markers. However, mining the TCGA data presents several bioinformatics challenges, such as data retrieval and integration with clinical data and other molecular data types (e.g. RNA and DNA methylation). We developed an R/Bioconductor package called TCGAbiolinks to address these challenges and offer bioinformatics solutions by using a guided workflow to allow users to query, download and perform integrative analyses of TCGA data. We combined methods from computer science and statistics into the pipeline and incorporated methodologies developed in previous TCGA marker studies and in our own group. Using four different TCGA tumor types (Kidney, Brain, Breast and Colon) as examples, we provide case studies to illustrate examples of reproducibility, integrative analysis and utilization of different Bioconductor packages to advance and accelerate novel discoveries.}, note = {DOI: 10.1093/nar/gkv1507}, keywords = {}, pubstate = {published}, tppubtype = {article} } The Cancer Genome Atlas (TCGA) research network has made public a large collection of clinical and molecular phenotypes of more than 10 000 tumor patients across 33 different tumor types. Using this cohort, TCGA has published over 20 marker papers detailing the genomic and epigenomic alterations associated with these tumor types. Although many important discoveries have been made by TCGA's research network, opportunities still exist to implement novel methods, thereby elucidating new biological pathways and diagnostic markers. However, mining the TCGA data presents several bioinformatics challenges, such as data retrieval and integration with clinical data and other molecular data types (e.g. RNA and DNA methylation). We developed an R/Bioconductor package called TCGAbiolinks to address these challenges and offer bioinformatics solutions by using a guided workflow to allow users to query, download and perform integrative analyses of TCGA data. We combined methods from computer science and statistics into the pipeline and incorporated methodologies developed in previous TCGA marker studies and in our own group. Using four different TCGA tumor types (Kidney, Brain, Breast and Colon) as examples, we provide case studies to illustrate examples of reproducibility, integrative analysis and utilization of different Bioconductor packages to advance and accelerate novel discoveries. |
Lerman, Liran; Bontempi, Gianluca; Markowitch, Olivier The bias--variance decomposition in profiled attacks Journal Article In: Journal of Cryptographic Engineering, 5 (4), pp. 255-267, 2015, (DOI: 10.1007/s13389-015-0106-1). @article{info:hdl:2013/220673, title = {The bias--variance decomposition in profiled attacks}, author = {Liran Lerman and Gianluca Bontempi and Olivier Markowitch}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/220673}, year = {2015}, date = {2015-01-01}, journal = {Journal of Cryptographic Engineering}, volume = {5}, number = {4}, pages = {255-267}, abstract = {The profiled attacks challenge the security of cryptographic devices in the worst case scenario. We elucidate the reasons underlying the success of different profiled attacks (that depend essentially on the context) based on the well-known bias--variance tradeoff developed in the machine learning field. Note that our approach can easily be extended to non-profiled attacks. We show (1) how to decompose (in three additive components) the error rate of an attack based on the bias--variance decomposition, and (2) how to reduce the error rate of a model based on the bias--variance diagnostic. Intuitively, we show that different models having the same error rate require different strategies (according to the bias--variance decomposition) to reduce their errors. More precisely, the success rate of a strategy depends on several criteria such as its complexity, the leakage information and the number of points per trace. As a result, a suboptimal strategy in a specific context can lead the adversary to overestimate the security level of the cryptographic device. Our results also bring warnings related to the estimation of the success rate of a profiled attack that can lead the evaluator to underestimate the security level. In brief, certify that a chip leaks (or not) sensitive information represents a hard if not impossible task.}, note = {DOI: 10.1007/s13389-015-0106-1}, keywords = {}, pubstate = {published}, tppubtype = {article} } The profiled attacks challenge the security of cryptographic devices in the worst case scenario. We elucidate the reasons underlying the success of different profiled attacks (that depend essentially on the context) based on the well-known bias--variance tradeoff developed in the machine learning field. Note that our approach can easily be extended to non-profiled attacks. We show (1) how to decompose (in three additive components) the error rate of an attack based on the bias--variance decomposition, and (2) how to reduce the error rate of a model based on the bias--variance diagnostic. Intuitively, we show that different models having the same error rate require different strategies (according to the bias--variance decomposition) to reduce their errors. More precisely, the success rate of a strategy depends on several criteria such as its complexity, the leakage information and the number of points per trace. As a result, a suboptimal strategy in a specific context can lead the adversary to overestimate the security level of the cryptographic device. Our results also bring warnings related to the estimation of the success rate of a profiled attack that can lead the evaluator to underestimate the security level. In brief, certify that a chip leaks (or not) sensitive information represents a hard if not impossible task. |
Lerman, Liran; Poussier, Romain; Bontempi, Gianluca; Markowitch, Olivier; c c, Fran Template attacks vs Machine Learning Revisited Journal Article In: Lecture notes in computer science, 9064 , pp. 20-33, 2015, (Language of publication: en). @article{info:hdl:2013/223764, title = {Template attacks vs Machine Learning Revisited}, author = {Liran Lerman and Romain Poussier and Gianluca Bontempi and Olivier Markowitch and Fran{c c}ois-Xavier Standaert}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/223764}, year = {2015}, date = {2015-01-01}, journal = {Lecture notes in computer science}, volume = {9064}, pages = {20-33}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Lerman, Liran; Bontempi, Gianluca; Markowitch, Olivier A machine learning approach against a masked AES: Reaching the limit of side-channel attacks with a learning model Journal Article In: Journal of Cryptographic Engineering, 5 (2), pp. 123-139, 2015, (DOI: 10.1007/s13389-014-0089-3). @article{info:hdl:2013/205371, title = {A machine learning approach against a masked AES: Reaching the limit of side-channel attacks with a learning model}, author = {Liran Lerman and Gianluca Bontempi and Olivier Markowitch}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/205371}, year = {2015}, date = {2015-01-01}, journal = {Journal of Cryptographic Engineering}, volume = {5}, number = {2}, pages = {123-139}, abstract = {Side-channel attacks challenge the security of cryptographic devices. A widespread countermeasure against these attacks is the masking approach. Masking combines sensitive variables with secret random values to reduce its leakage. In 2012, Nassar et al. (DATE, pp 1173--1178. IEEE, 2012) presented a new lightweight (low-cost) boolean masking countermeasure to protect the implementation of the Advanced Encryption Standard (AES) block-cipher. This masking scheme represents the target algorithm of the DPAContest V4 (http://www.dpacontest.org/home/, 2013). In this paper, we present the first machine learning attack against a specific masking countermeasure (more precisely the low-entropy boolean masking countermeasure of Nassar et al.), using the dataset of the DPAContest V4. We succeeded to extract each targeted byte of the key of the masked AES with 7.8 traces during the attacking phase with a strategy based solely on machine learning models. Finally, we compared our proposal with (1) a stochastic attack, (2) a strategy based on template attack and (3) a multivariate regression attack. We show that an attack based on a machine learning model reduces significantly the number of traces required during the attacking step compared to these profiling attacks when analyzing the same leakage information.}, note = {DOI: 10.1007/s13389-014-0089-3}, keywords = {}, pubstate = {published}, tppubtype = {article} } Side-channel attacks challenge the security of cryptographic devices. A widespread countermeasure against these attacks is the masking approach. Masking combines sensitive variables with secret random values to reduce its leakage. In 2012, Nassar et al. (DATE, pp 1173--1178. IEEE, 2012) presented a new lightweight (low-cost) boolean masking countermeasure to protect the implementation of the Advanced Encryption Standard (AES) block-cipher. This masking scheme represents the target algorithm of the DPAContest V4 (http://www.dpacontest.org/home/, 2013). In this paper, we present the first machine learning attack against a specific masking countermeasure (more precisely the low-entropy boolean masking countermeasure of Nassar et al.), using the dataset of the DPAContest V4. We succeeded to extract each targeted byte of the key of the masked AES with 7.8 traces during the attacking phase with a strategy based solely on machine learning models. Finally, we compared our proposal with (1) a stochastic attack, (2) a strategy based on template attack and (3) a multivariate regression attack. We show that an attack based on a machine learning model reduces significantly the number of traces required during the attacking step compared to these profiling attacks when analyzing the same leakage information. |
Olsen, Catharina; Fleming, Kathleen; Prendergast, Niall; Rubio, Renee; Emmert-Streib, Frank; Bontempi, Gianluca; Quackenbush, John; Haibe-Kains, Benjamin Using shRNA experiments to validate gene regulatory networks Journal Article In: Genomics Data, 4 , pp. 123-126, 2015, (DOI: 10.1016/j.gdata.2015.03.011). @article{info:hdl:2013/205439, title = {Using shRNA experiments to validate gene regulatory networks}, author = {Catharina Olsen and Kathleen Fleming and Niall Prendergast and Renee Rubio and Frank Emmert-Streib and Gianluca Bontempi and John Quackenbush and Benjamin Haibe-Kains}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/205439/4/doi_189066.pdf}, year = {2015}, date = {2015-01-01}, journal = {Genomics Data}, volume = {4}, pages = {123-126}, abstract = {Quantitative validation of gene regulatory networks (GRNs) inferred from observational expression data is a difficult task usually involving time intensive and costly laboratory experiments. We were able to show that gene knock-down experiments can be used to quantitatively assess the quality of large-scale GRNs via a purely data-driven approach (Olsen et al. 2014). Our new validation framework also enables the statistical comparison of multiple network inference techniques, which was a long-standing challenge in the field.In this Data in Brief we detail the contents and quality controls for the gene expression data (available from NCBI Gene Expression Omnibus repository with accession number GSE53091) associated with our study published in Genomics (Olsen et al. 2014). We also provide R code to access the data and reproduce the analysis presented in this article.}, note = {DOI: 10.1016/j.gdata.2015.03.011}, keywords = {}, pubstate = {published}, tppubtype = {article} } Quantitative validation of gene regulatory networks (GRNs) inferred from observational expression data is a difficult task usually involving time intensive and costly laboratory experiments. We were able to show that gene knock-down experiments can be used to quantitatively assess the quality of large-scale GRNs via a purely data-driven approach (Olsen et al. 2014). Our new validation framework also enables the statistical comparison of multiple network inference techniques, which was a long-standing challenge in the field.In this Data in Brief we detail the contents and quality controls for the gene expression data (available from NCBI Gene Expression Omnibus repository with accession number GSE53091) associated with our study published in Genomics (Olsen et al. 2014). We also provide R code to access the data and reproduce the analysis presented in this article. |
Mendez, Gipsi Lima; Faust, Karoline; Henry, Lynn N; Decelle, Johan; Colin, Simon; Carcillo, Fabrizio; Chaffron, Samuel; Ignacio-Espinosa, Cesar JC; Roux, Simon; Vincent, Flora; Bittner, Lucie; Darzi, Youssef; Wang, Jun; Audic, Stéphane; Berline, Léo; Bontempi, Gianluca; Cabello, Ana AM; Coppola, Laurent; Cornejo-Castillo, Francisco FM; d'Ovidio, Francesco; Meester, Luc De; Ferrera, Isabel; Garet-Delmas, Marie-José; Guidi, Lionel; Lara, Elena; Pesant, Stéphane; Royo-Llonch, Marta; Salazar, Guillem; Sanchez, Paloma; Sebastian, Marta; Souffreau, Caroline; Dimier, Céline; Picheral, Marc; Searson, Sarah; Kandels-Lewis, Stefanie; coordinators, Tara Oceans; Gorsky, Gabriel; Not, Fabrice; Ogata, Hiroyuki; Speich, Sabrina; Stemmann, Lars; Weissenbach, Jean; Wincker, Patrick; Acinas, Silvia SG; Sunagawa, Shinichi; Bork, Peer; Sullivan, Matthew B; Karsenti, Eric; Bowler, Chris; de Vargas, Colomban; Raes, Jeroen JR Ocean plankton. Determinants of community structure in the global plankton interactome. Journal Article In: Science, 348 (6237), pp. 1262073, 2015, (DOI: 10.1126/science.1262073). @article{info:hdl:2013/200950, title = {Ocean plankton. Determinants of community structure in the global plankton interactome.}, author = {Gipsi Lima Mendez and Karoline Faust and Lynn N Henry and Johan Decelle and Simon Colin and Fabrizio Carcillo and Samuel Chaffron and Cesar JC Ignacio-Espinosa and Simon Roux and Flora Vincent and Lucie Bittner and Youssef Darzi and Jun Wang and Stéphane Audic and Léo Berline and Gianluca Bontempi and Ana AM Cabello and Laurent Coppola and Francisco FM Cornejo-Castillo and Francesco d'Ovidio and Luc De Meester and Isabel Ferrera and Marie-José Garet-Delmas and Lionel Guidi and Elena Lara and Stéphane Pesant and Marta Royo-Llonch and Guillem Salazar and Paloma Sanchez and Marta Sebastian and Caroline Souffreau and Céline Dimier and Marc Picheral and Sarah Searson and Stefanie Kandels-Lewis and Tara Oceans coordinators and Gabriel Gorsky and Fabrice Not and Hiroyuki Ogata and Sabrina Speich and Lars Stemmann and Jean Weissenbach and Patrick Wincker and Silvia SG Acinas and Shinichi Sunagawa and Peer Bork and Matthew B Sullivan and Eric Karsenti and Chris Bowler and Colomban de Vargas and Jeroen JR Raes}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/200950}, year = {2015}, date = {2015-01-01}, journal = {Science}, volume = {348}, number = {6237}, pages = {1262073}, abstract = {Species interaction networks are shaped by abiotic and biotic factors. Here, as part of the Tara Oceans project, we studied the photic zone interactome using environmental factors and organismal abundance profiles and found that environmental factors are incomplete predictors of community structure. We found associations across plankton functional types and phylogenetic groups to be nonrandomly distributed on the network and driven by both local and global patterns. We identified interactions among grazers, primary producers, viruses, and (mainly parasitic) symbionts and validated network-generated hypotheses using microscopy to confirm symbiotic relationships. We have thus provided a resource to support further research on ocean food webs and integrating biological components into ocean models.}, note = {DOI: 10.1126/science.1262073}, keywords = {}, pubstate = {published}, tppubtype = {article} } Species interaction networks are shaped by abiotic and biotic factors. Here, as part of the Tara Oceans project, we studied the photic zone interactome using environmental factors and organismal abundance profiles and found that environmental factors are incomplete predictors of community structure. We found associations across plankton functional types and phylogenetic groups to be nonrandomly distributed on the network and driven by both local and global patterns. We identified interactions among grazers, primary producers, viruses, and (mainly parasitic) symbionts and validated network-generated hypotheses using microscopy to confirm symbiotic relationships. We have thus provided a resource to support further research on ocean food webs and integrating biological components into ocean models. |
Colaprico, Antonio; Cava, Claudia; Bertoli, Gloria; Bontempi, Gianluca; Castiglioni, Isabella Integrative Analysis with Monte Carlo Cross-Validation Reveals miRNAs Regulating Pathways Cross-Talk in Aggressive Breast Cancer Journal Article In: BioMed Research International, 2015 , 2015, (DOI: 10.1155/2015/831314). @article{info:hdl:2013/217546, title = {Integrative Analysis with Monte Carlo Cross-Validation Reveals miRNAs Regulating Pathways Cross-Talk in Aggressive Breast Cancer}, author = {Antonio Colaprico and Claudia Cava and Gloria Bertoli and Gianluca Bontempi and Isabella Castiglioni}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/217546}, year = {2015}, date = {2015-01-01}, journal = {BioMed Research International}, volume = {2015}, abstract = {In this work an integrated approach was used to identify functional miRNAs regulating gene pathway cross-talk in breast cancer (BC). We first integrated gene expression profiles and biological pathway information to explore the underlying associations between genes differently expressed among normal and BC samples and pathways enriched from these genes. For each pair of pathways, a score was derived from the distribution of gene expression levels by quantifying their pathway cross-talk. Random forest classification allowed the identification of pairs of pathways with high cross-talk. We assessed miRNAs regulating the identified gene pathways by a mutual information analysis. A Fisher test was applied to demonstrate their significance in the regulated pathways. Our results suggest interesting networks of pathways that could be key regulatory of target genes in BC, including stem cell pluripotency, coagulation, and hypoxia pathways and miRNAs that control these networks could be potential biomarkers for diagnostic, prognostic, and therapeutic development in BC. This work shows that standard methods of predicting normal and tumor classes such as differentially expressed miRNAs or transcription factors could lose intrinsic features; instead our approach revealed the responsible molecules of the disease.}, note = {DOI: 10.1155/2015/831314}, keywords = {}, pubstate = {published}, tppubtype = {article} } In this work an integrated approach was used to identify functional miRNAs regulating gene pathway cross-talk in breast cancer (BC). We first integrated gene expression profiles and biological pathway information to explore the underlying associations between genes differently expressed among normal and BC samples and pathways enriched from these genes. For each pair of pathways, a score was derived from the distribution of gene expression levels by quantifying their pathway cross-talk. Random forest classification allowed the identification of pairs of pathways with high cross-talk. We assessed miRNAs regulating the identified gene pathways by a mutual information analysis. A Fisher test was applied to demonstrate their significance in the regulated pathways. Our results suggest interesting networks of pathways that could be key regulatory of target genes in BC, including stem cell pluripotency, coagulation, and hypoxia pathways and miRNAs that control these networks could be potential biomarkers for diagnostic, prognostic, and therapeutic development in BC. This work shows that standard methods of predicting normal and tumor classes such as differentially expressed miRNAs or transcription factors could lose intrinsic features; instead our approach revealed the responsible molecules of the disease. |
Bontempi, Gianluca; Flauder, Maxime From dependency to causality: a machine learning approach Journal Article In: Journal of machine learning research, 2015, (Language of publication: en). @article{info:hdl:2013/222900, title = {From dependency to causality: a machine learning approach}, author = {Gianluca Bontempi and Maxime Flauder}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/222900}, year = {2015}, date = {2015-01-01}, journal = {Journal of machine learning research}, abstract = {The relationship between statistical dependency and causality lies at the heart of all statistical approaches to causal inference. Recent results in the ChaLearn cause-effect pair challenge have shown that causal directionality can be inferred with good accuracy also in Markov indistinguishable configurations thanks to data driven approaches. This paper proposes a supervised machine learning approach to infer the existence of a directed causal link between two variables in multivariate settings with n > 2 variables. The approach relies on the asymmetry of some conditional (in)dependence relations between the members of the Markov blankets of two variables causally connected. Our results show that supervised learning methods may be successfully used to extract causal information on the basis of asymmetric statistical descriptors also for n > 2 variate distributions.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } The relationship between statistical dependency and causality lies at the heart of all statistical approaches to causal inference. Recent results in the ChaLearn cause-effect pair challenge have shown that causal directionality can be inferred with good accuracy also in Markov indistinguishable configurations thanks to data driven approaches. This paper proposes a supervised machine learning approach to infer the existence of a directed causal link between two variables in multivariate settings with n > 2 variables. The approach relies on the asymmetry of some conditional (in)dependence relations between the members of the Markov blankets of two variables causally connected. Our results show that supervised learning methods may be successfully used to extract causal information on the basis of asymmetric statistical descriptors also for n > 2 variate distributions. |
Lerman, Liran; Poussier, Romain; Bontempi, Gianluca; Markowitch, Olivier; c c, Fran Template attacks vs. Machine learning revisited (and the curse of dimensionality in side-channel analysis) Journal Article In: Lecture notes in computer science, 9064 , pp. 20-33, 2015, (DOI: 10.1007/978-3-319-21476-4_2). @article{info:hdl:2013/226800, title = {Template attacks vs. Machine learning revisited (and the curse of dimensionality in side-channel analysis)}, author = {Liran Lerman and Romain Poussier and Gianluca Bontempi and Olivier Markowitch and Fran{c c}ois-Xavier Standaert}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/226800}, year = {2015}, date = {2015-01-01}, journal = {Lecture notes in computer science}, volume = {9064}, pages = {20-33}, abstract = {Template attacks and machine learning are two popular approaches to profiled side-channel analysis. In this paper, we aim to contribute to the understanding of their respective strengths and weaknesses, with a particular focus on their curse of dimensionality. For this purpose, we take advantage of a well-controlled simulated experimental setting in order to put forward two important intuitions. First and from a theoretical point of view, the data complexity of template attacks is not sensitive to the dimension increase in side-channel traces given that their profiling is perfect. Second and from a practical point of view, concrete attacks are always affected by (estimation and assumption) errors during profiling. As these errors increase, machine learning gains interest compared to template attacks, especially when based on random forests.}, note = {DOI: 10.1007/978-3-319-21476-4_2}, keywords = {}, pubstate = {published}, tppubtype = {article} } Template attacks and machine learning are two popular approaches to profiled side-channel analysis. In this paper, we aim to contribute to the understanding of their respective strengths and weaknesses, with a particular focus on their curse of dimensionality. For this purpose, we take advantage of a well-controlled simulated experimental setting in order to put forward two important intuitions. First and from a theoretical point of view, the data complexity of template attacks is not sensitive to the dimension increase in side-channel traces given that their profiling is perfect. Second and from a practical point of view, concrete attacks are always affected by (estimation and assumption) errors during profiling. As these errors increase, machine learning gains interest compared to template attacks, especially when based on random forests. |
Pozzolo, Andrea Dal; Caelen, Olivier; Bontempi, Gianluca When is undersampling effective in unbalanced classification tasks? Journal Article In: Lecture notes in computer science, 9284 , pp. 200-215, 2015, (DOI: 10.1007/978-3-319-23528-8_13). @article{info:hdl:2013/237086, title = {When is undersampling effective in unbalanced classification tasks?}, author = {Andrea Dal Pozzolo and Olivier Caelen and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/237086}, year = {2015}, date = {2015-01-01}, journal = {Lecture notes in computer science}, volume = {9284}, pages = {200-215}, abstract = {A well-known rule of thumb in unbalanced classification recommends the rebalancing (typically by resampling) of the classes before proceeding with the learning of the classifier. Though this seems to work for the majority of cases, no detailed analysis exists about the impact of undersampling on the accuracy of the final classifier. This paper aims to fill this gap by proposing an integrated analysis of the two elements which have the largest impact on the effectiveness of an undersampling strategy: the increase of the variance due to the reduction of the number of samples and the warping of the posterior distribution due to the change of priori probabilities. In particular we will propose a theoretical analysis specifying under which conditions undersampling is recommended and expected to be effective. It emerges that the impact of undersampling depends on the number of samples, the variance of the classifier, the degree of imbalance and more specifically on the value of the posterior probability. This makes difficult to predict the average effectiveness of an undersampling strategy since its benefits depend on the distribution of the testing points. Results from several synthetic and real-world unbalanced datasets support and validate our findings.}, note = {DOI: 10.1007/978-3-319-23528-8_13}, keywords = {}, pubstate = {published}, tppubtype = {article} } A well-known rule of thumb in unbalanced classification recommends the rebalancing (typically by resampling) of the classes before proceeding with the learning of the classifier. Though this seems to work for the majority of cases, no detailed analysis exists about the impact of undersampling on the accuracy of the final classifier. This paper aims to fill this gap by proposing an integrated analysis of the two elements which have the largest impact on the effectiveness of an undersampling strategy: the increase of the variance due to the reduction of the number of samples and the warping of the posterior distribution due to the change of priori probabilities. In particular we will propose a theoretical analysis specifying under which conditions undersampling is recommended and expected to be effective. It emerges that the impact of undersampling depends on the number of samples, the variance of the classifier, the degree of imbalance and more specifically on the value of the posterior probability. This makes difficult to predict the average effectiveness of an undersampling strategy since its benefits depend on the distribution of the testing points. Results from several synthetic and real-world unbalanced datasets support and validate our findings. |
Cuellar, M P M P; Ros, Maria; Bautista, Maria Martin J; "e, Yann-A; Bontempi, Gianluca An approach for the evaluation of human activities in physical therapy scenarios Journal Article In: Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 141 , pp. 401-414, 2015, (DOI: 10.1007/978-3-319-16292-8_29). @article{info:hdl:2013/198531, title = {An approach for the evaluation of human activities in physical therapy scenarios}, author = {M P M P Cuellar and Maria Ros and Maria Martin J Bautista and Yann-A{"e}l Le Borgne and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/198531}, year = {2015}, date = {2015-01-01}, journal = {Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering}, volume = {141}, pages = {401-414}, abstract = {Human activity recognition has been widely studied since the last decade in ambient intelligence scenarios. Remarkable progresses have been made in this domain, especially in research lines such as ambient assisted living, gesture recognition, behaviour detection and classification, etc. Most of the works in the literature focus on activity classification or recognition, prediction of future events, or anomaly detection and prevention. However, it is hard to find approaches that do not only recognize an activity, but also provide an evaluation of its performance according to an optimality criterion. This problem is of special interest in applications such as sports performance evaluation, physical therapy, etc. In this work, we address the problem of the evaluation of such human activities in monitored environments using depth sensors. In particular, we propose a system able to provide an automatic evaluation of the correctness in the performance of activities involving motion, and more specifically, diagnosis exercises in physical therapy.}, note = {DOI: 10.1007/978-3-319-16292-8_29}, keywords = {}, pubstate = {published}, tppubtype = {article} } Human activity recognition has been widely studied since the last decade in ambient intelligence scenarios. Remarkable progresses have been made in this domain, especially in research lines such as ambient assisted living, gesture recognition, behaviour detection and classification, etc. Most of the works in the literature focus on activity classification or recognition, prediction of future events, or anomaly detection and prevention. However, it is hard to find approaches that do not only recognize an activity, but also provide an evaluation of its performance according to an optimality criterion. This problem is of special interest in applications such as sports performance evaluation, physical therapy, etc. In this work, we address the problem of the evaluation of such human activities in monitored environments using depth sensors. In particular, we propose a system able to provide an automatic evaluation of the correctness in the performance of activities involving motion, and more specifically, diagnosis exercises in physical therapy. |
Delatte, Benjamin; Jeschke, Jana; Defrance, Matthieu; Bachman, Martin; Creppe, Catherine; Calonne, Emilie; Bizet, Martin; Deplus, Rachel; 'i, Laura Marroqu; Libin, Myriam; Ravichandran, Mirunalini; c c, Fran; Eizirik, Decio L; Murrell, Adele; Jurkowski, Tomasz Piotr; c c, Fran Genome-wide hydroxymethylcytosine pattern changes in response to oxidative stress. Journal Article In: Scientific reports, 5 , pp. 12714, 2015, (DOI: 10.1038/srep12714). @article{info:hdl:2013/265293, title = {Genome-wide hydroxymethylcytosine pattern changes in response to oxidative stress.}, author = {Benjamin Delatte and Jana Jeschke and Matthieu Defrance and Martin Bachman and Catherine Creppe and Emilie Calonne and Martin Bizet and Rachel Deplus and Laura Marroqu{'i} and Myriam Libin and Mirunalini Ravichandran and Fran{c c}oise Mascart and Decio L Eizirik and Adele Murrell and Tomasz Piotr Jurkowski and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/265293/4/doi_248920.pdf}, year = {2015}, date = {2015-01-01}, journal = {Scientific reports}, volume = {5}, pages = {12714}, abstract = {The TET enzymes convert methylcytosine to the newly discovered base hydroxymethylcytosine. While recent reports suggest that TETs may play a role in response to oxidative stress, this role remains uncertain, and results lack in vivo models. Here we show a global decrease of hydroxymethylcytosine in cells treated with buthionine sulfoximine, and in mice depleted for the major antioxidant enzymes GPx1 and 2. Furthermore, genome-wide profiling revealed differentially hydroxymethylated regions in coding genes, and intriguingly in microRNA genes, both involved in response to oxidative stress. These results thus suggest a profound effect of in vivo oxidative stress on the global hydroxymethylome.}, note = {DOI: 10.1038/srep12714}, keywords = {}, pubstate = {published}, tppubtype = {article} } The TET enzymes convert methylcytosine to the newly discovered base hydroxymethylcytosine. While recent reports suggest that TETs may play a role in response to oxidative stress, this role remains uncertain, and results lack in vivo models. Here we show a global decrease of hydroxymethylcytosine in cells treated with buthionine sulfoximine, and in mice depleted for the major antioxidant enzymes GPx1 and 2. Furthermore, genome-wide profiling revealed differentially hydroxymethylated regions in coding genes, and intriguingly in microRNA genes, both involved in response to oxidative stress. These results thus suggest a profound effect of in vivo oxidative stress on the global hydroxymethylome. |
Larsimont, Jean-Christophe; Kass, Youssef Khalil; Danes, Adriana Sanchez; Sukumaran, Vijayakumar; Defrance, Matthieu; Delatte, Benjamin; Liagre, Mélanie; Baatsen, Pieter; Marine, Jean-Christophe; Lippens, Saskia; Guerin, Christopher; Marmol, Véronique Del; Vanderwinden, Jean-Marie; c c, Fran; Blanpain, Cédric Sox9 Controls Self-Renewal of Oncogene Targeted Cells and Links Tumor Initiation and Invasion. Journal Article In: Cell stem cell, 17 (1), pp. 60-73, 2015, (DOI: 10.1016/j.stem.2015.05.008). @article{info:hdl:2013/262159, title = {Sox9 Controls Self-Renewal of Oncogene Targeted Cells and Links Tumor Initiation and Invasion.}, author = {Jean-Christophe Larsimont and Youssef Khalil Kass and Adriana Sanchez Danes and Vijayakumar Sukumaran and Matthieu Defrance and Benjamin Delatte and Mélanie Liagre and Pieter Baatsen and Jean-Christophe Marine and Saskia Lippens and Christopher Guerin and Véronique Del Marmol and Jean-Marie Vanderwinden and Fran{c c}ois Fuks and Cédric Blanpain}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/262159/1/Elsevier_245786.pdf}, year = {2015}, date = {2015-01-01}, journal = {Cell stem cell}, volume = {17}, number = {1}, pages = {60-73}, abstract = {Sox9 is a transcription factor expressed in most solid tumors. However, the molecular mechanisms underlying Sox9 function during tumorigenesis remain unclear. Here, using a genetic mouse model of basal cell carcinoma (BCC), the most frequent cancer in humans, we show that Sox9 is expressed from the earliest step of tumor formation in a Wnt/β-catenin-dependent manner. Deletion of Sox9 together with the constitutive activation of Hedgehog signaling completely prevents BCC formation and leads to a progressive loss of oncogene-expressing cells. Transcriptional profiling of oncogene-expressing cells with Sox9 deletion, combined with in vivo ChIP sequencing, uncovers a cancer-specific gene network regulated by Sox9 that promotes stemness, extracellular matrix deposition, and cytoskeleton remodeling while repressing epidermal differentiation. Our study identifies the molecular mechanisms regulated by Sox9 that link tumor initiation and invasion.}, note = {DOI: 10.1016/j.stem.2015.05.008}, keywords = {}, pubstate = {published}, tppubtype = {article} } Sox9 is a transcription factor expressed in most solid tumors. However, the molecular mechanisms underlying Sox9 function during tumorigenesis remain unclear. Here, using a genetic mouse model of basal cell carcinoma (BCC), the most frequent cancer in humans, we show that Sox9 is expressed from the earliest step of tumor formation in a Wnt/β-catenin-dependent manner. Deletion of Sox9 together with the constitutive activation of Hedgehog signaling completely prevents BCC formation and leads to a progressive loss of oncogene-expressing cells. Transcriptional profiling of oncogene-expressing cells with Sox9 deletion, combined with in vivo ChIP sequencing, uncovers a cancer-specific gene network regulated by Sox9 that promotes stemness, extracellular matrix deposition, and cytoskeleton remodeling while repressing epidermal differentiation. Our study identifies the molecular mechanisms regulated by Sox9 that link tumor initiation and invasion. |
Medina-Rivera, Alejandra; Defrance, Matthieu; Sand, Olivier; Herrmann, Carl; Castro-Mondragon, Jaime Abraham; Delerce, Jeremy; Jaeger, Sébastien; Blanchet, Christophe; Vincens, Pierre; Caron, Christophe; Staines, Daniel Michael Ichael D M; Contreras-Moreira, Bruno; Artufel, Marie; Charbonnier-Khamvongsa, Lucie; Hernandez, Céline; Thieffry, Denis; Thomas-Chollier, Morgane; van Helden, Jacques RSAT 2015: Regulatory sequence analysis tools Journal Article In: Nucleic acids research, 43 (W1), pp. W50-W56, 2015, (DOI: 10.1093/nar/gkv362). @article{info:hdl:2013/237115, title = {RSAT 2015: Regulatory sequence analysis tools}, author = {Alejandra Medina-Rivera and Matthieu Defrance and Olivier Sand and Carl Herrmann and Jaime Abraham Castro-Mondragon and Jeremy Delerce and Sébastien Jaeger and Christophe Blanchet and Pierre Vincens and Christophe Caron and Daniel Michael Ichael D M Staines and Bruno Contreras-Moreira and Marie Artufel and Lucie Charbonnier-Khamvongsa and Céline Hernandez and Denis Thieffry and Morgane Thomas-Chollier and Jacques van Helden}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/237115}, year = {2015}, date = {2015-01-01}, journal = {Nucleic acids research}, volume = {43}, number = {W1}, pages = {W50-W56}, abstract = {RSAT (Regulatory Sequence Analysis Tools) is a modular software suite for the analysis of cisregulatory elements in genome sequences. Its main applications are (i) motif discovery, appropriate to genome-wide data sets like ChIP-seq, (ii) transcription factor binding motif analysis (quality assessment, comparisons and clustering), (iii) comparative genomics and (iv) analysis of regulatory variations. Nine new programs have been added to the 43 described in the 2011 NAR Web Software Issue, including a tool to extract sequences from a list of coordinates (fetch-sequences from UCSC), novel programs dedicated to the analysis of regulatory variants from GWAS or population genomics (retrieve-variationseq and variation-scan), a program to cluster motifs and visualize the similarities as trees (matrixclustering). To deal with the drastic increase of sequenced genomes, RSAT public sites have been reorganized into taxon-specific servers. The suite is well-documented with tutorials and published protocols. The software suite is available through Web sites, SOAP/WSDL Web services, virtual machines and stand-alone programs at http://www.rsat.eu/.}, note = {DOI: 10.1093/nar/gkv362}, keywords = {}, pubstate = {published}, tppubtype = {article} } RSAT (Regulatory Sequence Analysis Tools) is a modular software suite for the analysis of cisregulatory elements in genome sequences. Its main applications are (i) motif discovery, appropriate to genome-wide data sets like ChIP-seq, (ii) transcription factor binding motif analysis (quality assessment, comparisons and clustering), (iii) comparative genomics and (iv) analysis of regulatory variations. Nine new programs have been added to the 43 described in the 2011 NAR Web Software Issue, including a tool to extract sequences from a list of coordinates (fetch-sequences from UCSC), novel programs dedicated to the analysis of regulatory variants from GWAS or population genomics (retrieve-variationseq and variation-scan), a program to cluster motifs and visualize the similarities as trees (matrixclustering). To deal with the drastic increase of sequenced genomes, RSAT public sites have been reorganized into taxon-specific servers. The suite is well-documented with tutorials and published protocols. The software suite is available through Web sites, SOAP/WSDL Web services, virtual machines and stand-alone programs at http://www.rsat.eu/. |
Uribe-Lewis, Santiago; Stark, Rory; Carroll, Thomas; Dunning, Mark J; Bachman, Martin; Ito, Yoko; Stojic, Lovorka; Halim, Silvia; Vowler, Sarah L; Lynch, Andy G; Delatte, Benjamin; de Bony, Eric James; Colin, Laurence; Defrance, Matthieu; Krueger, Felix; Silva, Ana Luisa; ten Hoopen, Rogier; Ibrahim, Ashraf Ek; Murrell, Adele; c c, Fran 5-hydroxymethylcytosine marks promoters in colon that resist DNA hypermethylation in cancer. Journal Article In: Genome biology, 16 , pp. 69, 2015, (DOI: 10.1186/s13059-015-0605-5). @article{info:hdl:2013/262160, title = {5-hydroxymethylcytosine marks promoters in colon that resist DNA hypermethylation in cancer.}, author = {Santiago Uribe-Lewis and Rory Stark and Thomas Carroll and Mark J Dunning and Martin Bachman and Yoko Ito and Lovorka Stojic and Silvia Halim and Sarah L Vowler and Andy G Lynch and Benjamin Delatte and Eric James de Bony and Laurence Colin and Matthieu Defrance and Felix Krueger and Ana Luisa Silva and Rogier ten Hoopen and Ashraf Ek Ibrahim and Adele Murrell and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/262160/4/doi_245787.pdf}, year = {2015}, date = {2015-01-01}, journal = {Genome biology}, volume = {16}, pages = {69}, abstract = {The discovery of cytosine hydroxymethylation (5hmC) as a mechanism that potentially controls DNA methylation changes typical of neoplasia prompted us to investigate its behaviour in colon cancer. 5hmC is globally reduced in proliferating cells such as colon tumours and the gut crypt progenitors, from which tumours can arise.}, note = {DOI: 10.1186/s13059-015-0605-5}, keywords = {}, pubstate = {published}, tppubtype = {article} } The discovery of cytosine hydroxymethylation (5hmC) as a mechanism that potentially controls DNA methylation changes typical of neoplasia prompted us to investigate its behaviour in colon cancer. 5hmC is globally reduced in proliferating cells such as colon tumours and the gut crypt progenitors, from which tumours can arise. |
c c, Fran; Jeschke, Jana; Defrance, Matthieu; Desmedt, Christine; Bizet, Martin; Sotiriou, Christos BREAST CANCER EPIGENETIC MARKERS USEFUL IN ANTHRACYCLINE TREATMENT PROGNOSIS Miscellaneous 2015, (Language of publication: fr). @misc{info:hdl:2013/272725, title = {BREAST CANCER EPIGENETIC MARKERS USEFUL IN ANTHRACYCLINE TREATMENT PROGNOSIS}, author = {Fran{c c}ois Fuks and Jana Jeschke and Matthieu Defrance and Christine Desmedt and Martin Bizet and Christos Sotiriou}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/272725}, year = {2015}, date = {2015-01-01}, note = {Language of publication: fr}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
2014 |
Gagliolo, Matteo; Lenaerts, Tom; Jacobs, Dirk Politics Matters: Dynamics of Inter-organizational Networks among Immigrant Associations Journal Article In: Studies in Computational Intelligence, 549 , pp. 47-55, 2014, (DOI: 10.1007/978-3-319-05401-8_5). @article{info:hdl:2013/264842, title = {Politics Matters: Dynamics of Inter-organizational Networks among Immigrant Associations}, author = {Matteo Gagliolo and Tom Lenaerts and Dirk Jacobs}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/264842/3/Gagliolo2014CompleNet.pdf}, year = {2014}, date = {2014-01-01}, journal = {Studies in Computational Intelligence}, volume = {549}, pages = {47-55}, abstract = {We model the dynamics of the two-mode network among directors and boards of voluntary associations, using a stochastic actor-based model, SIENA [12], including the structural effects proposed in [6], and considering the political orientation of associations as a covariate. Using data from [14], we compare the evolution of interlocks among Turkish associations in two European capitals, and explain the noticeable difference in structure by looking at statistically significant differences among the estimated effects.}, note = {DOI: 10.1007/978-3-319-05401-8_5}, keywords = {}, pubstate = {published}, tppubtype = {article} } We model the dynamics of the two-mode network among directors and boards of voluntary associations, using a stochastic actor-based model, SIENA [12], including the structural effects proposed in [6], and considering the political orientation of associations as a covariate. Using data from [14], we compare the evolution of interlocks among Turkish associations in two European capitals, and explain the noticeable difference in structure by looking at statistically significant differences among the estimated effects. |
Pozzolo, Andrea Dal; Johnson, Reid; Caelen, Olivier; Waterschoot, Serge; Chawla, Nitesh V; Bontempi, Gianluca Using HDDT to avoid instances propagation in unbalanced and evolving data streams Inproceedings In: Neural Networks (IJCNN), 2014 International Joint Conference on, pp. 588-594, 2014, (DOI: 10.1109/IJCNN.2014.6889638). @inproceedings{info:hdl:2013/221667, title = {Using HDDT to avoid instances propagation in unbalanced and evolving data streams}, author = {Andrea Dal Pozzolo and Reid Johnson and Olivier Caelen and Serge Waterschoot and Nitesh V Chawla and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/221667}, year = {2014}, date = {2014-01-01}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {588-594}, abstract = {Hellinger Distance Decision Trees [10] (HDDT) has been previously used for static datasets with skewed distributions. In unbalanced data streams, state-of-the-art techniques use instance propagation and standard decision trees (e.g. C4.5 [27]) to cope with the unbalanced problem. However it is not always possible to revisit/store old instances of a stream. In this paper we show how HDDT can be successfully applied in unbalanced and evolving stream data. Using HDDT allows us to remove instance propagations between batches with several benefits: i) improved predictive accuracy ii) speed iii) single-pass through the data. We use a Hellinger weighted ensemble of HDDTs to combat concept drift and increase accuracy of single classifiers. We test our framework on several streaming datasets with unbalanced classes and concept drift.}, note = {DOI: 10.1109/IJCNN.2014.6889638}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Hellinger Distance Decision Trees [10] (HDDT) has been previously used for static datasets with skewed distributions. In unbalanced data streams, state-of-the-art techniques use instance propagation and standard decision trees (e.g. C4.5 [27]) to cope with the unbalanced problem. However it is not always possible to revisit/store old instances of a stream. In this paper we show how HDDT can be successfully applied in unbalanced and evolving stream data. Using HDDT allows us to remove instance propagations between batches with several benefits: i) improved predictive accuracy ii) speed iii) single-pass through the data. We use a Hellinger weighted ensemble of HDDTs to combat concept drift and increase accuracy of single classifiers. We test our framework on several streaming datasets with unbalanced classes and concept drift. |
Lenaerts, Tom; Giacobini, Mario; Bersini, Hugues; Bourgine, Paul; Dorigo, Marco; Doursat, René Special issue for the 20th anniversary of the European conference on artificial life (ECAL 2011): Editorial Journal Article In: Artificial life, 20 (1), pp. 1-3, 2014, (DOI: 10.1162/ARTL-a-00093). @article{info:hdl:2013/204002, title = {Special issue for the 20th anniversary of the European conference on artificial life (ECAL 2011): Editorial}, author = {Tom Lenaerts and Mario Giacobini and Hugues Bersini and Paul Bourgine and Marco Dorigo and René Doursat}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/204002}, year = {2014}, date = {2014-01-01}, journal = {Artificial life}, volume = {20}, number = {1}, pages = {1-3}, note = {DOI: 10.1162/ARTL-a-00093}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Cilia, Elisa; Pancsa, Rita; Tompa, Peter; Lenaerts, Tom; Vranken, Wim The DynaMine webserver: predicting protein dynamics from sequence. Journal Article In: Nucleic acids research, 42 , pp. W264-W270, 2014, (DOI: 10.1093/nar/gku270). @article{info:hdl:2013/186420, title = {The DynaMine webserver: predicting protein dynamics from sequence.}, author = {Elisa Cilia and Rita Pancsa and Peter Tompa and Tom Lenaerts and Wim Vranken}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/186420/4/PMC4086073.pdf}, year = {2014}, date = {2014-01-01}, journal = {Nucleic acids research}, volume = {42}, pages = {W264-W270}, abstract = {Protein dynamics are important for understanding protein function. Unfortunately, accurate protein dynamics information is difficult to obtain: here we present the DynaMine webserver, which provides predictions for the fast backbone movements of proteins directly from their amino-acid sequence. DynaMine rapidly produces a profile describing the statistical potential for such movements at residue-level resolution. The predicted values have meaning on an absolute scale and go beyond the traditional binary classification of residues as ordered or disordered, thus allowing for direct dynamics comparisons between protein regions. Through this webserver, we provide molecular biologists with an efficient and easy to use tool for predicting the dynamical characteristics of any protein of interest, even in the absence of experimental observations. The prediction results are visualized and can be directly downloaded. The DynaMine webserver, including instructive examples describing the meaning of the profiles, is available at http://dynamine.ibsquare.be.}, note = {DOI: 10.1093/nar/gku270}, keywords = {}, pubstate = {published}, tppubtype = {article} } Protein dynamics are important for understanding protein function. Unfortunately, accurate protein dynamics information is difficult to obtain: here we present the DynaMine webserver, which provides predictions for the fast backbone movements of proteins directly from their amino-acid sequence. DynaMine rapidly produces a profile describing the statistical potential for such movements at residue-level resolution. The predicted values have meaning on an absolute scale and go beyond the traditional binary classification of residues as ordered or disordered, thus allowing for direct dynamics comparisons between protein regions. Through this webserver, we provide molecular biologists with an efficient and easy to use tool for predicting the dynamical characteristics of any protein of interest, even in the absence of experimental observations. The prediction results are visualized and can be directly downloaded. The DynaMine webserver, including instructive examples describing the meaning of the profiles, is available at http://dynamine.ibsquare.be. |
Cilia, Elisa; Teso, Stefano; Ammendola, Sergio; Lenaerts, Tom; Passerini, Andrea Predicting virus mutations through statistical relational learning. Journal Article In: BMC bioinformatics, 15 , pp. 309, 2014, (DOI: 10.1186/1471-2105-15-309). @article{info:hdl:2013/186411, title = {Predicting virus mutations through statistical relational learning.}, author = {Elisa Cilia and Stefano Teso and Sergio Ammendola and Tom Lenaerts and Andrea Passerini}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/186411/4/doi_170038.pdf}, year = {2014}, date = {2014-01-01}, journal = {BMC bioinformatics}, volume = {15}, pages = {309}, abstract = {Background: Viruses are typically characterized by high mutation rates, which allow them to quickly develop drug-resistant mutations. Mining relevant rules from mutation data can be extremely useful to understand the virus adaptation mechanism and to design drugs that effectively counter potentially resistant mutants.Results: We propose a simple statistical relational learning approach for mutant prediction where the input consists of mutation data with drug-resistance information, either as sets of mutations conferring resistance to a certain drug, or as sets of mutants with information on their susceptibility to the drug. The algorithm learns a set of relational rules characterizing drug-resistance and uses them to generate a set of potentially resistant mutants. Learning a weighted combination of rules allows to attach generated mutants with a resistance score as predicted by the statistical relational model and select only the highest scoring ones.Conclusions: Promising results were obtained in generating resistant mutations for both nucleoside and non-nucleoside HIV reverse transcriptase inhibitors. The approach can be generalized quite easily to learning mutants characterized by more complex rules correlating multiple mutations.}, note = {DOI: 10.1186/1471-2105-15-309}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Viruses are typically characterized by high mutation rates, which allow them to quickly develop drug-resistant mutations. Mining relevant rules from mutation data can be extremely useful to understand the virus adaptation mechanism and to design drugs that effectively counter potentially resistant mutants.Results: We propose a simple statistical relational learning approach for mutant prediction where the input consists of mutation data with drug-resistance information, either as sets of mutations conferring resistance to a certain drug, or as sets of mutants with information on their susceptibility to the drug. The algorithm learns a set of relational rules characterizing drug-resistance and uses them to generate a set of potentially resistant mutants. Learning a weighted combination of rules allows to attach generated mutants with a resistance score as predicted by the statistical relational model and select only the highest scoring ones.Conclusions: Promising results were obtained in generating resistant mutations for both nucleoside and non-nucleoside HIV reverse transcriptase inhibitors. The approach can be generalized quite easily to learning mutants characterized by more complex rules correlating multiple mutations. |
Rubio, Lucia; Huculeci, Radu; Buts, Lieven; Vanwetswinkel, Sophie; Lenaerts, Tom; van Nuland, Nico A J (1)H, (13)C, and (15)N backbone and side-chain chemical shift assignments of the free and bound forms of the human PTPN11 second SH2 domain. Journal Article In: Biomolecular N M R Assignments, 8 , 2014, (DOI: 10.1007/s12104-013-9504-4). @article{info:hdl:2013/155960, title = {(1)H, (13)C, and (15)N backbone and side-chain chemical shift assignments of the free and bound forms of the human PTPN11 second SH2 domain.}, author = {Lucia Rubio and Radu Huculeci and Lieven Buts and Sophie Vanwetswinkel and Tom Lenaerts and Nico A J van Nuland}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/155960}, year = {2014}, date = {2014-01-01}, journal = {Biomolecular N M R Assignments}, volume = {8}, abstract = {Src homology 2 (SH2) domains have an important role in the regulation of protein activity and intracellular signaling processes. They are geared to bind to specific phosphotyrosine (pY) motifs, with a substrate sequence specificity depending on the three amino acids immediately C-terminal to the pY. Here we report for the first time the (1)H, (15)N and (13)C backbone and side-chain chemical shift assignments for the C-terminal SH2 domain of the human protein tyrosine phosphatase PTPN11, both in its free and bound forms, where the ligand in the latter corresponds to a specific sequence of the human erythropoietin receptor.}, note = {DOI: 10.1007/s12104-013-9504-4}, keywords = {}, pubstate = {published}, tppubtype = {article} } Src homology 2 (SH2) domains have an important role in the regulation of protein activity and intracellular signaling processes. They are geared to bind to specific phosphotyrosine (pY) motifs, with a substrate sequence specificity depending on the three amino acids immediately C-terminal to the pY. Here we report for the first time the (1)H, (15)N and (13)C backbone and side-chain chemical shift assignments for the C-terminal SH2 domain of the human protein tyrosine phosphatase PTPN11, both in its free and bound forms, where the ligand in the latter corresponds to a specific sequence of the human erythropoietin receptor. |
Reggiani, Claudio; "e, Yann-A; Pozzolo, Andrea Dal; Olsen, Catharina; Bontempi, Gianluca Minimum Redundancy Maximum Relevance: MapReduce implementation using Apache Hadoop Miscellaneous 2014, (Conference: Benelearn 2014). @misc{info:hdl:2013/184925, title = {Minimum Redundancy Maximum Relevance: MapReduce implementation using Apache Hadoop}, author = {Claudio Reggiani and Yann-A{"e}l Le Borgne and Andrea Dal Pozzolo and Catharina Olsen and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/184925}, year = {2014}, date = {2014-01-01}, note = {Conference: Benelearn 2014}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Meyer, Patrick E; Bontempi, Gianluca Information-theoretic gene selection in expression data Book Chapter In: pp. 399-419, wiley, 2014, (DOI: 10.1002/9781118617151.ch17). @inbook{info:hdl:2013/321214, title = {Information-theoretic gene selection in expression data}, author = {Patrick E Meyer and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/321214}, year = {2014}, date = {2014-01-01}, pages = {399-419}, publisher = {wiley}, abstract = {This chapter introduces the curse of dimensionality, and focuses on widely used variable exploration strategies. The chapter also introduces the information-theoretic framework and recalls variable selection techniques which have been proposed in the literature. It discusses estimation techniques that can be used for implementing the selection strategies on the basis of observed data. The three sequential heuristic searches introduced, namely forward, backward, and bidirectional selection, share with the two mutual information estimators, the empirical and the Gaussian, a low computational cost coupled with a growing literature of good empirical results. Most of the selection criteria presented here use combinations of only bi- and trivariate probability distributions in order to reduce the effect of the curse of dimensionality. Finally, the chapter introduces the notions of relevance, redundancy, and synergy in order to explain and compare each method's ability to combine those bi- and trivariate distributions in an efficient setting.}, note = {DOI: 10.1002/9781118617151.ch17}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } This chapter introduces the curse of dimensionality, and focuses on widely used variable exploration strategies. The chapter also introduces the information-theoretic framework and recalls variable selection techniques which have been proposed in the literature. It discusses estimation techniques that can be used for implementing the selection strategies on the basis of observed data. The three sequential heuristic searches introduced, namely forward, backward, and bidirectional selection, share with the two mutual information estimators, the empirical and the Gaussian, a low computational cost coupled with a growing literature of good empirical results. Most of the selection criteria presented here use combinations of only bi- and trivariate probability distributions in order to reduce the effect of the curse of dimensionality. Finally, the chapter introduces the notions of relevance, redundancy, and synergy in order to explain and compare each method's ability to combine those bi- and trivariate distributions in an efficient setting. |
Taieb, Souhaib Ben Machine learning strategies for multi-step-ahead time series forecasting PhD Thesis 2014, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/209234, title = {Machine learning strategies for multi-step-ahead time series forecasting}, author = {Souhaib Ben Taieb}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/209234/4/2c5e8bfe-3eab-4c2a-acb0-843504ddfcbd.txt}, year = {2014}, date = {2014-01-01}, abstract = {How much electricity is going to be consumed for the next 24 hours? What will be the temperature for the next three days? What will be the number of sales of a certain product for the next few months? Answering these questions often requires forecasting several future observations from a given sequence of historical observations, called a time series. Historically, time series forecasting has been mainly studied in econometrics and statistics. In the last two decades, machine learning, a field that is concerned with the development of algorithms that can automatically learn from data, has become one of the most active areas of predictive modeling research. This success is largely due to the superior performance of machine learning prediction algorithms in many different applications as diverse as natural language processing, speech recognition and spam detection. However, there has been very little research at the intersection of time series forecasting and machine learning. The goal of this dissertation is to narrow this gap by addressing the problem of multi-step-ahead time series forecasting from the perspective of machine learning. To that end, we propose a series of forecasting strategies based on machine learning algorithms. Multi-step-ahead forecasts can be produced recursively by iterating a one-step-ahead model, or directly using a specific model for each horizon. As a first contribution, we conduct an in-depth study to compare recursive and direct forecasts generated with different learning algorithms for different data generating processes. More precisely, we decompose the multi-step mean squared forecast errors into the bias and variance components, and analyze their behavior over the forecast horizon for different time series lengths. The results and observations made in this study then guide us for the development of new forecasting strategies. In particular, we find that choosing between recursive and direct forecasts is not an easy task since it involves a trade-off between bias and estimation variance that depends on many interacting factors, including the learning model, the underlying data generating process, the time series length and the forecast horizon. As a second contribution, we develop multi-stage forecasting strategies that do not treat the recursive and direct strategies as competitors, but seek to combine their best properties. More precisely, the multi-stage strategies generate recursive linear forecasts, and then adjust these forecasts by modeling the multi-step forecast residuals with direct nonlinear models at each horizon, called rectification models. We propose a first multi-stage strategy, that we called the rectify strategy, which estimates the rectification models using the nearest neighbors model. However, because recursive linear forecasts often need small adjustments with real-world time series, we also consider a second multi-stage strategy, called the boost strategy, that estimates the rectification models using gradient boosting algorithms that use so-called weak learners. Generating multi-step forecasts using a different model at each horizon provides a large modeling flexibility. However, selecting these models independently can lead to irregularities in the forecasts that can contribute to increase the forecast variance. The problem is exacerbated with nonlinear machine learning models estimated from short time series. To address this issue, and as a third contribution, we introduce and analyze multi-horizon forecasting strategies that exploit the information contained in other horizons when learning the model for each horizon. In particular, to select the lag order and the hyperparameters of each model, multi-horizon strategies minimize forecast errors over multiple horizons rather than just the horizon of interest. We compare all the proposed strategies with both the recursive and direct strategies. We first apply a bias and variance study, then we evaluate the different strategies using real-world time series from two past forecasting competitions. For the rectify strategy, in addition to avoiding the choice between recursive and direct forecasts, the results demonstrate that it has better, or at least has close performance to, the best of the recursive and direct forecasts in different settings. For the multi-horizon strategies, the results emphasize the decrease in variance compared to single-horizon strategies, especially with linear or weakly nonlinear data generating processes. Overall, we found that the accuracy of multi-step-ahead forecasts based on machine learning algorithms can be significantly improved if an appropriate forecasting strategy is used to select the model parameters and to generate the forecasts. Lastly, as a fourth contribution, we have participated in the Load Forecasting track of the Global Energy Forecasting Competition 2012. The competition involved a hierarchical load forecasting problem where we were required to backcast and forecast hourly loads for a US utility with twenty geographical zones. Our team, TinTin, ranked fifth out of 105 participating teams, and we have been awarded an IEEE Power & Energy Society award. }, How much electricity is going to be consumed for the next 24 hours? What will be the temperature for the next three days? What will be the number of sales of a certain product for the next few months? Answering these questions often requires forecasting several future observations from a given sequence of historical observations, called a time series. <p><p>Historically, time series forecasting has been mainly studied in econometrics and statistics. In the last two decades, machine learning, a field that is concerned with the development of algorithms that can automatically learn from data, has become one of the most active areas of predictive modeling research. This success is largely due to the superior performance of machine learning prediction algorithms in many different applications as diverse as natural language processing, speech recognition and spam detection. However, there has been very little research at the intersection of time series forecasting and machine learning.<p><p>The goal of this dissertation is to narrow this gap by addressing the problem of multi-step-ahead time series forecasting from the perspective of machine learning. To that end, we propose a series of forecasting strategies based on machine learning algorithms.<p><p>Multi-step-ahead forecasts can be produced recursively by iterating a one-step-ahead model, or directly using a specific model for each horizon. As a first contribution, we conduct an in-depth study to compare recursive and direct forecasts generated with different learning algorithms for different data generating processes. More precisely, we decompose the multi-step mean squared forecast errors into the bias and variance components, and analyze their behavior over the forecast horizon for different time series lengths. The results and observations made in this study then guide us for the development of new forecasting strategies.<p><p>In particular, we find that choosing between recursive and direct forecasts is not an easy task since it involves a trade-off between bias and estimation variance that depends on many interacting factors, including the learning model, the underlying data generating process, the time series length and the forecast horizon. As a second contribution, we develop multi-stage forecasting strategies that do not treat the recursive and direct strategies as competitors, but seek to combine their best properties. More precisely, the multi-stage strategies generate recursive linear forecasts, and then adjust these forecasts by modeling the multi-step forecast residuals with direct nonlinear models at each horizon, called rectification models. We propose a first multi-stage strategy, that we called the rectify strategy, which estimates the rectification models using the nearest neighbors model. However, because recursive linear forecasts often need small adjustments with real-world time series, we also consider a second multi-stage strategy, called the boost strategy, that estimates the rectification models using gradient boosting algorithms that use so-called weak learners.<p><p>Generating multi-step forecasts using a different model at each horizon provides a large modeling flexibility. However, selecting these models independently can lead to irregularities in the forecasts that can contribute to increase the forecast variance. The problem is exacerbated with nonlinear machine learning models estimated from short time series. To address this issue, and as a third contribution, we introduce and analyze multi-horizon forecasting strategies that exploit the information contained in other horizons when learning the model for each horizon. In particular, to select the lag order and the hyperparameters of each model, multi-horizon strategies minimize forecast errors over multiple horizons rather than just the horizon of interest.<p><p>We compare all the proposed strategies with both the recursive and direct strategies. We first apply a bias and variance study, then we evaluate the different strategies using real-world time series from two past forecasting competitions. For the rectify strategy, in addition to avoiding the choice between recursive and direct forecasts, the results demonstrate that it has better, or at least has close performance to, the best of the recursive and direct forecasts in different settings. For the multi-horizon strategies, the results emphasize the decrease in variance compared to single-horizon strategies, especially with linear or weakly nonlinear data generating processes. Overall, we found that the accuracy of multi-step-ahead forecasts based on machine learning algorithms can be significantly improved if an appropriate forecasting strategy is used to select the model parameters and to generate the forecasts.<p><p>Lastly, as a fourth contribution, we have participated in the Load Forecasting track of the Global Energy Forecasting Competition 2012. The competition involved a hierarchical load forecasting problem where we were required to backcast and forecast hourly loads for a US utility with twenty geographical zones. Our team, TinTin, ranked fifth out of 105 participating teams, and we have been awarded an IEEE Power & Energy Society award.<p> |
Lerman, Liran; Medeiros, Stéphane Fernandes; Bontempi, Gianluca; Markowitch, Olivier A Machine Learning Approach Against a Masked AES Journal Article In: Lecture notes in computer science, 8419 , pp. 61-75, 2014, (Language of publication: en). @article{info:hdl:2013/223763, title = {A Machine Learning Approach Against a Masked AES}, author = {Liran Lerman and Stéphane Fernandes Medeiros and Gianluca Bontempi and Olivier Markowitch}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/223763}, year = {2014}, date = {2014-01-01}, journal = {Lecture notes in computer science}, volume = {8419}, pages = {61-75}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Trepo, Eric; Nahon, Pierre; Bontempi, Gianluca; Valenti, Luca; Falleti, Edmondo; Nischalke, Hans Dieter; Hamza, Samia; Corradini, Stefano Ginanni; Burza, Maria Antonella; Guyot, Erwan; Donati, Benedetta; Spengler, Ulrich; Hillon, Patrick; Toniutto, Pierluigi; Henrion, Jean; Franchimont, Denis; `e, Jacques Devi; Mathurin, Philippe; Moreno, Christophe; Romeo, Stefano; Deltenre, Pierre In: Hepatology, 59 (6), pp. 2170-2177, 2014, (DOI: 10.1002/hep.26767). @article{info:hdl:2013/196264, title = {Association between the PNPLA3 (rs738409 C>G) variant and hepatocellular carcinoma: Evidence from a meta-analysis of individual participant data.}, author = {Eric Trepo and Pierre Nahon and Gianluca Bontempi and Luca Valenti and Edmondo Falleti and Hans Dieter Nischalke and Samia Hamza and Stefano Ginanni Corradini and Maria Antonella Burza and Erwan Guyot and Benedetta Donati and Ulrich Spengler and Patrick Hillon and Pierluigi Toniutto and Jean Henrion and Denis Franchimont and Jacques Devi{`e}re and Philippe Mathurin and Christophe Moreno and Stefano Romeo and Pierre Deltenre}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/196264/3/196264.pdf}, year = {2014}, date = {2014-01-01}, journal = {Hepatology}, volume = {59}, number = {6}, pages = {2170-2177}, abstract = {The incidence of hepatocellular carcinoma (HCC) is increasing in Western countries. Although several clinical factors have been identified, many individuals never develop HCC, suggesting a genetic susceptibility. However, to date, only a few single-nucleotide polymorphisms have been reproducibly shown to be linked to HCC onset. A variant (rs738409 C>G, encoding for p.I148M) in the PNPLA3 gene is associated with liver damage in chronic liver diseases. Interestingly, several studies have reported that the minor rs738409[G] allele is more represented in HCC cases in chronic hepatitis C (CHC) and alcoholic liver disease (ALD). However, a significant association with HCC related to CHC has not been consistently observed, and the strength of the association between rs738409 and HCC remains unclear. We performed a meta-analysis of individual participant data including 2,503 European patients with cirrhosis to assess the association between rs738409 and HCC, particularly in ALD and CHC. We found that rs738409 was strongly associated with overall HCC (odds ratio [OR] per G allele, additive model=1.77; 95% confidence interval [CI]: 1.42-2.19; P=2.78 ?x 10(-7) ). This association was more pronounced in ALD (OR=2.20; 95% CI: 1.80-2.67; P=4.71 ?x 10(-15) ) than in CHC patients (OR=1.55; 95% CI: 1.03-2.34; P=3.52 ?x 10(-2) ). After adjustment for age, sex, and body mass index, the variant remained strongly associated with HCC.}, note = {DOI: 10.1002/hep.26767}, keywords = {}, pubstate = {published}, tppubtype = {article} } The incidence of hepatocellular carcinoma (HCC) is increasing in Western countries. Although several clinical factors have been identified, many individuals never develop HCC, suggesting a genetic susceptibility. However, to date, only a few single-nucleotide polymorphisms have been reproducibly shown to be linked to HCC onset. A variant (rs738409 C>G, encoding for p.I148M) in the PNPLA3 gene is associated with liver damage in chronic liver diseases. Interestingly, several studies have reported that the minor rs738409[G] allele is more represented in HCC cases in chronic hepatitis C (CHC) and alcoholic liver disease (ALD). However, a significant association with HCC related to CHC has not been consistently observed, and the strength of the association between rs738409 and HCC remains unclear. We performed a meta-analysis of individual participant data including 2,503 European patients with cirrhosis to assess the association between rs738409 and HCC, particularly in ALD and CHC. We found that rs738409 was strongly associated with overall HCC (odds ratio [OR] per G allele, additive model=1.77; 95% confidence interval [CI]: 1.42-2.19; P=2.78 ?x 10(-7) ). This association was more pronounced in ALD (OR=2.20; 95% CI: 1.80-2.67; P=4.71 ?x 10(-15) ) than in CHC patients (OR=1.55; 95% CI: 1.03-2.34; P=3.52 ?x 10(-2) ). After adjustment for age, sex, and body mass index, the variant remained strongly associated with HCC. |
Lopes, Miguel; Kutlu, Burak; Miani, MICHELA; Bang-Berthelsen, Claus H; Størling, Joachim; Pociot, Flemming; Goodman, Nathan; Hood, Lee; Welsh, Nils; Bontempi, Gianluca; Eizirik, Decio L Temporal profiling of cytokine-induced genes in pancreatic beta-cells by meta-analysis and network inference. Journal Article In: Genomics, 2014, (DOI: 10.1016/j.ygeno.2013.12.007). @article{info:hdl:2013/163447, title = {Temporal profiling of cytokine-induced genes in pancreatic beta-cells by meta-analysis and network inference.}, author = {Miguel Lopes and Burak Kutlu and MICHELA Miani and Claus H Bang-Berthelsen and Joachim Størling and Flemming Pociot and Nathan Goodman and Lee Hood and Nils Welsh and Gianluca Bontempi and Decio L Eizirik}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/163447/1/Elsevier_147077.pdf}, year = {2014}, date = {2014-01-01}, journal = {Genomics}, abstract = {Type 1 Diabetes (T1D) is an autoimmune disease where local release of cytokines such as IL-1β and IFN-γ contributes to β-cell apoptosis. To identify relevant genes regulating this process we performed a meta-analysis of 8 datasets of β-cell gene expression after exposure to IL-1β and IFN-γ. Two of these datasets are novel and contain time-series expressions in human islet cells and rat INS-1E cells. Genes were ranked according to their differential expression within and after 24h from exposure, and characterized by function and prior knowledge in the literature. A regulatory network was then inferred from the human time expression datasets, using a time-series extension of a network inference method. The two most differentially expressed genes previously unknown in T1D literature (RIPK2 and ELF3) were found to modulate cytokine-induced apoptosis. The inferred regulatory network is thus supported by the experimental validation, providing a proof-of-concept for the proposed statistical inference approach.}, note = {DOI: 10.1016/j.ygeno.2013.12.007}, keywords = {}, pubstate = {published}, tppubtype = {article} } Type 1 Diabetes (T1D) is an autoimmune disease where local release of cytokines such as IL-1β and IFN-γ contributes to β-cell apoptosis. To identify relevant genes regulating this process we performed a meta-analysis of 8 datasets of β-cell gene expression after exposure to IL-1β and IFN-γ. Two of these datasets are novel and contain time-series expressions in human islet cells and rat INS-1E cells. Genes were ranked according to their differential expression within and after 24h from exposure, and characterized by function and prior knowledge in the literature. A regulatory network was then inferred from the human time expression datasets, using a time-series extension of a network inference method. The two most differentially expressed genes previously unknown in T1D literature (RIPK2 and ELF3) were found to modulate cytokine-induced apoptosis. The inferred regulatory network is thus supported by the experimental validation, providing a proof-of-concept for the proposed statistical inference approach. |
Lerman, Liran; Bontempi, Gianluca; Markowitch, Olivier Power analysis attack: an approach based on machine learning Journal Article In: International Journal of Applied Cryptography, 3 (2), pp. 97-115, 2014, (DOI: 10.1504/IJACT.2014.062722). @article{info:hdl:2013/163770, title = {Power analysis attack: an approach based on machine learning}, author = {Liran Lerman and Gianluca Bontempi and Olivier Markowitch}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/163770}, year = {2014}, date = {2014-01-01}, journal = {International Journal of Applied Cryptography}, volume = {3}, number = {2}, pages = {97-115}, abstract = {In cryptography, a side-channel attack is any attack based on the analysis of measurements related to the physical implementation of a cryptosystem. Nowadays, the possibility of collecting a large amount of observations paves the way to the adoption of machine learning techniques, i.e., techniques able to extract information and patterns from large datasets. The use of statistical techniques for side-channel attacks is not new. Techniques like the template attack have shown their effectiveness in recent years. However, these techniques rely on parametric assumptions and are often limited to small dimensionality settings, which limit their range of application. This paper explores the use of machine learning techniques to relax such assumptions and to deal with high dimensional feature vectors. copyright 2014 Inderscience Enterprises Ltd.}, note = {DOI: 10.1504/IJACT.2014.062722}, keywords = {}, pubstate = {published}, tppubtype = {article} } In cryptography, a side-channel attack is any attack based on the analysis of measurements related to the physical implementation of a cryptosystem. Nowadays, the possibility of collecting a large amount of observations paves the way to the adoption of machine learning techniques, i.e., techniques able to extract information and patterns from large datasets. The use of statistical techniques for side-channel attacks is not new. Techniques like the template attack have shown their effectiveness in recent years. However, these techniques rely on parametric assumptions and are often limited to small dimensionality settings, which limit their range of application. This paper explores the use of machine learning techniques to relax such assumptions and to deal with high dimensional feature vectors. copyright 2014 Inderscience Enterprises Ltd. |
Olsen, Catharina; Fleming, Kathleen; Prendergast, Niall; Rubio, Renee; Emmert-Streib, Frank; Bontempi, Gianluca; Haibe-Kains, Benjamin; Quackenbush, John Inference and validation of predictive gene networks from biomedical literature and gene expression data Journal Article In: Genomics, 103 , pp. 329-336, 2014, (DOI: 10.1016/j.ygeno.2014.03.004). @article{info:hdl:2013/172095, title = {Inference and validation of predictive gene networks from biomedical literature and gene expression data}, author = {Catharina Olsen and Kathleen Fleming and Niall Prendergast and Renee Rubio and Frank Emmert-Streib and Gianluca Bontempi and Benjamin Haibe-Kains and John Quackenbush}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/172095/4/doi_155725.pdf}, year = {2014}, date = {2014-01-01}, journal = {Genomics}, volume = {103}, pages = {329-336}, abstract = {Although many methods have been developed for inference of biological networks, the validation of the resulting models has largely remained an unsolved problem. Here we present a framework for quantitative assessment of inferred gene interaction networks using knock-down data from cell line experiments. Using this framework we are able to show that network inference based on integration of prior knowledge derived from the biomedical literature with genomic data significantly improves the quality of inferred networks relative to other approaches. Our results also suggest that cell line experiments can be used to quantitatively assess the quality of networks inferred from tumor samples. copyright 2014.}, note = {DOI: 10.1016/j.ygeno.2014.03.004}, keywords = {}, pubstate = {published}, tppubtype = {article} } Although many methods have been developed for inference of biological networks, the validation of the resulting models has largely remained an unsolved problem. Here we present a framework for quantitative assessment of inferred gene interaction networks using knock-down data from cell line experiments. Using this framework we are able to show that network inference based on integration of prior knowledge derived from the biomedical literature with genomic data significantly improves the quality of inferred networks relative to other approaches. Our results also suggest that cell line experiments can be used to quantitatively assess the quality of networks inferred from tumor samples. copyright 2014. |
Olsen, Catharina; Bontempi, Gianluca; Emmert-Streib, Frank; Quackenbush, John; Haibe-Kains, Benjamin Relevance of different prior knowledge sources for inferring gene interaction networks Journal Article In: Frontiers in Genetics, 5 (177), 2014, (DOI: 10.3389/fgene.2014.00177). @article{info:hdl:2013/172097, title = {Relevance of different prior knowledge sources for inferring gene interaction networks}, author = {Catharina Olsen and Gianluca Bontempi and Frank Emmert-Streib and John Quackenbush and Benjamin Haibe-Kains}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/172097}, year = {2014}, date = {2014-01-01}, journal = {Frontiers in Genetics}, volume = {5}, number = {177}, abstract = {When inferring networks from high-throughput genomic data, one of the main challenges is the subsequent validation of these networks. In the best case scenario, the true network is partially known from previous research results published in structured databases or research articles. Traditionally, inferred networks are validated against these known interactions. Whenever the recovery rate is gauged to be high enough, subsequent high scoring but unknown inferred interactions are deemed good candidates for further experimental validation. Therefore such validation framework strongly depends on the quantity and quality of published interactions and presents serious pitfalls: (1) availability of these known interactions for the studied problem might be sparse; (2) quantitatively comparing different inference algorithms is not trivial; and (3) the use of these known interactions for validation prevents their integration in the inference procedure. The latter is particularly relevant as it has recently been showed that integration of priors during network inference significantly improves the quality of inferred networks. To overcome these problems when validating inferred networks, we recently proposed a data-driven validation framework based on single gene knock-down experiments. Using this framework, we were able to demonstrate the benefits of integrating prior knowledge and expression data. In this paper we used this framework to assess the quality of different sources of prior knowledge on their own and in combination with different genomic data sets in colorectal cancer. We observed that most prior sources lead to significant F -scores. Furthermore, their integration with genomic data leads to a significant increase in F -scores, especially for priors extracted from full text PubMed articles, known co-expression modules and genetic interactions. Lastly, we observed that the results are consistent for three different data sets: experimental knock-down data and two human tumor data sets. copyright 2014 Olsen, Bontempi, Emmert-Streib, Quackenbush and Haibe-Kains.}, note = {DOI: 10.3389/fgene.2014.00177}, keywords = {}, pubstate = {published}, tppubtype = {article} } When inferring networks from high-throughput genomic data, one of the main challenges is the subsequent validation of these networks. In the best case scenario, the true network is partially known from previous research results published in structured databases or research articles. Traditionally, inferred networks are validated against these known interactions. Whenever the recovery rate is gauged to be high enough, subsequent high scoring but unknown inferred interactions are deemed good candidates for further experimental validation. Therefore such validation framework strongly depends on the quantity and quality of published interactions and presents serious pitfalls: (1) availability of these known interactions for the studied problem might be sparse; (2) quantitatively comparing different inference algorithms is not trivial; and (3) the use of these known interactions for validation prevents their integration in the inference procedure. The latter is particularly relevant as it has recently been showed that integration of priors during network inference significantly improves the quality of inferred networks. To overcome these problems when validating inferred networks, we recently proposed a data-driven validation framework based on single gene knock-down experiments. Using this framework, we were able to demonstrate the benefits of integrating prior knowledge and expression data. In this paper we used this framework to assess the quality of different sources of prior knowledge on their own and in combination with different genomic data sets in colorectal cancer. We observed that most prior sources lead to significant F -scores. Furthermore, their integration with genomic data leads to a significant increase in F -scores, especially for priors extracted from full text PubMed articles, known co-expression modules and genetic interactions. Lastly, we observed that the results are consistent for three different data sets: experimental knock-down data and two human tumor data sets. copyright 2014 Olsen, Bontempi, Emmert-Streib, Quackenbush and Haibe-Kains. |
Lopes, Miguel; Bontempi, Gianluca On the null distribution of the precision and recall curve Journal Article In: Lecture notes in computer science, 8725 LNAI (PART 2), pp. 322-337, 2014, (DOI: 10.1007/978-3-662-44851-9_21). @article{info:hdl:2013/187934, title = {On the null distribution of the precision and recall curve}, author = {Miguel Lopes and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/187934}, year = {2014}, date = {2014-01-01}, journal = {Lecture notes in computer science}, volume = {8725 LNAI}, number = {PART 2}, pages = {322-337}, abstract = {Precision recall curves (pr-curves) and the associated area under (AUPRC) are commonly used to assess the accuracy of information retrieval (IR) algorithms. An informative baseline is random selection. The associated probability distribution makes it possible to assess pr-curve significancy (as a p-value relative to the null of random). To our knowledge, no analytical expression of the null distribution of empirical pr-curves is available, and the only measure of significancy used in the literature relies on non-parametric Monte Carlo simulations. In this paper, we derive analytically the expected null pr-curve and AUPRC, for different interpolation strategies. The AUPRC variance is also derived, and we use it to propose a continuous approximation to the null AUPRC distribution, based on the beta distribution. Properties of the empirical pr-curve and common interpolation strategies are also discussed. copyright 2014 Springer-Verlag.}, note = {DOI: 10.1007/978-3-662-44851-9_21}, keywords = {}, pubstate = {published}, tppubtype = {article} } Precision recall curves (pr-curves) and the associated area under (AUPRC) are commonly used to assess the accuracy of information retrieval (IR) algorithms. An informative baseline is random selection. The associated probability distribution makes it possible to assess pr-curve significancy (as a p-value relative to the null of random). To our knowledge, no analytical expression of the null distribution of empirical pr-curves is available, and the only measure of significancy used in the literature relies on non-parametric Monte Carlo simulations. In this paper, we derive analytically the expected null pr-curve and AUPRC, for different interpolation strategies. The AUPRC variance is also derived, and we use it to propose a continuous approximation to the null AUPRC distribution, based on the beta distribution. Properties of the empirical pr-curve and common interpolation strategies are also discussed. copyright 2014 Springer-Verlag. |
Pozzolo, Andrea Dal; "e, Yann-A; Bontempi, Gianluca; Caelen, Olivier; Waterschoot, Serge Learned lessons in credit card fraud detection from a practitioner perspective Journal Article In: Expert systems with applications, 41 (10), pp. 4915-4928, 2014, (DOI: 10.1016/j.eswa.2014.02.026). @article{info:hdl:2013/183504, title = {Learned lessons in credit card fraud detection from a practitioner perspective}, author = {Andrea Dal Pozzolo and Yann-A{"e}l Le Borgne and Gianluca Bontempi and Olivier Caelen and Serge Waterschoot}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/183504/1/Elsevier_167131.pdf}, year = {2014}, date = {2014-01-01}, journal = {Expert systems with applications}, volume = {41}, number = {10}, pages = {4915-4928}, abstract = {Billions of dollars of loss are caused every year due to fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to non-stationary distribution of the data, highly imbalanced classes distributions and continuous streams of transactions. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about which is the best strategy to deal with them. In this paper we provide some answers from the practitioner's perspective by focusing on three crucial issues: unbalancedness, non-stationarity and assessment. The analysis is made possible by a real credit card dataset provided by our industrial partner. copyright 2014 Elsevier Ltd. All rights reserved.}, note = {DOI: 10.1016/j.eswa.2014.02.026}, keywords = {}, pubstate = {published}, tppubtype = {article} } Billions of dollars of loss are caused every year due to fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to non-stationary distribution of the data, highly imbalanced classes distributions and continuous streams of transactions. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about which is the best strategy to deal with them. In this paper we provide some answers from the practitioner's perspective by focusing on three crucial issues: unbalancedness, non-stationarity and assessment. The analysis is made possible by a real credit card dataset provided by our industrial partner. copyright 2014 Elsevier Ltd. All rights reserved. |
Dedeurwaerder, Sarah; Defrance, Matthieu; Bizet, Martin; Calonne, Emilie; Bontempi, Gianluca; c c, Fran A comprehensive overview of Infinium Human Methylation450 data processing Journal Article In: Briefings in bioinformatics, 15 (6), pp. 929-941, 2014, (DOI: 0.1093/bib/bbt054). @article{info:hdl:2013/186990, title = {A comprehensive overview of Infinium Human Methylation450 data processing}, author = {Sarah Dedeurwaerder and Matthieu Defrance and Martin Bizet and Emilie Calonne and Gianluca Bontempi and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/186990/3/Dedeurwaerder2014.pdf}, year = {2014}, date = {2014-01-01}, journal = {Briefings in bioinformatics}, volume = {15}, number = {6}, pages = {929-941}, abstract = {Infinium HumanMethylation450 beadarray is a popular technology to explore DNA methylomes in health and disease, and there is a current explosion in the use of this technique. Despite experience acquired from gene expression microarrays, analyzing Infinium Methylation arrays appeared more complex than initially thought and several difficulties have been encountered, as those arrays display specific features that need to be taken into consideration during data processing. Here, we review several issues that have been highlighted by the scientific community, and we present an overview of the general data processing scheme and an evaluation of the different normalization methods available to date to guide the 450K users in their analysis and data interpretation.}, note = {DOI: 0.1093/bib/bbt054}, keywords = {}, pubstate = {published}, tppubtype = {article} } Infinium HumanMethylation450 beadarray is a popular technology to explore DNA methylomes in health and disease, and there is a current explosion in the use of this technique. Despite experience acquired from gene expression microarrays, analyzing Infinium Methylation arrays appeared more complex than initially thought and several difficulties have been encountered, as those arrays display specific features that need to be taken into consideration during data processing. Here, we review several issues that have been highlighted by the scientific community, and we present an overview of the general data processing scheme and an evaluation of the different normalization methods available to date to guide the 450K users in their analysis and data interpretation. |
Deplus, Rachel; "i, Lo; Rajavelu, Arumugam; Boukaba, Abdel Halim; Defrance, Matthieu; Luciani, Judith; c c, Fran; Dedeurwaerder, Sarah; `e, Hél; Brinkman, Arie B; Simmer, Femke; Müller, Fabian; Bertin, Benjamin; Berdasco, Maria; Putmans, Pascale; Calonne, Emilie; Litchfield, David DW; Launoit, Yvan De; Jurkowski, Tomasz Piotr; Stunnenberg, Hendrik HG; Bock, Christoph; Sotiriou, Christos; Fraga, Mario F; Esteller, Manel; Jeltsch, Albert; c c, Fran Regulation of DNA methylation patterns by CK2-mediated phosphorylation of Dnmt3a. Journal Article In: Cell reports, 8 (3), pp. 743-753, 2014, (DOI: 10.1016/j.celrep.2014.06.048). @article{info:hdl:2013/178545, title = {Regulation of DNA methylation patterns by CK2-mediated phosphorylation of Dnmt3a.}, author = {Rachel Deplus and Lo{"i}c Blanchon and Arumugam Rajavelu and Abdel Halim Boukaba and Matthieu Defrance and Judith Luciani and Fran{c c}oise Rothé and Sarah Dedeurwaerder and Hél{`e}ne Denis and Arie B Brinkman and Femke Simmer and Fabian Müller and Benjamin Bertin and Maria Berdasco and Pascale Putmans and Emilie Calonne and David DW Litchfield and Yvan De Launoit and Tomasz Piotr Jurkowski and Hendrik HG Stunnenberg and Christoph Bock and Christos Sotiriou and Mario F Fraga and Manel Esteller and Albert Jeltsch and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/178545/4/doi_162172.pdf}, year = {2014}, date = {2014-01-01}, journal = {Cell reports}, volume = {8}, number = {3}, pages = {743-753}, abstract = {DNA methylation is a central epigenetic modification that is established by de novo DNA methyltransferases. The mechanisms underlying the generation of genomic methylation patterns are still poorly understood. Using mass spectrometry and a phosphospecific Dnmt3a antibody, we demonstrate that CK2 phosphorylates endogenous Dnmt3a at two key residues located near its PWWP domain, thereby downregulating the ability of Dnmt3a to methylate DNA. Genome-wide DNA methylation analysis shows that CK2 primarily modulates CpG methylation of several repeats, most notably of Alu SINEs. This modulation can be directly attributed to CK2-mediated phosphorylation of Dnmt3a. We also find that CK2-mediated phosphorylation is required for localization of Dnmt3a to heterochromatin. By revealing phosphorylation as a mode of regulation of de novo DNA methyltransferase function and by uncovering a mechanism for the regulation of methylation at repetitive elements, our results shed light on the origin of DNA methylation patterns.}, note = {DOI: 10.1016/j.celrep.2014.06.048}, keywords = {}, pubstate = {published}, tppubtype = {article} } DNA methylation is a central epigenetic modification that is established by de novo DNA methyltransferases. The mechanisms underlying the generation of genomic methylation patterns are still poorly understood. Using mass spectrometry and a phosphospecific Dnmt3a antibody, we demonstrate that CK2 phosphorylates endogenous Dnmt3a at two key residues located near its PWWP domain, thereby downregulating the ability of Dnmt3a to methylate DNA. Genome-wide DNA methylation analysis shows that CK2 primarily modulates CpG methylation of several repeats, most notably of Alu SINEs. This modulation can be directly attributed to CK2-mediated phosphorylation of Dnmt3a. We also find that CK2-mediated phosphorylation is required for localization of Dnmt3a to heterochromatin. By revealing phosphorylation as a mode of regulation of de novo DNA methyltransferase function and by uncovering a mechanism for the regulation of methylation at repetitive elements, our results shed light on the origin of DNA methylation patterns. |
Milenkovic, Dragan; Berghe, Wim Vanden; Boby, Céline; Leroux, Christine; Declerck, Ken; vel Szic, Katarzyna Szarc; Heyninck, Karen; Laukens, Kris; Bizet, Martin; Defrance, Matthieu; Dedeurwaerder, Sarah; Calonne, Emilie; c c, Fran; Haegeman, Guy; Haenen, Guido R M M G R M M; Bast, Aalt; Weseler, Antje R Dietary flavanols modulate the transcription of genes associated with cardiovascular pathology without changes in their DNA methylation state. Journal Article In: PloS one, 9 (4), pp. e95527, 2014, (DOI: 10.1371/journal.pone.0095527). @article{info:hdl:2013/262156, title = {Dietary flavanols modulate the transcription of genes associated with cardiovascular pathology without changes in their DNA methylation state.}, author = {Dragan Milenkovic and Wim Vanden Berghe and Céline Boby and Christine Leroux and Ken Declerck and Katarzyna Szarc vel Szic and Karen Heyninck and Kris Laukens and Martin Bizet and Matthieu Defrance and Sarah Dedeurwaerder and Emilie Calonne and Fran{c c}ois Fuks and Guy Haegeman and Guido R M M G R M M Haenen and Aalt Bast and Antje R Weseler}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/262156/4/doi_245783.pdf}, year = {2014}, date = {2014-01-01}, journal = {PloS one}, volume = {9}, number = {4}, pages = {e95527}, abstract = {In a recent intervention study, the daily supplementation with 200 mg monomeric and oligomeric flavanols (MOF) from grape seeds for 8 weeks revealed a vascular health benefit in male smokers. The objective of the present study was to determine the impact of MOF consumption on the gene expression profile of leukocytes and to assess changes in DNA methylation.}, note = {DOI: 10.1371/journal.pone.0095527}, keywords = {}, pubstate = {published}, tppubtype = {article} } In a recent intervention study, the daily supplementation with 200 mg monomeric and oligomeric flavanols (MOF) from grape seeds for 8 weeks revealed a vascular health benefit in male smokers. The objective of the present study was to determine the impact of MOF consumption on the gene expression profile of leukocytes and to assess changes in DNA methylation. |
2013 |
Bonnechere, Bruno; Wermenbol, Vanessa; Dan, Bernard; Salvia, Patrick; "e, Yann-A; Bontempi, Gianluca; Vansummeren, Stijn; Sholukha, Victor; Moiseev, Fedor; Jansen, Bart; Rooze, Marcel; Jan, Serge Van Sint Management and interpretation of medical data related to Cerebral Palsy : the ICT4Rehab project. Inproceedings In: EPNS, 2013, (Conference: (2013: Brussels, Belgium)). @inproceedings{info:hdl:2013/151891, title = {Management and interpretation of medical data related to Cerebral Palsy : the ICT4Rehab project.}, author = {Bruno Bonnechere and Vanessa Wermenbol and Bernard Dan and Patrick Salvia and Yann-A{"e}l Le Borgne and Gianluca Bontempi and Stijn Vansummeren and Victor Sholukha and Fedor Moiseev and Bart Jansen and Marcel Rooze and Serge Van Sint Jan}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151891}, year = {2013}, date = {2013-01-01}, booktitle = {EPNS}, note = {Conference: (2013: Brussels, Belgium)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
"e, Yann-A; Bontempi, Gianluca; Bonnechere, Bruno; Salvia, Patrick; Degelaen, Marc; Jan, Serge Van Sint Data mining toolbox for gait analysis in children with cerebral palsy Inproceedings In: ISB, 2013, (Conference: (2013: Natal, Brazil)). @inproceedings{info:hdl:2013/151884, title = {Data mining toolbox for gait analysis in children with cerebral palsy}, author = {Yann-A{"e}l Le Borgne and Gianluca Bontempi and Bruno Bonnechere and Patrick Salvia and Marc Degelaen and Serge Van Sint Jan}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151884}, year = {2013}, date = {2013-01-01}, booktitle = {ISB}, note = {Conference: (2013: Natal, Brazil)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Jan, Serge Van Sint; Wermenbol, Vanessa; Dan, Bernard; Salvia, Patrick; Bonnechere, Bruno; "e, Yann-A; Bontempi, Gianluca; Vansummeren, Stijn; Sholukha, Victor; Moiseev, Fedor; Jansen, Bart; Rooze, Marcel In: SOFAMEA, 2013, (Conference: (2013: Luxembourg, Luxembourg)). @inproceedings{info:hdl:2013/151876, title = {Développement d'instruments partagés pour la gestion et l'interprétation de données relatives `a la locomoation : le projet ICT4Rehab}, author = {Serge Van Sint Jan and Vanessa Wermenbol and Bernard Dan and Patrick Salvia and Bruno Bonnechere and Yann-A{"e}l Le Borgne and Gianluca Bontempi and Stijn Vansummeren and Victor Sholukha and Fedor Moiseev and Bart Jansen and Marcel Rooze}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151876}, year = {2013}, date = {2013-01-01}, booktitle = {SOFAMEA}, note = {Conference: (2013: Luxembourg, Luxembourg)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
"e, Yann-A; Bonnechere, Bruno; Salvia, Patrick; Jan, Serge Van Sint; Bontempi, Gianluca Fouille de donnée pour l'analyse de la marche de patients atteints d'infirmité motrice cérébrale (ICT4Rehab) Inproceedings In: SOFAMEA, 2013, (Conference: (2013: Luxembourg, Luxembourg)). @inproceedings{info:hdl:2013/151877, title = {Fouille de donnée pour l'analyse de la marche de patients atteints d'infirmité motrice cérébrale (ICT4Rehab)}, author = {Yann-A{"e}l Le Borgne and Bruno Bonnechere and Patrick Salvia and Serge Van Sint Jan and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151877}, year = {2013}, date = {2013-01-01}, booktitle = {SOFAMEA}, note = {Conference: (2013: Luxembourg, Luxembourg)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Cilia, Elisa; Pancsa, Rita; Tompa, Peter; Lenaerts, Tom; Vranken, Wim From protein sequence to dynamics and disorder with DynaMine. Journal Article In: Nature communications, 4 , pp. 2741, 2013, (DOI: 10.1038/ncomms3741). @article{info:hdl:2013/186425, title = {From protein sequence to dynamics and disorder with DynaMine.}, author = {Elisa Cilia and Rita Pancsa and Peter Tompa and Tom Lenaerts and Wim Vranken}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/186425/3/doi_170052.pdf}, year = {2013}, date = {2013-01-01}, journal = {Nature communications}, volume = {4}, pages = {2741}, abstract = {Protein function and dynamics are closely related; however, accurate dynamics information is difficult to obtain. Here based on a carefully assembled data set derived from experimental data for proteins in solution, we quantify backbone dynamics properties on the amino-acid level and develop DynaMine--a fast, high-quality predictor of protein backbone dynamics. DynaMine uses only protein sequence information as input and shows great potential in distinguishing regions of different structural organization, such as folded domains, disordered linkers, molten globules and pre-structured binding motifs of different sizes. It also identifies disordered regions within proteins with an accuracy comparable to the most sophisticated existing predictors, without depending on prior disorder knowledge or three-dimensional structural information. DynaMine provides molecular biologists with an important new method that grasps the dynamical characteristics of any protein of interest, as we show here for human p53 and E1A from human adenovirus 5.}, note = {DOI: 10.1038/ncomms3741}, keywords = {}, pubstate = {published}, tppubtype = {article} } Protein function and dynamics are closely related; however, accurate dynamics information is difficult to obtain. Here based on a carefully assembled data set derived from experimental data for proteins in solution, we quantify backbone dynamics properties on the amino-acid level and develop DynaMine--a fast, high-quality predictor of protein backbone dynamics. DynaMine uses only protein sequence information as input and shows great potential in distinguishing regions of different structural organization, such as folded domains, disordered linkers, molten globules and pre-structured binding motifs of different sizes. It also identifies disordered regions within proteins with an accuracy comparable to the most sophisticated existing predictors, without depending on prior disorder knowledge or three-dimensional structural information. DynaMine provides molecular biologists with an important new method that grasps the dynamical characteristics of any protein of interest, as we show here for human p53 and E1A from human adenovirus 5. |
Han, The Anh T A H; 'i, Lu; Santos, Francisco C; Lenaerts, Tom Good agreements make good friends. Journal Article In: Scientific reports, 3 , pp. 2695, 2013, (DOI: 10.1038/srep02695). @article{info:hdl:2013/155962, title = {Good agreements make good friends.}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/155962/4/doi_140875.pdf}, year = {2013}, date = {2013-01-01}, journal = {Scientific reports}, volume = {3}, pages = {2695}, abstract = {When starting a new collaborative endeavor, it pays to establish upfront how strongly your partner commits to the common goal and what compensation can be expected in case the collaboration is violated. Diverse examples in biological and social contexts have demonstrated the pervasiveness of making prior agreements on posterior compensations, suggesting that this behavior could have been shaped by natural selection. Here, we analyze the evolutionary relevance of such a commitment strategy and relate it to the costly punishment strategy, where no prior agreements are made. We show that when the cost of arranging a commitment deal lies within certain limits, substantial levels of cooperation can be achieved. Moreover, these levels are higher than that achieved by simple costly punishment, especially when one insists on sharing the arrangement cost. Not only do we show that good agreements make good friends, agreements based on shared costs result in even better outcomes.}, note = {DOI: 10.1038/srep02695}, keywords = {}, pubstate = {published}, tppubtype = {article} } When starting a new collaborative endeavor, it pays to establish upfront how strongly your partner commits to the common goal and what compensation can be expected in case the collaboration is violated. Diverse examples in biological and social contexts have demonstrated the pervasiveness of making prior agreements on posterior compensations, suggesting that this behavior could have been shaped by natural selection. Here, we analyze the evolutionary relevance of such a commitment strategy and relate it to the costly punishment strategy, where no prior agreements are made. We show that when the cost of arranging a commitment deal lies within certain limits, substantial levels of cooperation can be achieved. Moreover, these levels are higher than that achieved by simple costly punishment, especially when one insists on sharing the arrangement cost. Not only do we show that good agreements make good friends, agreements based on shared costs result in even better outcomes. |
Traulsen, Arne; Lenaerts, Tom; Pacheco, Jorge J M; Dingli, David On the dynamics of neutral mutations in a mathematical model for a homogeneous stem cell population. Journal Article In: Journal of the Royal Society, Interface / the Royal Society, 10 (79), pp. 20120810, 2013, (DOI: 10.1098/rsif.2012.0810). @article{info:hdl:2013/138049, title = {On the dynamics of neutral mutations in a mathematical model for a homogeneous stem cell population.}, author = {Arne Traulsen and Tom Lenaerts and Jorge J M Pacheco and David Dingli}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/138049}, year = {2013}, date = {2013-01-01}, journal = {Journal of the Royal Society, Interface / the Royal Society}, volume = {10}, number = {79}, pages = {20120810}, abstract = {The theory of the clonal origin of cancer states that a tumour arises from one cell that acquires mutation(s) leading to the malignant phenotype. It is the current belief that many of these mutations give a fitness advantage to the mutant population allowing it to expand, eventually leading to disease. However, mutations that lead to such a clonal expansion need not give a fitness advantage and may in fact be neutral-or almost neutral-with respect to fitness. Such mutant clones can be eliminated or expand stochastically, leading to a malignant phenotype (disease). Mutations in haematopoietic stem cells give rise to diseases such as chronic myeloid leukaemia (CML) and paroxysmal nocturnal haemoglobinuria (PNH). Although neutral drift often leads to clonal extinction, disease is still possible, and in this case, it has important implications both for the incidence of disease and for therapy, as it may be more difficult to eliminate neutral mutations with therapy. We illustrate the consequences of such dynamics, using CML and PNH as examples. These considerations have implications for many other tumours as well.}, note = {DOI: 10.1098/rsif.2012.0810}, keywords = {}, pubstate = {published}, tppubtype = {article} } The theory of the clonal origin of cancer states that a tumour arises from one cell that acquires mutation(s) leading to the malignant phenotype. It is the current belief that many of these mutations give a fitness advantage to the mutant population allowing it to expand, eventually leading to disease. However, mutations that lead to such a clonal expansion need not give a fitness advantage and may in fact be neutral-or almost neutral-with respect to fitness. Such mutant clones can be eliminated or expand stochastically, leading to a malignant phenotype (disease). Mutations in haematopoietic stem cells give rise to diseases such as chronic myeloid leukaemia (CML) and paroxysmal nocturnal haemoglobinuria (PNH). Although neutral drift often leads to clonal extinction, disease is still possible, and in this case, it has important implications both for the incidence of disease and for therapy, as it may be more difficult to eliminate neutral mutations with therapy. We illustrate the consequences of such dynamics, using CML and PNH as examples. These considerations have implications for many other tumours as well. |
Olsen, Catharina; Bontempi, Gianluca; Quackenbush, John; Haibe-Kains, Benjamin Data-driven validation of gene regulatory networks using knock-down data Miscellaneous 2013, (Conference: 8th Benelux Bioinformatics Conference (BBC13)). @misc{info:hdl:2013/155454, title = {Data-driven validation of gene regulatory networks using knock-down data}, author = {Catharina Olsen and Gianluca Bontempi and John Quackenbush and Benjamin Haibe-Kains}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/155454}, year = {2013}, date = {2013-01-01}, note = {Conference: 8th Benelux Bioinformatics Conference (BBC13)}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Olsen, Catharina; Bontempi, Gianluca; Quackenbush, John; Haibe-Kains, Benjamin Data-driven validation of gene regulatory networks using knock-down data Miscellaneous 2013, (Conference: 8th Benelux Bioinformatics Conference (BBC13)). @misc{info:hdl:2013/245104, title = {Data-driven validation of gene regulatory networks using knock-down data}, author = {Catharina Olsen and Gianluca Bontempi and John Quackenbush and Benjamin Haibe-Kains}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/245104}, year = {2013}, date = {2013-01-01}, note = {Conference: 8th Benelux Bioinformatics Conference (BBC13)}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Trepo, Eric; Nahon, Pierre; Bontempi, Gianluca; Valenti, Luca; Falleti, Edmondo; Nischalke, Hans Dieter; Hamza, Samia; Corradini, Stefano Ginanni; Burza, Maria Antonella; Guyot, Erwan; Donati, Benedetta; Spengler, Ulrich; Hillon, Patrick; Toniutto, Pierluigi; Henrion, Jean; Mathurin, Philippe; Moreno, Christophe; Romeo, Stefano; Deltenre, Pierre 2013, (Conference: The Liver Meeting, American Association for the Study of Liver Diseases(2013: Washington, USA)). @misc{info:hdl:2013/225572, title = {Association between the PNPLA3 (rs738409 C>G) variant and hepatocellular carcinoma: evidence from a meta-analysis of individual participant data}, author = {Eric Trepo and Pierre Nahon and Gianluca Bontempi and Luca Valenti and Edmondo Falleti and Hans Dieter Nischalke and Samia Hamza and Stefano Ginanni Corradini and Maria Antonella Burza and Erwan Guyot and Benedetta Donati and Ulrich Spengler and Patrick Hillon and Pierluigi Toniutto and Jean Henrion and Philippe Mathurin and Christophe Moreno and Stefano Romeo and Pierre Deltenre}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/225572}, year = {2013}, date = {2013-01-01}, note = {Conference: The Liver Meeting, American Association for the Study of Liver Diseases(2013: Washington, USA)}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Han, The Anh T A H; 'i, Lu; Santos, F C; Lenaerts, Tom Why is it so hard to say sorry: evolution of apology with commitment in the iterated Prisoner's Dilemma Inproceedings In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2013, (Language of publication: na). @inproceedings{info:hdl:2013/155970, title = {Why is it so hard to say sorry: evolution of apology with commitment in the iterated Prisoner's Dilemma}, author = {The Anh T A H Han and Lu{'i}s Moniz Pereira and F C Santos and Tom Lenaerts}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/155970}, year = {2013}, date = {2013-01-01}, booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)}, note = {Language of publication: na}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Lerat, Jean-Sébastien; Han, The Anh T A H; Lenaerts, Tom Evolution of Common-Pool Resources and Social Welfare in Structured Populations Inproceedings In: Joint Conference on Artificial Intelligence: Twenty-Third International Joint Conference on Artificial Intelligence, pp. 2848-2854, Association for the Advancement of Artificial Intelligence, 2013, (Conference: (August 3-9 2013: Beijing)). @inproceedings{info:hdl:2013/149489, title = {Evolution of Common-Pool Resources and Social Welfare in Structured Populations}, author = {Jean-Sébastien Lerat and The Anh T A H Han and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/149489/1/IJCAI13-419.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Joint Conference on Artificial Intelligence: Twenty-Third International Joint Conference on Artificial Intelligence}, pages = {2848-2854}, publisher = {Association for the Advancement of Artificial Intelligence}, series = {Agent-Based and Multiagent Systems}, abstract = {The Common-pool resource (CPR) game is a social dilemma where agents have to decide how to consume a shared CPR. Either they each take their cut, completely destroying the CPR, or they restrain themselves, gaining less immediate profit but sustaining the resource and future profit. When no consumption takes place the CPR simply grows to its carrying capacity. As such, this dilemma provides a framework to study the evolution of social consumption strategies and the sustainability of resources, whose size adjusts dynamically through consumption and their own implicit population dynamics. The present study provides for the first time a detailed analysis of the evolutionary dynamics of consumption strategies in finite populations, focusing on the interplay between the resource levels and preferred consumption strategies. We show analytically which restrained consumers survive in relation to the growth rate of the resources and how this affects the resources' carrying capacity. Second, we show that population structures affect the sustainability of the resources and social welfare in the population. Current results provide an initial insight into the complexity of the CPR game, showing potential for a variety of different studies in the context of social welfare and resource sustainability.}, note = {Conference: (August 3-9 2013: Beijing)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The Common-pool resource (CPR) game is a social dilemma where agents have to decide how to consume a shared CPR. Either they each take their cut, completely destroying the CPR, or they restrain themselves, gaining less immediate profit but sustaining the resource and future profit. When no consumption takes place the CPR simply grows to its carrying capacity. As such, this dilemma provides a framework to study the evolution of social consumption strategies and the sustainability of resources, whose size adjusts dynamically through consumption and their own implicit population dynamics. The present study provides for the first time a detailed analysis of the evolutionary dynamics of consumption strategies in finite populations, focusing on the interplay between the resource levels and preferred consumption strategies. We show analytically which restrained consumers survive in relation to the growth rate of the resources and how this affects the resources' carrying capacity. Second, we show that population structures affect the sustainability of the resources and social welfare in the population. Current results provide an initial insight into the complexity of the CPR game, showing potential for a variety of different studies in the context of social welfare and resource sustainability. |
Olsen, Catharina; Haibe-Kains, Benjamin; Quackenbush, John; Bontempi, Gianluca On the Integration of Prior Knowledge in the Inference of Regulatory Networks. Book Chapter In: World Scientific, 2013, (Language of publication: fr). @inbook{info:hdl:2013/223360, title = {On the Integration of Prior Knowledge in the Inference of Regulatory Networks.}, author = {Catharina Olsen and Benjamin Haibe-Kains and John Quackenbush and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/223360}, year = {2013}, date = {2013-01-01}, publisher = {World Scientific}, series = {Biological Data Mining and Its Applications in Healthcare}, note = {Language of publication: fr}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
Olsen, Catharina Causal inference and prior integration in bioinformatics using information theory PhD Thesis 2013, (Funder: Universite Libre de Bruxelles). @phdthesis{info:hdl:2013/209401, title = {Causal inference and prior integration in bioinformatics using information theory}, author = {Catharina Olsen}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/209401/1/ba9583ce-51e9-4718-b438-fb816d60aea4.txt}, year = {2013}, date = {2013-01-01}, abstract = {An important problem in bioinformatics is the reconstruction of gene regulatory networks from expression data. The analysis of genomic data stemming from high- throughput technologies such as microarray experiments or RNA-sequencing faces several difficulties. The first major issue is the high variable to sample ratio which is due to a number of factors: a single experiment captures all genes while the number of experiments is restricted by the experiment's cost, time and patient cohort size. The second problem is that these data sets typically exhibit high amounts of noise. Another important problem in bioinformatics is the question of how the inferred networks' quality can be evaluated. The current best practice is a two step procedure. In the first step, the highest scoring interactions are compared to known interactions stored in biological databases. The inferred networks passes this quality assessment if there is a large overlap with the known interactions. In this case, a second step is carried out in which unknown but high scoring and thus promising new interactions are validated 'by hand' via laboratory experiments. Unfortunately when integrating prior knowledge in the inference procedure, this validation procedure would be biased by using the same information in both the inference and the validation. Therefore, it would no longer allow an independent validation of the resulting network. The main contribution of this thesis is a complete computational framework that uses experimental knock down data in a cross-validation scheme to both infer and validate directed networks. Its components are i) a method that integrates genomic data and prior knowledge to infer directed networks, ii) its implementation in an R/Bioconductor package and iii) a web application to retrieve prior knowledge from PubMed abstracts and biological databases. To infer directed networks from genomic data and prior knowledge, we propose a two step procedure: First, we adapt the pairwise feature selection strategy mRMR to integrate prior knowledge in order to obtain the network's skeleton. Then for the subsequent orientation phase of the algorithm, we extend a criterion based on interaction information to include prior knowledge. The implementation of this method is available both as part of the prior retrieval tool Predictive Networks and as a stand-alone R/Bioconductor package named predictionet. Furthermore, we propose a fully data-driven quantitative validation of such directed networks using experimental knock-down data: We start by identifying the set of genes that was truly affected by the perturbation experiment. The rationale of our validation procedure is that these truly affected genes should also be part of the perturbed gene's childhood in the inferred network. Consequently, we can compute a performance score}, An important problem in bioinformatics is the reconstruction of gene regulatory networks from expression data. The analysis of genomic data stemming from high- throughput technologies such as microarray experiments or RNA-sequencing faces several difficulties. The first major issue is the high variable to sample ratio which is due to a number of factors: a single experiment captures all genes while the number of experiments is restricted by the experiment's cost, time and patient cohort size. The second problem is that these data sets typically exhibit high amounts of noise.<p><p>Another important problem in bioinformatics is the question of how the inferred networks' quality can be evaluated. The current best practice is a two step procedure. In the first step, the highest scoring interactions are compared to known interactions stored in biological databases. The inferred networks passes this quality assessment if there is a large overlap with the known interactions. In this case, a second step is carried out in which unknown but high scoring and thus promising new interactions are validated 'by hand' via laboratory experiments. Unfortunately when integrating prior knowledge in the inference procedure, this validation procedure would be biased by using the same information in both the inference and the validation. Therefore, it would no longer allow an independent validation of the resulting network.<p><p>The main contribution of this thesis is a complete computational framework that uses experimental knock down data in a cross-validation scheme to both infer and validate directed networks. Its components are i) a method that integrates genomic data and prior knowledge to infer directed networks, ii) its implementation in an R/Bioconductor package and iii) a web application to retrieve prior knowledge from PubMed abstracts and biological databases. To infer directed networks from genomic data and prior knowledge, we propose a two step procedure: First, we adapt the pairwise feature selection strategy mRMR to integrate prior knowledge in order to obtain the network's skeleton. Then for the subsequent orientation phase of the algorithm, we extend a criterion based on interaction information to include prior knowledge. The implementation of this method is available both as part of the prior retrieval tool Predictive Networks and as a stand-alone R/Bioconductor package named predictionet.<p><p>Furthermore, we propose a fully data-driven quantitative validation of such directed networks using experimental knock-down data: We start by identifying the set of genes that was truly affected by the perturbation experiment. The rationale of our validation procedure is that these truly affected genes should also be part of the perturbed gene's childhood in the inferred network. Consequently, we can compute a performance score |
Haibe-Kains, Benjamin; Desmedt, Christine; Leo, Angelo Di; Azambuja, Evandro; Larsimont, Denis; Selleslags, Jean; Delaloge, Suzette; Duhem, Caroline; Kains, Jean-Pierre; Carly, Birgit; Maerevoet, Marie; Vindevoghel, Anita; Rouas, Ghizlane; c c, Fran; Durbecq, Virginie; Cardoso, Fatima; Salgado, Roberto; Rovere, Rodrigo Kraft; Bontempi, Gianluca; Michiels, Stefan; Buyse, Marc; Nogaret, Jean-Marie; Qi, Yuan; Symmans, William Fraser; Pusztai, Lajos; D'Hondt, Veronique; Piccart-Gebhart, Martine; Sotiriou, Christos Genome-wide gene expression profiling to predict resistance to anthracyclines in breast cancer patients Journal Article In: Genomics Data, 1 , pp. 7-10, 2013, (DOI: 10.1016/j.gdata.2013.09.001). @article{info:hdl:2013/177704, title = {Genome-wide gene expression profiling to predict resistance to anthracyclines in breast cancer patients}, author = {Benjamin Haibe-Kains and Christine Desmedt and Angelo Di Leo and Evandro Azambuja and Denis Larsimont and Jean Selleslags and Suzette Delaloge and Caroline Duhem and Jean-Pierre Kains and Birgit Carly and Marie Maerevoet and Anita Vindevoghel and Ghizlane Rouas and Fran{c c}oise Lallemand and Virginie Durbecq and Fatima Cardoso and Roberto Salgado and Rodrigo Kraft Rovere and Gianluca Bontempi and Stefan Michiels and Marc Buyse and Jean-Marie Nogaret and Yuan Qi and William Fraser Symmans and Lajos Pusztai and Veronique D'Hondt and Martine Piccart-Gebhart and Christos Sotiriou}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/177704/4/doi_161331.pdf}, year = {2013}, date = {2013-01-01}, journal = {Genomics Data}, volume = {1}, pages = {7-10}, abstract = {Validated biomarkers predictive of response/resistance to anthracyclines in breast cancer are currently lacking. The neoadjuvant Trial of Principle (TOP) study, in which patients with estrogen receptor (ER)-negative tumors were treated with anthracycline (epirubicin) monotherapy, was specifically designed to evaluate the predictive value of topoisomerase II-alpha (TOP2A) and develop a gene expression signature to identify those patients who do not benefit from anthracyclines. Here we describe in details the contents and quality controls for the gene expression and clinical data associated with the study published by Desmedt and colleagues in the Journal of Clinical Oncology in 2011 (Desmedt et al., 2011). We also provide R code to easily access the data and perform the quality controls and basic analyses relevant to this dataset. copyright 2013 The Authors.}, note = {DOI: 10.1016/j.gdata.2013.09.001}, keywords = {}, pubstate = {published}, tppubtype = {article} } Validated biomarkers predictive of response/resistance to anthracyclines in breast cancer are currently lacking. The neoadjuvant Trial of Principle (TOP) study, in which patients with estrogen receptor (ER)-negative tumors were treated with anthracycline (epirubicin) monotherapy, was specifically designed to evaluate the predictive value of topoisomerase II-alpha (TOP2A) and develop a gene expression signature to identify those patients who do not benefit from anthracyclines. Here we describe in details the contents and quality controls for the gene expression and clinical data associated with the study published by Desmedt and colleagues in the Journal of Clinical Oncology in 2011 (Desmedt et al., 2011). We also provide R code to easily access the data and perform the quality controls and basic analyses relevant to this dataset. copyright 2013 The Authors. |
Bonnechere, Bruno; Wermenbol, Vanessa; Dan, Bernard; Salvia, Patrick; "e, Yann-A; Bontempi, Gianluca; Vansummeren, Stijn; Sholukha, Victor; Moiseev, Fedor; Jansen, Bart; Rooze, Marcel; Jan, Serge Van Sint Management and interpretation of medical data related to cerebral pasly: the ICT4 Rehab project Journal Article In: European journal of paediatric neurology, 17 (1), pp. 32, 2013, (Language of publication: na). @article{info:hdl:2013/151908, title = {Management and interpretation of medical data related to cerebral pasly: the ICT4 Rehab project}, author = {Bruno Bonnechere and Vanessa Wermenbol and Bernard Dan and Patrick Salvia and Yann-A{"e}l Le Borgne and Gianluca Bontempi and Stijn Vansummeren and Victor Sholukha and Fedor Moiseev and Bart Jansen and Marcel Rooze and Serge Van Sint Jan}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151908}, year = {2013}, date = {2013-01-01}, journal = {European journal of paediatric neurology}, volume = {17}, number = {1}, pages = {32}, note = {Language of publication: na}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Papillon-Cavanagh, Simon; Jay, Nicolas De; Hachem, Nehme; Olsen, Catharina; Bontempi, Gianluca; Aerts, Hugo J W L; Quackenbush, John; Haibe-Kains, Benjamin Comparison and validation of genomic predictors for anticancer drug sensitivity. Journal Article In: Journal of the American Medical Informatics Association, 20 (4), pp. 597-602, 2013, (DOI: 10.1136/amiajnl-2012-001442). @article{info:hdl:2013/145203, title = {Comparison and validation of genomic predictors for anticancer drug sensitivity.}, author = {Simon Papillon-Cavanagh and Nicolas De Jay and Nehme Hachem and Catharina Olsen and Gianluca Bontempi and Hugo J W L Aerts and John Quackenbush and Benjamin Haibe-Kains}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/145203/3/doi_129008.pdf}, year = {2013}, date = {2013-01-01}, journal = {Journal of the American Medical Informatics Association}, volume = {20}, number = {4}, pages = {597-602}, abstract = {An enduring challenge in personalized medicine lies in selecting the right drug for each individual patient. While testing of drugs on patients in large trials is the only way to assess their clinical efficacy and toxicity, we dramatically lack resources to test the hundreds of drugs currently under development. Therefore the use of preclinical model systems has been intensively investigated as this approach enables response to hundreds of drugs to be tested in multiple cell lines in parallel.}, note = {DOI: 10.1136/amiajnl-2012-001442}, keywords = {}, pubstate = {published}, tppubtype = {article} } An enduring challenge in personalized medicine lies in selecting the right drug for each individual patient. While testing of drugs on patients in large trials is the only way to assess their clinical efficacy and toxicity, we dramatically lack resources to test the hundreds of drugs currently under development. Therefore the use of preclinical model systems has been intensively investigated as this approach enables response to hundreds of drugs to be tested in multiple cell lines in parallel. |
Lerman, Liran; Medeiros, Stéphane Fernandes; Veshchikov, Nikita; Meuter, Cédric; Bontempi, Gianluca; Markowitch, Olivier Semi-Supervised Template Attack Journal Article In: Lecture Notes in Computer Science, 7864 , pp. 184-199, 2013, (DOI: 10.1007/978-3-642-40026-1_12). @article{info:hdl:2013/147304, title = {Semi-Supervised Template Attack}, author = {Liran Lerman and Stéphane Fernandes Medeiros and Nikita Veshchikov and Cédric Meuter and Gianluca Bontempi and Olivier Markowitch}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/147304}, year = {2013}, date = {2013-01-01}, journal = {Lecture Notes in Computer Science}, volume = {7864}, pages = {184-199}, abstract = {Side channel attacks take advantage of information leakagesin cryptographic devices. Template attacks form a family of side channelattacks which is reputed to be extremely effective. This kind of attacksassumes that the attacker fully controls a cryptographic device before at-tacking a similar one. In this paper, we propose to relax this assumption bygeneralizing the template attack using a method based on a semi-supervisedlearning strategy. The effectiveness of our proposal is confirmed by softwaresimulations, by experiments on a 8-bit microcontroller and by a comparisonto a template attack as well as to two supervised machine learning methods.}, note = {DOI: 10.1007/978-3-642-40026-1_12}, keywords = {}, pubstate = {published}, tppubtype = {article} } Side channel attacks take advantage of information leakagesin cryptographic devices. Template attacks form a family of side channelattacks which is reputed to be extremely effective. This kind of attacksassumes that the attacker fully controls a cryptographic device before at-tacking a similar one. In this paper, we propose to relax this assumption bygeneralizing the template attack using a method based on a semi-supervisedlearning strategy. The effectiveness of our proposal is confirmed by softwaresimulations, by experiments on a 8-bit microcontroller and by a comparisonto a template attack as well as to two supervised machine learning methods. |
Jay, Nicolas De; Papillon-Cavanagh, Simon; Olsen, Catharina; El-Hachem, N; Bontempi, Gianluca; Haibe-Kains, Benjamin mRMRe: an R package for parallelized mRMR ensemble feature selection Journal Article In: Bioinformatics, 2013, (DOI: 10.1093/bioinformatics/btt383). @article{info:hdl:2013/155448, title = {mRMRe: an R package for parallelized mRMR ensemble feature selection}, author = {Nicolas De Jay and Simon Papillon-Cavanagh and Catharina Olsen and N El-Hachem and Gianluca Bontempi and Benjamin Haibe-Kains}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/155448/3/doi_140339.pdf}, year = {2013}, date = {2013-01-01}, journal = {Bioinformatics}, abstract = {Motivation: Feature selection is one of the main challenges in analyzing high-throughput genomic data. Minimum redundancy maximum relevance (mRMR) is a particularly fast feature selection method for finding a set of both relevant and complementary features. Here we describe the mRMRe R package, in which the mRMR technique is extended by using an ensemble approach in order to better explore the feature space and build more robust predictors. To deal with the computational complexity of the ensemble approach the main functions of the package are implemented and parallelized in C using the openMP API.Results: Our ensemble mRMR implementations outperform the classical mRMR approach in terms of prediction accuracy. They identify genes more relevant to the biological context and may lead to richer biological interpretations. The parallelized functions included in the package show significant gains in terms of run-time speed when compared to previously released packages.Availability: The R package mRMRe is available on CRAN and is provided open source under the Artistic-2.0 License. The code used to generate all the results reported in this application note is available from Supplementary File 1.Contact: bhaibeka@ircm.qc.caSupplementary Information: Supplementary information is available at Bioinformatics online.}, note = {DOI: 10.1093/bioinformatics/btt383}, keywords = {}, pubstate = {published}, tppubtype = {article} } Motivation: Feature selection is one of the main challenges in analyzing high-throughput genomic data. Minimum redundancy maximum relevance (mRMR) is a particularly fast feature selection method for finding a set of both relevant and complementary features. Here we describe the mRMRe R package, in which the mRMR technique is extended by using an ensemble approach in order to better explore the feature space and build more robust predictors. To deal with the computational complexity of the ensemble approach the main functions of the package are implemented and parallelized in C using the openMP API.Results: Our ensemble mRMR implementations outperform the classical mRMR approach in terms of prediction accuracy. They identify genes more relevant to the biological context and may lead to richer biological interpretations. The parallelized functions included in the package show significant gains in terms of run-time speed when compared to previously released packages.Availability: The R package mRMRe is available on CRAN and is provided open source under the Artistic-2.0 License. The code used to generate all the results reported in this application note is available from Supplementary File 1.Contact: bhaibeka@ircm.qc.caSupplementary Information: Supplementary information is available at Bioinformatics online. |
Bontempi, Gianluca; Taieb, Souhaib Ben; "e, Yann-A Machine learning strategies for time series forecasting Journal Article In: Lecture Notes in Business Information Processing, 138 LNBIP , pp. 62-77, 2013, (DOI: 10.1007/978-3-642-36318-4_3). @article{info:hdl:2013/167761, title = {Machine learning strategies for time series forecasting}, author = {Gianluca Bontempi and Souhaib Ben Taieb and Yann-A{"e}l Le Borgne}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/167761}, year = {2013}, date = {2013-01-01}, journal = {Lecture Notes in Business Information Processing}, volume = {138 LNBIP}, pages = {62-77}, abstract = {The increasing availability of large amounts of historical data and the need of performing accurate forecasting of future behavior in several scientific and applied domains demands the definition of robust and efficient techniques able to infer from observations the stochastic dependency between past and future. The forecasting domain has been influenced, from the 1960s on, by linear statistical methods such as ARIMA models. More recently, machine learning models have drawn attention and have established themselves as serious contenders to classical statistical models in the forecasting community. This chapter presents an overview of machine learning techniques in time series forecasting by focusing on three aspects: the formalization of one-step forecasting problems as supervised learning tasks, the discussion of local learning techniques as an effective tool for dealing with temporal data and the role of the forecasting strategy when we move from one-step to multiple-step forecasting. copyright 2013 Springer-Verlag.}, note = {DOI: 10.1007/978-3-642-36318-4_3}, keywords = {}, pubstate = {published}, tppubtype = {article} } The increasing availability of large amounts of historical data and the need of performing accurate forecasting of future behavior in several scientific and applied domains demands the definition of robust and efficient techniques able to infer from observations the stochastic dependency between past and future. The forecasting domain has been influenced, from the 1960s on, by linear statistical methods such as ARIMA models. More recently, machine learning models have drawn attention and have established themselves as serious contenders to classical statistical models in the forecasting community. This chapter presents an overview of machine learning techniques in time series forecasting by focusing on three aspects: the formalization of one-step forecasting problems as supervised learning tasks, the discussion of local learning techniques as an effective tool for dealing with temporal data and the role of the forecasting strategy when we move from one-step to multiple-step forecasting. copyright 2013 Springer-Verlag. |
Lopes, Miguel; Bontempi, Gianluca Experimental assessment of static and dynamic algorithms for gene regulation inference from time series expression data Journal Article In: Frontiers in Genetics, 4 (DEC), 2013, (DOI: 10.3389/fgene.2013.00303). @article{info:hdl:2013/168524, title = {Experimental assessment of static and dynamic algorithms for gene regulation inference from time series expression data}, author = {Miguel Lopes and Gianluca Bontempi}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/168524/3/doi_152154.pdf}, year = {2013}, date = {2013-01-01}, journal = {Frontiers in Genetics}, volume = {4}, number = {DEC}, abstract = {Accurate inference of causal gene regulatory networks from gene expression data is an open bioinformatics challenge. Gene interactions are dynamical processes and consequently we can expect that the effect of any regulation action occurs after a certain temporal lag. However such lag is unknown a priori and temporal aspects require specific inference algorithms. In this paper we aim to assess the impact of taking into consideration temporal aspects on the final accuracy of the inference procedure. In particular we will compare the accuracy of static algorithms, where no dynamic aspect is considered, to that of fixed lag and adaptive lag algorithms in three inference tasks from microarray expression data. Experimental results show that network inference algorithms that take dynamics into account perform consistently better than static ones, once the considered lags are properly chosen. However, no individual algorithm stands out in all three inference tasks, and the challenging nature of network inference tasks is evidenced, as a large number of the assessed algorithms does not perform better than random. copyright 2013 Lopes and Bontempi.}, note = {DOI: 10.3389/fgene.2013.00303}, keywords = {}, pubstate = {published}, tppubtype = {article} } Accurate inference of causal gene regulatory networks from gene expression data is an open bioinformatics challenge. Gene interactions are dynamical processes and consequently we can expect that the effect of any regulation action occurs after a certain temporal lag. However such lag is unknown a priori and temporal aspects require specific inference algorithms. In this paper we aim to assess the impact of taking into consideration temporal aspects on the final accuracy of the inference procedure. In particular we will compare the accuracy of static algorithms, where no dynamic aspect is considered, to that of fixed lag and adaptive lag algorithms in three inference tasks from microarray expression data. Experimental results show that network inference algorithms that take dynamics into account perform consistently better than static ones, once the considered lags are properly chosen. However, no individual algorithm stands out in all three inference tasks, and the challenging nature of network inference tasks is evidenced, as a large number of the assessed algorithms does not perform better than random. copyright 2013 Lopes and Bontempi. |
Pozzolo, Andrea Dal; Caelen, Olivier; Waterschoot, Serge; Bontempi, Gianluca Racing for unbalanced methods selection Journal Article In: Lecture notes in computer science, 8206 LNCS , pp. 24-31, 2013, (DOI: 10.1007/978-3-642-41278-3_4). @article{info:hdl:2013/168898, title = {Racing for unbalanced methods selection}, author = {Andrea Dal Pozzolo and Olivier Caelen and Serge Waterschoot and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/168898}, year = {2013}, date = {2013-01-01}, journal = {Lecture notes in computer science}, volume = {8206 LNCS}, pages = {24-31}, abstract = {State-of-the-art classification algorithms suffer when the data is skewed towards one class. This led to the development of a number of techniques to cope with unbalanced data. However, as confirmed by our experimental comparison, no technique appears to work consistently better in all conditions. We propose to use a racing method to select adaptively the most appropriate strategy for a given unbalanced task. The results show that racing is able to adapt the choice of the strategy to the specific nature of the unbalanced problem and to select rapidly the most appropriate strategy without compromising the accuracy. copyright 2013 Springer-Verlag.}, note = {DOI: 10.1007/978-3-642-41278-3_4}, keywords = {}, pubstate = {published}, tppubtype = {article} } State-of-the-art classification algorithms suffer when the data is skewed towards one class. This led to the development of a number of techniques to cope with unbalanced data. However, as confirmed by our experimental comparison, no technique appears to work consistently better in all conditions. We propose to use a racing method to select adaptively the most appropriate strategy for a given unbalanced task. The results show that racing is able to adapt the choice of the strategy to the specific nature of the unbalanced problem and to select rapidly the most appropriate strategy without compromising the accuracy. copyright 2013 Springer-Verlag. |
Lerman, Liran; Markowitch, Olivier; Bontempi, Gianluca; Taieb, Souhaib Ben A time series approach for profiling attack Journal Article In: Lecture notes in computer science, 8204 , pp. 75-94, 2013, (DOI: 10.1007/978-3-642-41224-0_7). @article{info:hdl:2013/183221, title = {A time series approach for profiling attack}, author = {Liran Lerman and Olivier Markowitch and Gianluca Bontempi and Souhaib Ben Taieb}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/183221}, year = {2013}, date = {2013-01-01}, journal = {Lecture notes in computer science}, volume = {8204}, pages = {75-94}, abstract = {The goal of a profiling attack is to challenge the security of a cryptographic device in the worst case scenario. Though template attack is reputed as the strongest power analysis attack, they effectiveness is strongly dependent on the validity of the Gaussian assumption. This led recently to the appearance of nonparametric approaches, often based on machine learning strategies. Though these approaches outperform template attack, they tend to neglect the potential source of information available in the temporal dependencies between power values. In this paper, we propose an original multi-class profiling attack that takes into account the temporal dependence of power traces. The experimental study shows that the time series analysis approach is competitive and often better than static classification alternatives. copyright 2013 Springer-Verlag.}, note = {DOI: 10.1007/978-3-642-41224-0_7}, keywords = {}, pubstate = {published}, tppubtype = {article} } The goal of a profiling attack is to challenge the security of a cryptographic device in the worst case scenario. Though template attack is reputed as the strongest power analysis attack, they effectiveness is strongly dependent on the validity of the Gaussian assumption. This led recently to the appearance of nonparametric approaches, often based on machine learning strategies. Though these approaches outperform template attack, they tend to neglect the potential source of information available in the temporal dependencies between power values. In this paper, we propose an original multi-class profiling attack that takes into account the temporal dependence of power traces. The experimental study shows that the time series analysis approach is competitive and often better than static classification alternatives. copyright 2013 Springer-Verlag. |
Jan, Serge Van Sint; Wermenbol, Vanessa; Bogaert, Patrick Van; Desloovere, Kaat; Degelaen, Marc; Dan, Bernard; Salvia, P; Bonnechere, Bruno; "e, Yann-A; Bontempi, Gianluca; Vansummeren, Stijn; Sholukha, Victor; Moiseev, Fedor; Rooze, Marcel In: Médecine, 29 (5), pp. 529-536, 2013, (Language of publication: na). @article{info:hdl:2013/185849, title = {Recherche intégrée relative `a l'appareil musculosquelettique : application `a la prise en charge clinique de l'infirmité motrice cérébrale (IMC) -- le projet ICT4Rehab}, author = {Serge Van Sint Jan and Vanessa Wermenbol and Patrick Van Bogaert and Kaat Desloovere and Marc Degelaen and Bernard Dan and P Salvia and Bruno Bonnechere and Yann-A{"e}l Leborgne and Gianluca Bontempi and Stijn Vansummeren and Victor Sholukha and Fedor Moiseev and Marcel Rooze}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/185849}, year = {2013}, date = {2013-01-01}, journal = {Médecine}, volume = {29}, number = {5}, pages = {529-536}, note = {Language of publication: na}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Deplus, Rachel; Delatte, Benjamin; Schwinn, Marie K; Defrance, Matthieu; Méndez, Jacqui; Murphy, Nancy; Dawson, Mark A; Volkmar, Michael; Putmans, Pascale; Calonne, Emilie; Shih, Alan H; Levine, Ross L; Bernard, Olivier; Mercher, Thomas; Solary, Eric; Urh, Marjeta; Daniels, Danette; c c, Fran TET2 and TET3 regulate GlcNAcylation and H3K4 methylation through OGT and SET1/COMPASS. Journal Article In: EMBO journal, 32 (5), pp. 645-655, 2013, (DOI: 10.1038/emboj.2012.357). @article{info:hdl:2013/140580, title = {TET2 and TET3 regulate GlcNAcylation and H3K4 methylation through OGT and SET1/COMPASS.}, author = {Rachel Deplus and Benjamin Delatte and Marie K Schwinn and Matthieu Defrance and Jacqui Méndez and Nancy Murphy and Mark A Dawson and Michael Volkmar and Pascale Putmans and Emilie Calonne and Alan H Shih and Ross L Levine and Olivier Bernard and Thomas Mercher and Eric Solary and Marjeta Urh and Danette Daniels and Fran{c c}ois Fuks}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/140580/4/140580.pdf}, year = {2013}, date = {2013-01-01}, journal = {EMBO journal}, volume = {32}, number = {5}, pages = {645-655}, abstract = {TET proteins convert 5-methylcytosine to 5-hydroxymethylcytosine, an emerging dynamic epigenetic state of DNA that can influence transcription. Evidence has linked TET1 function to epigenetic repression complexes, yet mechanistic information, especially for the TET2 and TET3 proteins, remains limited. Here, we show a direct interaction of TET2 and TET3 with O-GlcNAc transferase (OGT). OGT does not appear to influence hmC activity, rather TET2 and TET3 promote OGT activity. TET2/3-OGT co-localize on chromatin at active promoters enriched for H3K4me3 and reduction of either TET2/3 or OGT activity results in a direct decrease in H3K4me3 and concomitant decreased transcription. Further, we show that Host Cell Factor 1 (HCF1), a component of the H3K4 methyltransferase SET1/COMPASS complex, is a specific GlcNAcylation target of TET2/3-OGT, and modification of HCF1 is important for the integrity of SET1/COMPASS. Additionally, we find both TET proteins and OGT activity promote binding of the SET1/COMPASS H3K4 methyltransferase, SETD1A, to chromatin. Finally, studies in Tet2 knockout mouse bone marrow tissue extend and support the data as decreases are observed of global GlcNAcylation and also of H3K4me3, notably at several key regulators of haematopoiesis. Together, our results unveil a step-wise model, involving TET-OGT interactions, promotion of GlcNAcylation, and influence on H3K4me3 via SET1/COMPASS, highlighting a novel means by which TETs may induce transcriptional activation.}, note = {DOI: 10.1038/emboj.2012.357}, keywords = {}, pubstate = {published}, tppubtype = {article} } TET proteins convert 5-methylcytosine to 5-hydroxymethylcytosine, an emerging dynamic epigenetic state of DNA that can influence transcription. Evidence has linked TET1 function to epigenetic repression complexes, yet mechanistic information, especially for the TET2 and TET3 proteins, remains limited. Here, we show a direct interaction of TET2 and TET3 with O-GlcNAc transferase (OGT). OGT does not appear to influence hmC activity, rather TET2 and TET3 promote OGT activity. TET2/3-OGT co-localize on chromatin at active promoters enriched for H3K4me3 and reduction of either TET2/3 or OGT activity results in a direct decrease in H3K4me3 and concomitant decreased transcription. Further, we show that Host Cell Factor 1 (HCF1), a component of the H3K4 methyltransferase SET1/COMPASS complex, is a specific GlcNAcylation target of TET2/3-OGT, and modification of HCF1 is important for the integrity of SET1/COMPASS. Additionally, we find both TET proteins and OGT activity promote binding of the SET1/COMPASS H3K4 methyltransferase, SETD1A, to chromatin. Finally, studies in Tet2 knockout mouse bone marrow tissue extend and support the data as decreases are observed of global GlcNAcylation and also of H3K4me3, notably at several key regulators of haematopoiesis. Together, our results unveil a step-wise model, involving TET-OGT interactions, promotion of GlcNAcylation, and influence on H3K4me3 via SET1/COMPASS, highlighting a novel means by which TETs may induce transcriptional activation. |
Han, The Anh T A H; 'i, Lu; Santos, Francisco C; Lenaerts, Tom Why is it so hard to say sorry? Journal Article In: BNAIC, pp. 322-323, 2013, (Language of publication: en). @article{info:hdl:2013/297043, title = {Why is it so hard to say sorry?}, author = {The Anh T A H Han and Lu{'i}s Marcelo Pereira and Francisco C Santos and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/297043/3/6744-30548-1-PB.pdf}, year = {2013}, date = {2013-01-01}, journal = {BNAIC}, pages = {322-323}, abstract = {When making a mistake, individuals are willing to apologize to secure further cooperation, even if the apology is costly. Similarly, individuals arrange commitments to guarantee that an action such as a cooperative one is in the others' best interest, and thus will be carried out to avoid eventual penalties for commitment failure. Hence, both apology and commitment should go side by side in behavioral evolution. Here we discuss our work published in [6], wherein we study the relevance of a combination of those two strategies in the context of the iterated Prisoner's Dilemma (IPD). We show that apologizing acts are rare in non-committed interactions, especially whenever cooperation is very costly, and that arranging prior commitments can considerably increase the frequency of such behavior. In addition, we show that with or without commitments, apology resolves conflicts only if it is sincere, i.e. costly enough. Most interestingly, our model predicts that individuals tend to use much costlier apology in committed relationships than otherwise, because it helps better identify free-riders such as fake committers.}, note = {Language of publication: en}, keywords = {}, pubstate = {published}, tppubtype = {article} } When making a mistake, individuals are willing to apologize to secure further cooperation, even if the apology is costly. Similarly, individuals arrange commitments to guarantee that an action such as a cooperative one is in the others' best interest, and thus will be carried out to avoid eventual penalties for commitment failure. Hence, both apology and commitment should go side by side in behavioral evolution. Here we discuss our work published in [6], wherein we study the relevance of a combination of those two strategies in the context of the iterated Prisoner's Dilemma (IPD). We show that apologizing acts are rare in non-committed interactions, especially whenever cooperation is very costly, and that arranging prior commitments can considerably increase the frequency of such behavior. In addition, we show that with or without commitments, apology resolves conflicts only if it is sincere, i.e. costly enough. Most interestingly, our model predicts that individuals tend to use much costlier apology in committed relationships than otherwise, because it helps better identify free-riders such as fake committers. |
2012 |
Lopes, Miguel; Meyer, Patrick E; Bontempi, Gianluca Estimation of temporal lags for the inference of gene regulatory networks from time series (inproceedings) Author Inproceedings In: In proceedings of BENELEARN'12, 2012, (Language of publication: na). @inproceedings{info:hdl:2013/139466, title = {Estimation of temporal lags for the inference of gene regulatory networks from time series (inproceedings) Author}, author = {Miguel Lopes and Patrick E Meyer and Gianluca Bontempi}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/139466}, year = {2012}, date = {2012-01-01}, booktitle = {In proceedings of BENELEARN'12}, note = {Language of publication: na}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Jan, Serge Van Sint; Bono, De B; Sholukha, Victor; Moiseev, Fedor; Vansummeren, Stijn; "e, Yann-A; Bontempi, Gianluca; Bonnechere, Bruno; Rooze, Marcel seedEP2 : Integrated modeling of the musculoskeletal system. Inproceedings In: VPH-NOE, 2012, (Conference: (2012: London, UK)). @inproceedings{info:hdl:2013/151871, title = {seedEP2 : Integrated modeling of the musculoskeletal system.}, author = {Serge Van Sint Jan and B De Bono and Victor Sholukha and Fedor Moiseev and Stijn Vansummeren and Yann-A{"e}l Le Borgne and Gianluca Bontempi and Bruno Bonnechere and Marcel Rooze}, url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/151871}, year = {2012}, date = {2012-01-01}, booktitle = {VPH-NOE}, note = {Conference: (2012: London, UK)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Cilia, Elisa; Vuister, Geerten W; Lenaerts, Tom Accurate prediction of the dynamical changes within the second PDZ domain of PTP1e. Journal Article In: PLoS computational biology, 8 (11), pp. e1002794, 2012, (DOI: 10.1371/journal.pcbi.1002794). @article{info:hdl:2013/138318, title = {Accurate prediction of the dynamical changes within the second PDZ domain of PTP1e.}, author = {Elisa Cilia and Geerten W Vuister and Tom Lenaerts}, url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/138318/4/doi_121267.pdf}, year = {2012}, date = {2012-01-01}, journal = {PLoS computational biology}, volume = {8}, number = {11}, pages = {e1002794}, abstract = {Experimental NMR relaxation studies have shown that peptide binding induces dynamical changes at the side-chain level throughout the second PDZ domain of PTP1e, identifying as such the collection of residues involved in long-range communication. Even though different computational approaches have identified subsets of residues that were qualitatively comparable, no quantitative analysis of the accuracy of these predictions was thus far determined. Here, we show that our information theoretical method produces quantitatively better results with respect to the experimental data than some of these earlier methods. Moreover, it provides a global network perspective on the effect experienced by the different residues involved in the process. We also show that these predictions are consistent within both the human and mouse variants of this domain. Together, these results improve the understanding of intra-protein communication and allostery in PDZ domains, underlining at the same time the necessity of producing similar data sets for further validation of thses kinds of methods.}, note = {DOI: 10.1371/journal.pcbi.1002794}, keywords = {}, pubstate = {published}, tppubtype = {article} } Experimental NMR relaxation studies have shown that peptide binding induces dynamical changes at the side-chain level througho |