2024
Lebichot, Bertrand; Siblini, Wissam; Paldino, Gian Marco; Borgne, Yann-Aël Le; Oblé, Frédéric; Bontempi, Gianluca
Assessment of catastrophic forgetting in continual credit card fraud detection Journal Article
In: Expert systems with applications, vol. 249, 2024, (DOI: 10.1016/j.eswa.2024.123445).
@article{info:hdl:2013/370795b,
title = {Assessment of catastrophic forgetting in continual credit card fraud detection},
author = {Bertrand Lebichot and Wissam Siblini and Gian Marco Paldino and Yann-Aël Le Borgne and Frédéric Oblé and Gianluca Bontempi},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/370795/3/preproofs-main.pdf},
year = {2024},
date = {2024-01-01},
journal = {Expert systems with applications},
volume = {249},
abstract = {The volume of e-commerce continues to increase year after year. Buying goods on the internet is easy and practical, and took a huge boost during the lockdowns of the Covid crisis. However, this is also an open window for fraudsters and the corresponding financial loss costs billions of dollars. In this paper, we study e-commerce credit card fraud detection, in collaboration with our industrial partner, Worldline. Transactional companies are more and more dependent on machine learning models such as deep learning anomaly detection models, as part of real-world fraud detection systems (FDS). We focus on continual learning to find the best model with respect to two objectives: to maximize the accuracy and to minimize the catastrophic forgetting phenomenon. For the latter, we proposed an evaluation procedure to quantify the forgetting in data streams with delayed feedback: the plasticity/stability visualization matrix. We also investigated six strategies and 13 methods on a real-size case study including five months of e-commerce credit card transactions. Finally, we discuss how the trade-off between plasticity and stability is set, in practice, in the case of FDS.},
note = {DOI: 10.1016/j.eswa.2024.123445},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Molinghen, Yannick; Avalos, Raphaël; Achter, Mark Van; Nowé, Ann; Lenaerts, Tom
Laser Learning Environment: A new environment for coordination-critical multi-agent tasks Proceedings Article
In: Oliehoek, Frans F. A.; Manon, Kok; Verwer, Sicco (Ed.): Artificial Intelligence and Machine Learning: Revised Selected Papers, Springer Science and Business Media Deutschland GmbH, 2024, (Conference: Benelux Conference Ai conference, BNAIC(35: 8-10/11/2023: TU Delft)).
@inproceedings{info:hdl:2013/370546,
title = {Laser Learning Environment: A new environment for coordination-critical multi-agent tasks},
author = {Yannick Molinghen and Raphaël Avalos and Mark Van Achter and Ann Nowé and Tom Lenaerts},
editor = {Frans F. A. Oliehoek and Kok Manon and Sicco Verwer},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/370546/4/2404.03596v1.pdf},
year = {2024},
date = {2024-01-01},
booktitle = {Artificial Intelligence and Machine Learning: Revised Selected Papers},
publisher = {Springer Science and Business Media Deutschland GmbH},
series = {Communications in Computer and Information Science},
abstract = {We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment where coordination is key. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics). The challenge of such problems lies in the difficulty of escaping state space bottlenecks caused by interdependence steps since escaping those bottlenecks is not rewarded. We test multiple state-of-the-art value-based MARL algorithms against LLE and show that they consistently fail at the collaborative task because of their inability to escape state space bottlenecks, even though they successfully achieve perfect coordination. We show that Q-learning extensions such as prioritised experience replay and n-steps return hinder exploration in environments with zero-incentive dynamics, and find that intrinsic curiosity with random network distillation is not sufficient to escape those bottlenecks. We demonstrate the need for novel methods to solve this problem and the relevance of LLE as cooperative MARL benchmark.},
note = {Conference: Benelux Conference Ai conference, BNAIC(35: 8-10/11/2023: TU Delft)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Leung, Chin Wing; Lenaerts, Tom; Turrini, Paolo
To Promote Full Cooperation in Social Dilemmas, Agents Need to Unlearn Loyalty Proceedings Article
In: Larson, Kate (Ed.): Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 111-119, International Joint Conferences on Artificial Intelligence (IJCAI) Organization, 2024, (Conference: International Joint Conference on Artificial Intelligence(33: 3/8-9/8/2024: Jeju. Korea)).
@inproceedings{info:hdl:2013/385907,
title = {To Promote Full Cooperation in Social Dilemmas, Agents Need to Unlearn Loyalty},
author = {Chin Wing Leung and Tom Lenaerts and Paolo Turrini},
editor = {Kate Larson},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/385907/3/0013.pdf},
year = {2024},
date = {2024-01-01},
booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence},
pages = {111-119},
publisher = {International Joint Conferences on Artificial Intelligence (IJCAI) Organization},
abstract = {If given the choice, what strategy should agents use to switch partners in strategic social interactions? While many analyses have been performed on specific switching heuristics, showing how and when these lead to more cooperation, no insights have been provided into which rule will actually be learnt by agents when given the freedom to do so. Starting from a baseline model that has demonstrated the potential of rewiring for cooperation, we provide answers to this question over the full spectrum of social dilemmas. Multi-agent Q-learning with Boltzmann exploration is used to learn when to sever or maintain an association. In both the Prisoner's Dilemma and the Stag Hunt games we observe that the Out-for-Tat rewiring rule, breaking ties with other agents choosing socially undesirable actions, becomes dominant, confirming at the same time that cooperation flourishes when rewiring is fast enough relative to imitation. Nonetheless, in the transitory region before full cooperation, a Stay strategy, keeping a connection at all costs, remains present, which shows that loyalty needs to be overcome for full cooperation to emerge. In conclusion, individuals learn cooperation-promoting rewiring rules but need to overcome a kind of loyalty to achieve full cooperation in the full spectrum of social dilemmas.},
note = {Conference: International Joint Conference on Artificial Intelligence(33: 3/8-9/8/2024: Jeju. Korea)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jansen, Maarten; Claeskens, G.
Nonparametric estimation Book Chapter
In: 2024, (Language of publication: fr).
@inbook{info:hdl:2013/359775b,
title = {Nonparametric estimation},
author = {Maarten Jansen and G. Claeskens},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/359775/3/jansen23nonparametricencycl.pdf},
year = {2024},
date = {2024-01-01},
note = {Language of publication: fr},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Jansen, Maarten; Claeskens, Gerda
The Cramér-Rao Lower Bound Book Chapter
In: 2024, (Language of publication: fr).
@inbook{info:hdl:2013/359778b,
title = {The Cramér-Rao Lower Bound},
author = {Maarten Jansen and Gerda Claeskens},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/359778/3/jansen23cramerraoencycl.pdf},
year = {2024},
date = {2024-01-01},
note = {Language of publication: fr},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Bhattacharya, Shreya; Lefèvre, Laure; Chatzistergos, T; Hayakawa, Hisashi; Jansen, Maarten
RudolfWolf to AlfredWolfer: The Transfer of the Reference Observer in the International Sunspot Number Series (1876–1893) Journal Article
In: Solar physics, vol. 299, 2024, (Language of publication: fr).
@article{info:hdl:2013/372844b,
title = {RudolfWolf to AlfredWolfer: The Transfer of the Reference Observer in the International Sunspot Number Series (1876–1893)},
author = {Shreya Bhattacharya and Laure Lefèvre and T Chatzistergos and Hisashi Hayakawa and Maarten Jansen},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/372844/3/PreprintBhattacharya202404.pdf},
year = {2024},
date = {2024-01-01},
journal = {Solar physics},
volume = {299},
note = {Language of publication: fr},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Jansen, Maarten
Information criteria for structured parameter selection in high dimensional tree and graph models Journal Article
In: Digital signal processing, vol. 148, 2024, (Language of publication: fr).
@article{info:hdl:2013/372845b,
title = {Information criteria for structured parameter selection in high dimensional tree and graph models},
author = {Maarten Jansen},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/372845/3/jansen24structuredpreprint.pdf},
year = {2024},
date = {2024-01-01},
journal = {Digital signal processing},
volume = {148},
note = {Language of publication: fr},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2023
Tubella, Andrea Aler; Mollo, Dimitri Coelho; Lindström, Adam Dahlgren; Devinney, Hannah; Dignum, Virginia; Ericson, Petter; Jonsson, Ana; Kampik, Timotheus; Lenaerts, Tom; Mendez, Julian Alfredo; Nieves, Juan Carlos
ACROCPoLis: A Descriptive Framework for Making Sense of Fairness Proceedings Article
In: Proceedings of the 6th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023, pp. 1014-1025, Association for Computing Machinery, 2023, (Conference: 6th ACM Conference on Fairness, Accountability, and Transparency(6: 12/6/2023-15/06/2023: Chicago)).
@inproceedings{info:hdl:2013/366626b,
title = {ACROCPoLis: A Descriptive Framework for Making Sense of Fairness},
author = {Andrea Aler Tubella and Dimitri Coelho Mollo and Adam Dahlgren Lindström and Hannah Devinney and Virginia Dignum and Petter Ericson and Ana Jonsson and Timotheus Kampik and Tom Lenaerts and Julian Alfredo Mendez and Juan Carlos Nieves},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366626/5/doi_350270.pdf},
year = {2023},
date = {2023-01-01},
booktitle = {Proceedings of the 6th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023},
pages = {1014-1025},
publisher = {Association for Computing Machinery},
abstract = {Fairness is central to the ethical and responsible development and use of AI systems, with a large number of frameworks and formal notions of algorithmic fairness being available. However, many of the fairness solutions proposed revolve around technical considerations and not the needs of and consequences for the most impacted communities. We therefore want to take the focus away from definitions and allow for the inclusion of societal and relational aspects to represent how the effects of AI systems impact and are experienced by individuals and social groups. In this paper, we do this by means of proposing the ACROCPoLis framework to represent allocation processes with a modeling emphasis on fairness aspects. The framework provides a shared vocabulary in which the factors relevant to fairness assessments for different situations and procedures are made explicit, as well as their interrelationships. This enables us to compare analogous situations, to highlight the differences in dissimilar situations, and to capture differing interpretations of the same situation by different stakeholders.},
note = {Conference: 6th ACM Conference on Fairness, Accountability, and Transparency(6: 12/6/2023-15/06/2023: Chicago)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nachtegael, Charlotte; Stefani, Jacopo De; Lenaerts, Tom
ALAMBIC: Active Learning Automation with Methods to Battle Inefficient Curation Proceedings Article
In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pp. 117–127, Association for Computational Linguistics, 2023, (Conference: European Chapter of the Association for Computational Linguistics(17: 2 May 2023 to 4 May 2023: Dubrovnik, Croatia)).
@inproceedings{info:hdl:2013/359290b,
title = {ALAMBIC: Active Learning Automation with Methods to Battle Inefficient Curation},
author = {Charlotte Nachtegael and Jacopo De Stefani and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/359290/3/2023.eacl-demo.14.pdf},
year = {2023},
date = {2023-01-01},
booktitle = {Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations},
pages = {117–127},
publisher = {Association for Computational Linguistics},
abstract = {In this paper, we present ALAMBIC, an open-source dockerized web-based platform for annotating text data through active learning for classification task. Active learning is known to reduce the need of labelling, a time-consuming task, by selecting the most informative instances among the unlabelled instances, reaching an optimal accuracy faster than by just randomly labelling data. ALAMBIC integrates all the steps from data import to customization of the (active) learning process and annotation of the data, with indications of the progress of the trained model that can be downloaded and used in downstream tasks. Its architecture also allows the easy integration of other types of model, features and active learning strategies.The code is available on https://github.com/Trusted-AI-Labs/ALAMBIC and a video demonstration is available on https://youtu.be/4oh8UADfEmY.},
note = {Conference: European Chapter of the Association for Computational Linguistics(17: 2 May 2023 to 4 May 2023: Dubrovnik, Croatia)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making Proceedings Article
In: Proceedings of the 40th International Conference on Machine Learning: ICML’23, pp. 79-90, PMLR, 2023, (Conference: 40th International Conference on Machine Learning(Honolulu Hawaii USA)).
@inproceedings{info:hdl:2013/364331b,
title = {Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/364331/1/bibtex_347975.pdf},
year = {2023},
date = {2023-01-01},
booktitle = {Proceedings of the 40th International Conference on Machine Learning: ICML'23},
pages = {79-90},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
abstract = {Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work, we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm — expertise trees — that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.},
note = {Conference: 40th International Conference on Machine Learning(Honolulu Hawaii USA)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Versbraegen, Nassim; Gravel, Barbara; Nachtegael, Charlotte; Renaux, Alexandre; Verkinderen, Emma; Nowé, Ann; Lenaerts, Tom; Papadimitriou, Sofia
Faster and more accurate pathogenic combination predictions with VarCoPP2.0 Miscellaneous
2023, (Conference: Benelux AI Conference (BNAIC) / Benelux Machine Learning Conference (Benelearn)(8-10/11/2023: Delft, les Pays-Bas)).
@misc{info:hdl:2013/366750,
title = {Faster and more accurate pathogenic combination predictions with VarCoPP2.0},
author = {Nassim Versbraegen and Barbara Gravel and Charlotte Nachtegael and Alexandre Renaux and Emma Verkinderen and Ann Nowé and Tom Lenaerts and Sofia Papadimitriou},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366750/3/VarCoPP2.0_BNAIC23_abstract_nversbra.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Benelux AI Conference (BNAIC) / Benelux Machine Learning Conference (Benelearn)(8-10/11/2023: Delft, les Pays-Bas)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Cheron, Julian; Beccari, Leonardo; Hague, Perrine; Icick, Romain; Despontin, Chloé; Carusone, Teresa; Defrance, Matthieu; Bhogaraju, Sagar; Martin-Garcia, Elena; Capellan, Roberto; Maldonado, Rafael; Vorspan, Florence; Bonnefont, Jérôme; d’Exaerde, Alban
USP7/Maged1-mediated H2A monoubiquitination in the paraventricular thalamus: an epigenetic mechanism involved in cocaine use disorder Journal Article
In: Nature communications, vol. 14, no. 1, 2023, (DOI: 10.1038/s41467-023-44120-2).
@article{info:hdl:2013/366499,
title = {USP7/Maged1-mediated H2A monoubiquitination in the paraventricular thalamus: an epigenetic mechanism involved in cocaine use disorder},
author = {Julian Cheron and Leonardo Beccari and Perrine Hague and Romain Icick and Chloé Despontin and Teresa Carusone and Matthieu Defrance and Sagar Bhogaraju and Elena Martin-Garcia and Roberto Capellan and Rafael Maldonado and Florence Vorspan and Jérôme Bonnefont and Alban d'Exaerde},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366499/3/s41467-023-44120-2.pdf},
year = {2023},
date = {2023-01-01},
journal = {Nature communications},
volume = {14},
number = {1},
abstract = {Abstract The risk of developing drug addiction is strongly influenced by the epigenetic landscape and chromatin remodeling. While histone modifications such as methylation and acetylation have been studied in the ventral tegmental area and nucleus accumbens (NAc), the role of H2A monoubiquitination remains unknown. Our investigations, initially focused on the scaffold protein melanoma-associated antigen D1 (Maged1), reveal that H2A monoubiquitination in the paraventricular thalamus (PVT) significantly contributes to cocaine-adaptive behaviors and transcriptional repression induced by cocaine. Chronic cocaine use increases H2A monoubiquitination, regulated by Maged1 and its partner USP7. Accordingly, Maged1 specific inactivation in thalamic Vglut2 neurons, or USP7 inhibition, blocks cocaine-evoked H2A monoubiquitination and cocaine locomotor sensitization. Additionally, genetic variations in MAGED1 and USP7 are linked to altered susceptibility to cocaine addiction and cocaine-associated symptoms in humans. These findings unveil an epigenetic modification in a non-canonical reward pathway of the brain and a potent marker of epigenetic risk factors for drug addiction in humans.},
note = {DOI: 10.1038/s41467-023-44120-2},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowé, Ann
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making Miscellaneous
2023, (Conference: Benelux AI Conference (BNAIC) and the Benelux Machine learning Conference (Benelearn)(8-10/11/2023: Delft)).
@misc{info:hdl:2013/366669,
title = {Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowé},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366669/3/BNAIC2023ExpertiseTrees.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Benelux AI Conference (BNAIC) and the Benelux Machine learning Conference (Benelearn)(8-10/11/2023: Delft)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Piron, Anthony; Szymczak, Florian; Papadopoulou, Theodora; Alvelos, Maria Inês; Defrance, Matthieu; Lenaerts, Tom; Eizirik, Décio L; Cnop, Miriam
RedRibbon: A new rank–rank hypergeometric overlap for gene and transcript expression signatures Journal Article
In: Life science alliance, vol. 7, no. 2, pp. e202302203, 2023, (DOI: 10.26508/lsa.202302203).
@article{info:hdl:2013/366009,
title = {RedRibbon: A new rank–rank hypergeometric overlap for gene and transcript expression signatures},
author = {Anthony Piron and Florian Szymczak and Theodora Papadopoulou and Maria Inês Alvelos and Matthieu Defrance and Tom Lenaerts and Décio L Eizirik and Miriam Cnop},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366009/1/doi_349653.pdf},
year = {2023},
date = {2023-01-01},
journal = {Life science alliance},
volume = {7},
number = {2},
pages = {e202302203},
abstract = {High-throughput omics technologies have generated a wealth of large protein, gene, and transcript datasets that have exacerbated the need for new methods to analyse and compare big datasets. Rank–rank hypergeometric overlap is an important threshold-free method to combine and visualize two ranked lists of P -values or fold-changes, usually from differential gene expression analyses. Here, we introduce a new rank–rank hypergeometric overlap-based method aimed at gene level and alternative splicing analyses at transcript or exon level, hitherto unreachable as transcript numbers are an order of magnitude larger than gene numbers. We tested the tool on synthetic and real datasets at gene and transcript levels to detect correlation and anticorrelation patterns and found it to be fast and accurate, even on very large datasets thanks to an evolutionary algorithm-based minimal P -value search. The tool comes with a ready-to-use permutation scheme allowing the computation of adjusted P -values at low time cost. The package compatibility mode is a drop-in replacement to previous packages. RedRibbon holds the promise to accurately extricate detailed information from large comparative analyses.},
note = {DOI: 10.26508/lsa.202302203},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Terrucha, Ines; Domingos, Elias Fernandez; Simoens, Pieter; Lenaerts, Tom
To avoid collective disasters, it is better to commit to a flawed AI than to commit the errors ourselves Miscellaneous
2023, (Conference: Evolutionary Dynamics in social, cooperative and hybrid AI workshop(Cracovie)).
@misc{info:hdl:2013/366664,
title = {To avoid collective disasters, it is better to commit to a flawed AI than to commit the errors ourselves},
author = {Ines Terrucha and Elias Fernandez Domingos and Pieter Simoens and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366664/3/8388.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Evolutionary Dynamics in social, cooperative and hybrid AI workshop(Cracovie)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Giuili, Edoardo; Grolaux, Robin; Macedo, Catarina Z N M CZNM; Desmyter, Laurence; Pichon, Bruno; Neuens, Sebastian; Vilain, Catheline; Olsen, Catharina; Dooren, Sonia Van; Smits, Guillaume; Defrance, Matthieu
Comprehensive evaluation of the implementation of episignatures for diagnosis of neurodevelopmental disorders (NDDs). Journal Article
In: Human genetics, 2023, (DOI: 10.1007/s00439-023-02609-2).
@article{info:hdl:2013/364749,
title = {Comprehensive evaluation of the implementation of episignatures for diagnosis of neurodevelopmental disorders (NDDs).},
author = {Edoardo Giuili and Robin Grolaux and Catarina Z N M CZNM Macedo and Laurence Desmyter and Bruno Pichon and Sebastian Neuens and Catheline Vilain and Catharina Olsen and Sonia Van Dooren and Guillaume Smits and Matthieu Defrance},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/364749},
year = {2023},
date = {2023-01-01},
journal = {Human genetics},
abstract = {Episignatures are popular tools for the diagnosis of rare neurodevelopmental disorders. They are commonly based on a set of differentially methylated CpGs used in combination with a support vector machine model. DNA methylation (DNAm) data often include missing values due to changes in data generation technology and batch effects. While many normalization methods exist for DNAm data, their impact on episignature performance have never been assessed. In addition, technologies to quantify DNAm evolve quickly and this may lead to poor transposition of existing episignatures generated on deprecated array versions to new ones. Indeed, probe removal between array versions, technologies or during preprocessing leads to missing values. Thus, the effect of missing data on episignature performance must also be carefully evaluated and addressed through imputation or an innovative approach to episignatures design. In this paper, we used data from patients suffering from Kabuki and Sotos syndrome to evaluate the influence of normalization methods, classification models and missing data on the prediction performances of two existing episignatures. We compare how six popular normalization methods for methylarray data affect episignature classification performances in Kabuki and Sotos syndromes and provide best practice suggestions when building new episignatures. In this setting, we show that Illumina, Noob or Funnorm normalization methods achieved higher classification performances on the testing sets compared to Quantile, Raw and Swan normalization methods. We further show that penalized logistic regression and support vector machines perform best in the classification of Kabuki and Sotos syndrome patients. Then, we describe a new paradigm to build episignatures based on the detection of differentially methylated regions (DMRs) and evaluate their performance compared to classical differentially methylated cytosines (DMCs)-based episignatures in the presence of missing data. We show that the performance of classical DMC-based episignatures suffers from the presence of missing data more than the DMR-based approach. We present a comprehensive evaluation of how the normalization of DNA methylation data affects episignature performance, using three popular classification models. We further evaluate how missing data affect those models' predictions. Finally, we propose a novel methodology to develop episignatures based on differentially methylated regions identification and show how this method slightly outperforms classical episignatures in the presence of missing data.},
note = {DOI: 10.1007/s00439-023-02609-2},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Terrucha, Ines; Domingos, Elias Fernandez; Suchon, Remi; Santos, Francisco C; Simoens, Pieter; Lenaerts, Tom
Delegation to autonomous agents : a key to overcome past failure and focus on the collective target ahead Miscellaneous
2023, (Conference: the 9th International Conference on Computational Social Science (IC2S2)(17-19/07/2023: Copenhagen)).
@misc{info:hdl:2013/366663,
title = {Delegation to autonomous agents : a key to overcome past failure and focus on the collective target ahead},
author = {Ines Terrucha and Elias Fernandez Domingos and Remi Suchon and Francisco C Santos and Pieter Simoens and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366663/3/8352.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: the 9th International Conference on Computational Social Science (IC2S2)(17-19/07/2023: Copenhagen)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Araujo, Natalia Souza; Perez, Rémy; Willot, Quentin; Defrance, Matthieu; Aron, Serge
Facing lethal temperatures: Heat-shock response in desert and temperate ants. Journal Article
In: Ecology and evolution, vol. 13, no. 9, pp. e10438, 2023, (DOI: 10.1002/ece3.10438).
@article{info:hdl:2013/366010,
title = {Facing lethal temperatures: Heat-shock response in desert and temperate ants.},
author = {Natalia Souza Araujo and Rémy Perez and Quentin Willot and Matthieu Defrance and Serge Aron},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366010/3/Araujo-2023.pdf},
year = {2023},
date = {2023-01-01},
journal = {Ecology and evolution},
volume = {13},
number = {9},
pages = {e10438},
abstract = {Global climate changes may cause profound effects on species adaptation, particularly in ectotherms for whom even moderate warmer temperatures can lead to disproportionate heat failure. Still, several organisms evolved to endure high desert temperatures. Here, we describe the thermal tolerance survival and the transcriptomic heat stress response of three genera of desert (Cataglyphis, Melophorus, and Ocymyrmex) and two of temperate ants (Formica and Myrmica) and explore convergent and specific adaptations. We found heat stress led to either a reactive or a constitutive response in desert ants: Cataglyphis holgerseni and Melophorus bagoti differentially regulated very few transcripts in response to heat (0.12% and 0.14%, respectively), while Cataglyphis bombycina and Ocymyrmex robustior responded with greater expression alterations (respectively affecting 0.6% and 1.53% of their transcriptomes). These two responsive mechanisms-reactive and constitutive-were related to individual thermal tolerance survival and convergently evolved in distinct desert ant genera. Moreover, in comparison with desert species, the two temperate ants differentially expressed thousands of transcripts more in response to heat stress (affecting 8% and 12.71% of F. fusca and Myr. sabuleti transcriptomes). In summary, we show that heat adaptation in thermophilic ants involved changes in the expression response. Overall, desert ants show reduced transcriptional alterations even when under high thermal stress, and their expression response may be either constitutive or reactive to temperature increase.},
note = {DOI: 10.1002/ece3.10438},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hardy, Alexis; Duharcourt, Sandra; Defrance, Matthieu
DNA Modification Patterns Filtering and Analysis Using DNAModAnnot. Journal Article
In: Methods in molecular biology, vol. 2624, pp. 87-114, 2023, (DOI: 10.1007/978-1-0716-2962-8_7).
@article{info:hdl:2013/360023,
title = {DNA Modification Patterns Filtering and Analysis Using DNAModAnnot.},
author = {Alexis Hardy and Sandra Duharcourt and Matthieu Defrance},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/360023/4/DNAModAnnot-1.pdf},
year = {2023},
date = {2023-01-01},
journal = {Methods in molecular biology},
volume = {2624},
pages = {87-114},
abstract = {Mapping DNA modifications at the base resolution is now possible at the genome level thanks to advances in sequencing technologies. Long-read sequencing data can be used to identify modified base patterns. However, the downstream analysis of Pacific Biosciences (PacBio) or Oxford Nanopore Technologies (ONT) data requires the integration of genomic annotation and comprehensive filtering to prevent the accumulation of artifact signals. We present in this chapter, a linear workflow to fully analyze modified base patterns using the DNA Modification Annotation (DNAModAnnot) package. This workflow includes a thorough filtering based on sequencing quality and false discovery rate estimation and provides tools for a global analysis of DNA modifications. Here, we provide an application example of this workflow with PacBio data and guide the user by explaining expected outputs via a fully integrated Rmarkdown script. This protocol is presented with tips showing how to adapt the provided code for annotating epigenomes of any organism according to the user needs.},
note = {DOI: 10.1007/978-1-0716-2962-8_7},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nachtegael, Charlotte; Stefani, Jacopo De; Lenaerts, Tom
ALAMBIC : Active Learning Automation Methods to Battle Inefficient Curation Miscellaneous
2023, (Conference: European Chapter of the Association for Computational Linguistics: System Demonstrations (17: Dubrovnik)).
@misc{info:hdl:2013/367264,
title = {ALAMBIC : Active Learning Automation Methods to Battle Inefficient Curation},
author = {Charlotte Nachtegael and Jacopo De Stefani and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367264/3/23.pdf},
year = {2023},
date = {2023-01-01},
abstract = {We present ALAMBIC, an open-source dockerized web-based platform for annotating text data through active learning for classification tasks. Active learning is known to reduce the need of labelling, a time-consuming task, by selecting the most informative instances among the unlabelled instances, reaching an optimal accuracy faster than by just randomly labelling data. ALAMBIC integrates all the steps from data import to customization of the (active) learning process and annotation of the data, with indications of the progress of the trained model that can be downloaded and used in downstream tasks. Its architecture also allows the easy integration of other types of models, features and active learning strategies.},
note = {Conference: European Chapter of the Association for Computational Linguistics: System Demonstrations (17: Dubrovnik)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Gravel, Barbara; Papadimitriou, Sofia; Nachtegael, Charlotte; Baere, Elfride De; Loeys, Bart; Vikkula, Miikka; Smits, Guillaume; Lenaerts, Tom
2023, (Conference: Genomics of Rare Disease(17: 24-26/04/2023: Wellcome Genome Campus, UK)).
@misc{info:hdl:2013/366748,
title = {The importance of good data quality and proper pathogenicity reporting in the medical genetics field: the case of oligogenic diseases},
author = {Barbara Gravel and Sofia Papadimitriou and Charlotte Nachtegael and Elfride De Baere and Bart Loeys and Miikka Vikkula and Guillaume Smits and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366748/3/Abstract_GRD.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Genomics of Rare Disease(17: 24-26/04/2023: Wellcome Genome Campus, UK)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Bosch, Inas; Renaux, Alexandre; Gravel, Barbara; Lenaerts, Tom
Knowledge graph embeddings for the prediction of pathogenic gene pairs Miscellaneous
2023, (Conference: Benelux Ai Conference (BNAIC)(8-10/11/2023: Delft, les Pays-Bas)).
@misc{info:hdl:2013/366662b,
title = {Knowledge graph embeddings for the prediction of pathogenic gene pairs},
author = {Inas Bosch and Alexandre Renaux and Barbara Gravel and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366662/3/Abstract_thesis.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Benelux Ai Conference (BNAIC)(8-10/11/2023: Delft, les Pays-Bas)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowé, Ann
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making Miscellaneous
2023, (Conference: Benelux AI Conference (BNAIC) and the Benelux Machine learning Conference (Benelearn)(8-10/11/2023: Delft)).
@misc{info:hdl:2013/366669b,
title = {Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowé},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366669/3/BNAIC2023ExpertiseTrees.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: Benelux AI Conference (BNAIC) and the Benelux Machine learning Conference (Benelearn)(8-10/11/2023: Delft)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Giuili, Edoardo; Grolaux, Robin; Macedo, Catarina Z N M CZNM; Desmyter, Laurence; Pichon, Bruno; Neuens, Sebastian; Vilain, Catheline; Olsen, Catharina; Dooren, Sonia Van; Smits, Guillaume; Defrance, Matthieu
Comprehensive evaluation of the implementation of episignatures for diagnosis of neurodevelopmental disorders (NDDs). Journal Article
In: Human genetics, 2023, (DOI: 10.1007/s00439-023-02609-2).
@article{info:hdl:2013/364749b,
title = {Comprehensive evaluation of the implementation of episignatures for diagnosis of neurodevelopmental disorders (NDDs).},
author = {Edoardo Giuili and Robin Grolaux and Catarina Z N M CZNM Macedo and Laurence Desmyter and Bruno Pichon and Sebastian Neuens and Catheline Vilain and Catharina Olsen and Sonia Van Dooren and Guillaume Smits and Matthieu Defrance},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/364749},
year = {2023},
date = {2023-01-01},
journal = {Human genetics},
abstract = {Episignatures are popular tools for the diagnosis of rare neurodevelopmental disorders. They are commonly based on a set of differentially methylated CpGs used in combination with a support vector machine model. DNA methylation (DNAm) data often include missing values due to changes in data generation technology and batch effects. While many normalization methods exist for DNAm data, their impact on episignature performance have never been assessed. In addition, technologies to quantify DNAm evolve quickly and this may lead to poor transposition of existing episignatures generated on deprecated array versions to new ones. Indeed, probe removal between array versions, technologies or during preprocessing leads to missing values. Thus, the effect of missing data on episignature performance must also be carefully evaluated and addressed through imputation or an innovative approach to episignatures design. In this paper, we used data from patients suffering from Kabuki and Sotos syndrome to evaluate the influence of normalization methods, classification models and missing data on the prediction performances of two existing episignatures. We compare how six popular normalization methods for methylarray data affect episignature classification performances in Kabuki and Sotos syndromes and provide best practice suggestions when building new episignatures. In this setting, we show that Illumina, Noob or Funnorm normalization methods achieved higher classification performances on the testing sets compared to Quantile, Raw and Swan normalization methods. We further show that penalized logistic regression and support vector machines perform best in the classification of Kabuki and Sotos syndrome patients. Then, we describe a new paradigm to build episignatures based on the detection of differentially methylated regions (DMRs) and evaluate their performance compared to classical differentially methylated cytosines (DMCs)-based episignatures in the presence of missing data. We show that the performance of classical DMC-based episignatures suffers from the presence of missing data more than the DMR-based approach. We present a comprehensive evaluation of how the normalization of DNA methylation data affects episignature performance, using three popular classification models. We further evaluate how missing data affect those models' predictions. Finally, we propose a novel methodology to develop episignatures based on differentially methylated regions identification and show how this method slightly outperforms classical episignatures in the presence of missing data.},
note = {DOI: 10.1007/s00439-023-02609-2},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Terrucha, Ines; Domingos, Elias Fernandez; Suchon, Remi; Santos, Francisco C; Simoens, Pieter; Lenaerts, Tom
Delegation to autonomous agents : a key to overcome past failure and focus on the collective target ahead Miscellaneous
2023, (Conference: the 9th International Conference on Computational Social Science (IC2S2)(17-19/07/2023: Copenhagen)).
@misc{info:hdl:2013/366663b,
title = {Delegation to autonomous agents : a key to overcome past failure and focus on the collective target ahead},
author = {Ines Terrucha and Elias Fernandez Domingos and Remi Suchon and Francisco C Santos and Pieter Simoens and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366663/3/8352.pdf},
year = {2023},
date = {2023-01-01},
note = {Conference: the 9th International Conference on Computational Social Science (IC2S2)(17-19/07/2023: Copenhagen)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Abels, Axel; Lenaerts, Tom; Nowé, Ann
Mitigating Biases and Reward Uncertainty in Collective Decision-Making Miscellaneous
2023, (Conference: 7th Annual Center for Human-Compatible AI Workshop(7: 16-18/06/2023: Pacific Grove, California, USA)).
@misc{info:hdl:2013/366671b,
title = {Mitigating Biases and Reward Uncertainty in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Ann Nowé},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/366671},
year = {2023},
date = {2023-01-01},
note = {Conference: 7th Annual Center for Human-Compatible AI Workshop(7: 16-18/06/2023: Pacific Grove, California, USA)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Hardy, Alexis; Duharcourt, Sandra; Defrance, Matthieu
DNA Modification Patterns Filtering and Analysis Using DNAModAnnot. Journal Article
In: Methods in molecular biology, vol. 2624, pp. 87-114, 2023, (DOI: 10.1007/978-1-0716-2962-8_7).
@article{info:hdl:2013/360023b,
title = {DNA Modification Patterns Filtering and Analysis Using DNAModAnnot.},
author = {Alexis Hardy and Sandra Duharcourt and Matthieu Defrance},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/360023/4/DNAModAnnot-1.pdf},
year = {2023},
date = {2023-01-01},
journal = {Methods in molecular biology},
volume = {2624},
pages = {87-114},
abstract = {Mapping DNA modifications at the base resolution is now possible at the genome level thanks to advances in sequencing technologies. Long-read sequencing data can be used to identify modified base patterns. However, the downstream analysis of Pacific Biosciences (PacBio) or Oxford Nanopore Technologies (ONT) data requires the integration of genomic annotation and comprehensive filtering to prevent the accumulation of artifact signals. We present in this chapter, a linear workflow to fully analyze modified base patterns using the DNA Modification Annotation (DNAModAnnot) package. This workflow includes a thorough filtering based on sequencing quality and false discovery rate estimation and provides tools for a global analysis of DNA modifications. Here, we provide an application example of this workflow with PacBio data and guide the user by explaining expected outputs via a fully integrated Rmarkdown script. This protocol is presented with tips showing how to adapt the provided code for annotating epigenomes of any organism according to the user needs.},
note = {DOI: 10.1007/978-1-0716-2962-8_7},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nachtegael, Charlotte; Stefani, Jacopo De; Lenaerts, Tom
ALAMBIC : Active Learning Automation Methods to Battle Inefficient Curation Miscellaneous
2023, (Conference: European Chapter of the Association for Computational Linguistics: System Demonstrations (17: Dubrovnik)).
@misc{info:hdl:2013/367264b,
title = {ALAMBIC : Active Learning Automation Methods to Battle Inefficient Curation},
author = {Charlotte Nachtegael and Jacopo De Stefani and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367264/3/23.pdf},
year = {2023},
date = {2023-01-01},
abstract = {We present ALAMBIC, an open-source dockerized web-based platform for annotating text data through active learning for classification tasks. Active learning is known to reduce the need of labelling, a time-consuming task, by selecting the most informative instances among the unlabelled instances, reaching an optimal accuracy faster than by just randomly labelling data. ALAMBIC integrates all the steps from data import to customization of the (active) learning process and annotation of the data, with indications of the progress of the trained model that can be downloaded and used in downstream tasks. Its architecture also allows the easy integration of other types of models, features and active learning strategies.},
note = {Conference: European Chapter of the Association for Computational Linguistics: System Demonstrations (17: Dubrovnik)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Nachtegael, Charlotte; Stefani, Jacopo De; Lenaerts, Tom
A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction Journal Article
In: PloS one, vol. 18, no. 12, pp. e0292356, 2023, (DOI: 10.1371/journal.pone.0292356).
@article{info:hdl:2013/366625,
title = {A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction},
author = {Charlotte Nachtegael and Jacopo De Stefani and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366625/3/journal.pone.0292356.pdf},
year = {2023},
date = {2023-01-01},
journal = {PloS one},
volume = {18},
number = {12},
pages = {e0292356},
abstract = {Automatic biomedical relation extraction (bioRE) is an essential task in biomedical research in order to generate high-quality labelled data that can be used for the development of innovative predictive methods. However, building such fully labelled, high quality bioRE data sets of adequate size for the training of state-of-the-art relation extraction models is hindered by an annotation bottleneck due to limitations on time and expertise of researchers and curators. We show here how Active Learning (AL) plays an important role in resolving this issue and positively improve bioRE tasks, effectively overcoming the labelling limits inherent to a data set. Six different AL strategies are benchmarked on seven bioRE data sets, using PubMedBERT as the base model, evaluating their area under the learning curve (AULC) as well as intermediate results measurements. The results demonstrate that uncertainty-based strategies, such as Least-Confident or Margin Sampling, are statistically performing better in terms of F1-score, accuracy and precision, than other types of AL strategies. However, in terms of recall, a diversity-based strategy, called Core-set, outperforms all strategies. AL strategies are shown to reduce the annotation need (in order to reach a performance at par with training on all data), from 6% to 38%, depending on the data set; with Margin Sampling and Least-Confident Sampling strategies moreover obtaining the best AULCs compared to the Random Sampling baseline. We show through the experiments the importance of using AL methods to reduce the amount of labelling needed to construct high-quality data sets leading to optimal performance of deep learning models. The code and data sets to reproduce all the results presented in the article are available at https://github.com/oligogenic/Deep_active_learning_bioRE .},
note = {DOI: 10.1371/journal.pone.0292356},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Boutry, Simon; Helaers, Raphaël; Lenaerts, Tom; Vikkula, Miikka
Excalibur: A new ensemble method based on an optimal combination of aggregation tests for rare-variant association testing for sequencing data Journal Article
In: PLoS computational biology, vol. 19, no. 9, pp. e1011488, 2023, (DOI: 10.1371/journal.pcbi.1011488).
@article{info:hdl:2013/366629,
title = {Excalibur: A new ensemble method based on an optimal combination of aggregation tests for rare-variant association testing for sequencing data},
author = {Simon Boutry and Raphaël Helaers and Tom Lenaerts and Miikka Vikkula},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366629/1/doi_350273.pdf},
year = {2023},
date = {2023-01-01},
journal = {PLoS computational biology},
volume = {19},
number = {9},
pages = {e1011488},
abstract = {The development of high-throughput next-generation sequencing technologies and large-scale genetic association studies produced numerous advances in the biostatistics field. Various aggregation tests, i.e. statistical methods that analyze associations of a trait with multiple markers within a genomic region, have produced a variety of novel discoveries. Notwithstanding their usefulness, there is no single test that fits all needs, each suffering from specific drawbacks. Selecting the right aggregation test, while considering an unknown underlying genetic model of the disease, remains an important challenge. Here we propose a new ensemble method, called Excalibur, based on an optimal combination of 36 aggregation tests created after an in-depth study of the limitations of each test and their impact on the quality of result. Our findings demonstrate the ability of our method to control type I error and illustrate that it offers the best average power across all scenarios. The proposed method allows for novel advances in Whole Exome/Genome sequencing association studies, able to handle a wide range of association models, providing researchers with an optimal aggregation analysis for the genetic regions of interest.},
note = {DOI: 10.1371/journal.pcbi.1011488},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Renaux, Alexandre; Terwagne, Chloé CT; Cochez, Michael; Tiddi, Ilaria; Nowe, Ann; Lenaerts, Tom
A knowledge graph approach to predict and interpret disease-causing gene interactions Journal Article
In: BMC bioinformatics, vol. 24, no. 1, 2023, (DOI: 10.1186/s12859-023-05451-5).
@article{info:hdl:2013/363454,
title = {A knowledge graph approach to predict and interpret disease-causing gene interactions},
author = {Alexandre Renaux and Chloé CT Terwagne and Michael Cochez and Ilaria Tiddi and Ann Nowe and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/363454/1/doi_347098.pdf},
year = {2023},
date = {2023-01-01},
journal = {BMC bioinformatics},
volume = {24},
number = {1},
abstract = {Background: Understanding the impact of gene interactions on disease phenotypes is increasingly recognised as a crucial aspect of genetic disease research. This trend is reflected by the growing amount of clinical research on oligogenic diseases, where disease manifestations are influenced by combinations of variants on a few specific genes. Although statistical machine-learning methods have been developed to identify relevant genetic variant or gene combinations associated with oligogenic diseases, they rely on abstract features and black-box models, posing challenges to interpretability for medical experts and impeding their ability to comprehend and validate predictions. In this work, we present a novel, interpretable predictive approach based on a knowledge graph that not only provides accurate predictions of disease-causing gene interactions but also offers explanations for these results. Results: We introduce BOCK, a knowledge graph constructed to explore disease-causing genetic interactions, integrating curated information on oligogenic diseases from clinical cases with relevant biomedical networks and ontologies. Using this graph, we developed a novel predictive framework based on heterogenous paths connecting gene pairs. This method trains an interpretable decision set model that not only accurately predicts pathogenic gene interactions, but also unveils the patterns associated with these diseases. A unique aspect of our approach is its ability to offer, along with each positive prediction, explanations in the form of subgraphs, revealing the specific entities and relationships that led to each pathogenic prediction. Conclusion: Our method, built with interpretability in mind, leverages heterogenous path information in knowledge graphs to predict pathogenic gene interactions and generate meaningful explanations. This not only broadens our understanding of the molecular mechanisms underlying oligogenic diseases, but also presents a novel application of knowledge graphs in creating more transparent and insightful predictors for genetic research.},
note = {DOI: 10.1186/s12859-023-05451-5},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowé, Ann
Dealing with expert bias in collective decision-making Journal Article
In: Artificial intelligence, vol. 320, pp. 103921, 2023, (DOI: 10.1016/j.artint.2023.103921).
@article{info:hdl:2013/366627,
title = {Dealing with expert bias in collective decision-making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowé},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366627/3/2106.13539.pdf},
year = {2023},
date = {2023-01-01},
journal = {Artificial intelligence},
volume = {320},
pages = {103921},
abstract = {Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Multiple expert judgments, whether human or artificial, can help in taking correct decisions, especially when exploration of alternative solutions is costly. As expert opinions might deviate, the problem of finding the right alternative can be approached as a collective decision making problem (CDM) via aggregation of independent judgments. Current state-of-the-art approaches focus on efficiently finding the optimal expert, and thus perform poorly if all experts are not qualified or if they display consistent biases, thereby potentially derailing the decision-making process. In this paper, we propose a new algorithmic approach based on contextual multi-armed bandit problems (CMAB) to identify and counteract such biased expertise. We explore homogeneous, heterogeneous and polarized expert groups and show that this approach is able to effectively exploit the collective expertise, outperforming state-of-the-art methods, especially when the quality of the provided expertise degrades. Our novel CMAB-inspired approach achieves a higher final performance and does so while converging more rapidly than previous adaptive algorithms.},
note = {DOI: 10.1016/j.artint.2023.103921},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making Journal Article
In: Proceedings of Machine Learning Research, vol. 202, pp. 79-90, 2023, (Language of publication: en).
@article{info:hdl:2013/371232,
title = {Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/371232/3/abels23a.html},
year = {2023},
date = {2023-01-01},
journal = {Proceedings of Machine Learning Research},
volume = {202},
pages = {79-90},
abstract = {Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work, we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm ' expertise trees ' that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.},
note = {Language of publication: en},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Domingos, Elias Fernandez; Santos, Francisco C; Lenaerts, Tom
EGTtools: Evolutionary game dynamics in Python Journal Article
In: iScience, vol. 26, no. 4, pp. 106419, 2023, (DOI: 10.1016/j.isci.2023.106419).
@article{info:hdl:2013/366628,
title = {EGTtools: Evolutionary game dynamics in Python},
author = {Elias Fernandez Domingos and Francisco C Santos and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366628/1/doi_350272.pdf},
year = {2023},
date = {2023-01-01},
journal = {iScience},
volume = {26},
number = {4},
pages = {106419},
abstract = {Evolutionary Game Theory (EGT) provides an important framework to study collective behavior. It combines ideas from evolutionary biology and population dynamics with the game theoretical modeling of strategic interactions. Its importance is highlighted by the numerous high level publications that have enriched different fields, ranging from biology to social sciences, in many decades. Nevertheless, there has been no open source library that provided easy, and efficient, access to these methods and models. Here, we introduce EGTtools, an efficient hybrid C++/Python library which provides fast implementations of both analytical and numerical EGT methods. EGTtools is able to analytically evaluate a system based on the replicator dynamics. It is also able to evaluate any EGT problem resorting to finite populations and large-scale Markov processes. Finally, it resorts to C++ and MonteCarlo simulations to estimate many important indicators, such as stationary or strategy distributions. We illustrate all these methodologies with concrete examples and analysis.},
note = {DOI: 10.1016/j.isci.2023.106419},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Jacquemin, Valérie; Versbraegen, Nassim; Duerinckx, Sarah; Massart, Annick; Soblet, Julie; Perazzolo, Camille; Deconinck, Nicolas; Brischoux-Boucher, Elise; Leener, Anne De; Revencu, Nicole; Janssens, Sandra; Moorgat, Stèphanie; Blaumeiser, Bettina; Avela, Kristiina; Touraine, Renaud; Jaoude, Imad Abou; Keymolen, Kathelijn; Saugier-Veber, P.; Lenaerts, Tom; Abramowicz, Marc; Pirson, Isabelle
Congenital hydrocephalus: new Mendelian mutations and evidence for oligogenic inheritance. Journal Article
In: Human genomics, vol. 17, no. 1, pp. 16, 2023, (DOI: 10.1186/s40246-023-00464-w).
@article{info:hdl:2013/356774,
title = {Congenital hydrocephalus: new Mendelian mutations and evidence for oligogenic inheritance.},
author = {Valérie Jacquemin and Nassim Versbraegen and Sarah Duerinckx and Annick Massart and Julie Soblet and Camille Perazzolo and Nicolas Deconinck and Elise Brischoux-Boucher and Anne De Leener and Nicole Revencu and Sandra Janssens and Stèphanie Moorgat and Bettina Blaumeiser and Kristiina Avela and Renaud Touraine and Imad Abou Jaoude and Kathelijn Keymolen and P. Saugier-Veber and Tom Lenaerts and Marc Abramowicz and Isabelle Pirson},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/356774/1/doi_340418.pdf},
year = {2023},
date = {2023-01-01},
journal = {Human genomics},
volume = {17},
number = {1},
pages = {16},
abstract = {Congenital hydrocephalus is characterized by ventriculomegaly, defined as a dilatation of cerebral ventricles, and thought to be due to impaired cerebrospinal fluid (CSF) homeostasis. Primary congenital hydrocephalus is a subset of cases with prenatal onset and absence of another primary cause, e.g., brain hemorrhage. Published series report a Mendelian cause in only a minority of cases. In this study, we analyzed exome data of PCH patients in search of novel causal genes and addressed the possibility of an underlying oligogenic mode of inheritance for PCH.},
note = {DOI: 10.1186/s40246-023-00464-w},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Papadimitriou, Sofia; Gravel, Barbara; Nachtegael, Charlotte; Baere, Elfride De; Loeys, Bart; Vikkula, Miikka; Smits, Guillaume; Lenaerts, Tom
Toward reporting standards for the pathogenicity of variant combinations involved in multilocus/oligogenic diseases Journal Article
In: Human Genetics and Genomics Advances, vol. 4, no. 1, pp. 100165, 2023, (DOI: 10.1016/j.xhgg.2022.100165).
@article{info:hdl:2013/356000,
title = {Toward reporting standards for the pathogenicity of variant combinations involved in multilocus/oligogenic diseases},
author = {Sofia Papadimitriou and Barbara Gravel and Charlotte Nachtegael and Elfride De Baere and Bart Loeys and Miikka Vikkula and Guillaume Smits and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/356000/1/doi_339644.pdf},
year = {2023},
date = {2023-01-01},
journal = {Human Genetics and Genomics Advances},
volume = {4},
number = {1},
pages = {100165},
abstract = {Although standards and guidelines for the interpretation of variants identified in genes that cause Mendelian disorders have been developed, this is not the case for more complex genetic models including variant combinations in multiple genes. During a large curation process conducted on 318 research articles presenting oligogenic variant combinations, we encountered several recurring issues concerning their proper reporting and pathogenicity assessment. These mainly concern the absence of strong evidence that refutes a monogenic model and the lack of a proper genetic and functional assessment of the joint effect of the involved variants. With the increasing accumulation of such cases, it has become essential to develop standards and guidelines on how these oligogenic/multilocus variant combinations should be interpreted, validated, and reported in order to provide high-quality data and supporting evidence to the scientific community.},
note = {DOI: 10.1016/j.xhgg.2022.100165},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nachtegael, Charlotte; Stefani, Jacopo De; Lenaerts, Tom
A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction Journal Article
In: PloS one, vol. 18, no. 12, pp. e0292356, 2023, (DOI: 10.1371/journal.pone.0292356).
@article{info:hdl:2013/366625b,
title = {A study of deep active learning methods to reduce labelling efforts in biomedical relation extraction},
author = {Charlotte Nachtegael and Jacopo De Stefani and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366625/3/journal.pone.0292356.pdf},
year = {2023},
date = {2023-01-01},
journal = {PloS one},
volume = {18},
number = {12},
pages = {e0292356},
abstract = {Automatic biomedical relation extraction (bioRE) is an essential task in biomedical research in order to generate high-quality labelled data that can be used for the development of innovative predictive methods. However, building such fully labelled, high quality bioRE data sets of adequate size for the training of state-of-the-art relation extraction models is hindered by an annotation bottleneck due to limitations on time and expertise of researchers and curators. We show here how Active Learning (AL) plays an important role in resolving this issue and positively improve bioRE tasks, effectively overcoming the labelling limits inherent to a data set. Six different AL strategies are benchmarked on seven bioRE data sets, using PubMedBERT as the base model, evaluating their area under the learning curve (AULC) as well as intermediate results measurements. The results demonstrate that uncertainty-based strategies, such as Least-Confident or Margin Sampling, are statistically performing better in terms of F1-score, accuracy and precision, than other types of AL strategies. However, in terms of recall, a diversity-based strategy, called Core-set, outperforms all strategies. AL strategies are shown to reduce the annotation need (in order to reach a performance at par with training on all data), from 6% to 38%, depending on the data set; with Margin Sampling and Least-Confident Sampling strategies moreover obtaining the best AULCs compared to the Random Sampling baseline. We show through the experiments the importance of using AL methods to reduce the amount of labelling needed to construct high-quality data sets leading to optimal performance of deep learning models. The code and data sets to reproduce all the results presented in the article are available at https://github.com/oligogenic/Deep_active_learning_bioRE .},
note = {DOI: 10.1371/journal.pone.0292356},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Boutry, Simon; Helaers, Raphaël; Lenaerts, Tom; Vikkula, Miikka
Rare variant association on unrelated individuals in case–control studies using aggregation tests: existing methods and current limitations Journal Article
In: Briefings in bioinformatics, vol. 24, no. 6, 2023, (DOI: 10.1093/bib/bbad412).
@article{info:hdl:2013/366630b,
title = {Rare variant association on unrelated individuals in case–control studies using aggregation tests: existing methods and current limitations},
author = {Simon Boutry and Raphaël Helaers and Tom Lenaerts and Miikka Vikkula},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366630/3/revised_manuscript_clean.pdf},
year = {2023},
date = {2023-01-01},
journal = {Briefings in bioinformatics},
volume = {24},
number = {6},
abstract = {Abstract Over the past years, progress made in next-generation sequencing technologies and bioinformatics have sparked a surge in association studies. Especially, genome-wide association studies (GWASs) have demonstrated their effectiveness in identifying disease associations with common genetic variants. Yet, rare variants can contribute to additional disease risk or trait heterogeneity. Because GWASs are underpowered for detecting association with such variants, numerous statistical methods have been recently proposed. Aggregation tests collapse multiple rare variants within a genetic region (e.g. gene, gene set, genomic loci) to test for association. An increasing number of studies using such methods successfully identified trait-associated rare variants and led to a better understanding of the underlying disease mechanism. In this review, we compare existing aggregation tests, their statistical features and scope of application, splitting them into the five classical classes: burden, adaptive burden, variance-component, omnibus and other. Finally, we describe some limitations of current aggregation tests, highlighting potential direction for further investigations.},
note = {DOI: 10.1093/bib/bbad412},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Boutry, Simon; Helaers, Raphaël; Lenaerts, Tom; Vikkula, Miikka
Excalibur: A new ensemble method based on an optimal combination of aggregation tests for rare-variant association testing for sequencing data Journal Article
In: PLoS computational biology, vol. 19, no. 9, pp. e1011488, 2023, (DOI: 10.1371/journal.pcbi.1011488).
@article{info:hdl:2013/366629b,
title = {Excalibur: A new ensemble method based on an optimal combination of aggregation tests for rare-variant association testing for sequencing data},
author = {Simon Boutry and Raphaël Helaers and Tom Lenaerts and Miikka Vikkula},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366629/1/doi_350273.pdf},
year = {2023},
date = {2023-01-01},
journal = {PLoS computational biology},
volume = {19},
number = {9},
pages = {e1011488},
abstract = {The development of high-throughput next-generation sequencing technologies and large-scale genetic association studies produced numerous advances in the biostatistics field. Various aggregation tests, i.e. statistical methods that analyze associations of a trait with multiple markers within a genomic region, have produced a variety of novel discoveries. Notwithstanding their usefulness, there is no single test that fits all needs, each suffering from specific drawbacks. Selecting the right aggregation test, while considering an unknown underlying genetic model of the disease, remains an important challenge. Here we propose a new ensemble method, called Excalibur, based on an optimal combination of 36 aggregation tests created after an in-depth study of the limitations of each test and their impact on the quality of result. Our findings demonstrate the ability of our method to control type I error and illustrate that it offers the best average power across all scenarios. The proposed method allows for novel advances in Whole Exome/Genome sequencing association studies, able to handle a wide range of association models, providing researchers with an optimal aggregation analysis for the genetic regions of interest.},
note = {DOI: 10.1371/journal.pcbi.1011488},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Renaux, Alexandre; Terwagne, Chloé CT; Cochez, Michael; Tiddi, Ilaria; Nowe, Ann; Lenaerts, Tom
A knowledge graph approach to predict and interpret disease-causing gene interactions Journal Article
In: BMC bioinformatics, vol. 24, no. 1, 2023, (DOI: 10.1186/s12859-023-05451-5).
@article{info:hdl:2013/363454b,
title = {A knowledge graph approach to predict and interpret disease-causing gene interactions},
author = {Alexandre Renaux and Chloé CT Terwagne and Michael Cochez and Ilaria Tiddi and Ann Nowe and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/363454/1/doi_347098.pdf},
year = {2023},
date = {2023-01-01},
journal = {BMC bioinformatics},
volume = {24},
number = {1},
abstract = {Background: Understanding the impact of gene interactions on disease phenotypes is increasingly recognised as a crucial aspect of genetic disease research. This trend is reflected by the growing amount of clinical research on oligogenic diseases, where disease manifestations are influenced by combinations of variants on a few specific genes. Although statistical machine-learning methods have been developed to identify relevant genetic variant or gene combinations associated with oligogenic diseases, they rely on abstract features and black-box models, posing challenges to interpretability for medical experts and impeding their ability to comprehend and validate predictions. In this work, we present a novel, interpretable predictive approach based on a knowledge graph that not only provides accurate predictions of disease-causing gene interactions but also offers explanations for these results. Results: We introduce BOCK, a knowledge graph constructed to explore disease-causing genetic interactions, integrating curated information on oligogenic diseases from clinical cases with relevant biomedical networks and ontologies. Using this graph, we developed a novel predictive framework based on heterogenous paths connecting gene pairs. This method trains an interpretable decision set model that not only accurately predicts pathogenic gene interactions, but also unveils the patterns associated with these diseases. A unique aspect of our approach is its ability to offer, along with each positive prediction, explanations in the form of subgraphs, revealing the specific entities and relationships that led to each pathogenic prediction. Conclusion: Our method, built with interpretability in mind, leverages heterogenous path information in knowledge graphs to predict pathogenic gene interactions and generate meaningful explanations. This not only broadens our understanding of the molecular mechanisms underlying oligogenic diseases, but also presents a novel application of knowledge graphs in creating more transparent and insightful predictors for genetic research.},
note = {DOI: 10.1186/s12859-023-05451-5},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowé, Ann
Dealing with expert bias in collective decision-making Journal Article
In: Artificial intelligence, vol. 320, pp. 103921, 2023, (DOI: 10.1016/j.artint.2023.103921).
@article{info:hdl:2013/366627b,
title = {Dealing with expert bias in collective decision-making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowé},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366627/3/2106.13539.pdf},
year = {2023},
date = {2023-01-01},
journal = {Artificial intelligence},
volume = {320},
pages = {103921},
abstract = {Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Multiple expert judgments, whether human or artificial, can help in taking correct decisions, especially when exploration of alternative solutions is costly. As expert opinions might deviate, the problem of finding the right alternative can be approached as a collective decision making problem (CDM) via aggregation of independent judgments. Current state-of-the-art approaches focus on efficiently finding the optimal expert, and thus perform poorly if all experts are not qualified or if they display consistent biases, thereby potentially derailing the decision-making process. In this paper, we propose a new algorithmic approach based on contextual multi-armed bandit problems (CMAB) to identify and counteract such biased expertise. We explore homogeneous, heterogeneous and polarized expert groups and show that this approach is able to effectively exploit the collective expertise, outperforming state-of-the-art methods, especially when the quality of the provided expertise degrades. Our novel CMAB-inspired approach achieves a higher final performance and does so while converging more rapidly than previous adaptive algorithms.},
note = {DOI: 10.1016/j.artint.2023.103921},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowe, Ann
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making Journal Article
In: Proceedings of Machine Learning Research, vol. 202, pp. 79-90, 2023, (Language of publication: en).
@article{info:hdl:2013/371232b,
title = {Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowe},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/371232/3/abels23a.html},
year = {2023},
date = {2023-01-01},
journal = {Proceedings of Machine Learning Research},
volume = {202},
pages = {79-90},
abstract = {Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work, we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm ' expertise trees ' that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.},
note = {Language of publication: en},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Domingos, Elias Fernandez; Santos, Francisco C; Lenaerts, Tom
EGTtools: Evolutionary game dynamics in Python Journal Article
In: iScience, vol. 26, no. 4, pp. 106419, 2023, (DOI: 10.1016/j.isci.2023.106419).
@article{info:hdl:2013/366628b,
title = {EGTtools: Evolutionary game dynamics in Python},
author = {Elias Fernandez Domingos and Francisco C Santos and Tom Lenaerts},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/366628/1/doi_350272.pdf},
year = {2023},
date = {2023-01-01},
journal = {iScience},
volume = {26},
number = {4},
pages = {106419},
abstract = {Evolutionary Game Theory (EGT) provides an important framework to study collective behavior. It combines ideas from evolutionary biology and population dynamics with the game theoretical modeling of strategic interactions. Its importance is highlighted by the numerous high level publications that have enriched different fields, ranging from biology to social sciences, in many decades. Nevertheless, there has been no open source library that provided easy, and efficient, access to these methods and models. Here, we introduce EGTtools, an efficient hybrid C++/Python library which provides fast implementations of both analytical and numerical EGT methods. EGTtools is able to analytically evaluate a system based on the replicator dynamics. It is also able to evaluate any EGT problem resorting to finite populations and large-scale Markov processes. Finally, it resorts to C++ and MonteCarlo simulations to estimate many important indicators, such as stationary or strategy distributions. We illustrate all these methodologies with concrete examples and analysis.},
note = {DOI: 10.1016/j.isci.2023.106419},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Jacquemin, Valérie; Versbraegen, Nassim; Duerinckx, Sarah; Massart, Annick; Soblet, Julie; Perazzolo, Camille; Deconinck, Nicolas; Brischoux-Boucher, Elise; Leener, Anne De; Revencu, Nicole; Janssens, Sandra; Moorgat, Stèphanie; Blaumeiser, Bettina; Avela, Kristiina; Touraine, Renaud; Jaoude, Imad Abou; Keymolen, Kathelijn; Saugier-Veber, P.; Lenaerts, Tom; Abramowicz, Marc; Pirson, Isabelle
Congenital hydrocephalus: new Mendelian mutations and evidence for oligogenic inheritance. Journal Article
In: Human genomics, vol. 17, no. 1, pp. 16, 2023, (DOI: 10.1186/s40246-023-00464-w).
@article{info:hdl:2013/356774b,
title = {Congenital hydrocephalus: new Mendelian mutations and evidence for oligogenic inheritance.},
author = {Valérie Jacquemin and Nassim Versbraegen and Sarah Duerinckx and Annick Massart and Julie Soblet and Camille Perazzolo and Nicolas Deconinck and Elise Brischoux-Boucher and Anne De Leener and Nicole Revencu and Sandra Janssens and Stèphanie Moorgat and Bettina Blaumeiser and Kristiina Avela and Renaud Touraine and Imad Abou Jaoude and Kathelijn Keymolen and P. Saugier-Veber and Tom Lenaerts and Marc Abramowicz and Isabelle Pirson},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/356774/1/doi_340418.pdf},
year = {2023},
date = {2023-01-01},
journal = {Human genomics},
volume = {17},
number = {1},
pages = {16},
abstract = {Congenital hydrocephalus is characterized by ventriculomegaly, defined as a dilatation of cerebral ventricles, and thought to be due to impaired cerebrospinal fluid (CSF) homeostasis. Primary congenital hydrocephalus is a subset of cases with prenatal onset and absence of another primary cause, e.g., brain hemorrhage. Published series report a Mendelian cause in only a minority of cases. In this study, we analyzed exome data of PCH patients in search of novel causal genes and addressed the possibility of an underlying oligogenic mode of inheritance for PCH.},
note = {DOI: 10.1186/s40246-023-00464-w},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Coelho, Léonardo Bertolucci; Morillo, Daniel Torres; Vangrunderbeek, Vincent; Bernal, Miguel; Paldino, Gian Marco; Bontempi, Gianluca; Troyano, Jon Ustarroz
Estimating pitting descriptors of 316 L stainless steel by machine learning and statistical analysis Journal Article
In: npj Materials degradation, vol. 7, no. 1, 2023, (DOI: 10.1038/s41529-023-00403-z).
@article{info:hdl:2013/367646,
title = {Estimating pitting descriptors of 316 L stainless steel by machine learning and statistical analysis},
author = {Léonardo Bertolucci Coelho and Daniel Torres Morillo and Vincent Vangrunderbeek and Miguel Bernal and Gian Marco Paldino and Gianluca Bontempi and Jon Ustarroz Troyano},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367646/1/doi_351290.pdf},
year = {2023},
date = {2023-01-01},
journal = {npj Materials degradation},
volume = {7},
number = {1},
abstract = {Abstract A hybrid rule-based/ML approach using linear regression and artificial neural networks (ANNs) determined pitting corrosion descriptors from high-throughput data obtained with Scanning Electrochemical Cell Microscopy (SECCM) on 316 L stainless steel. Non-parametric density estimation determined the central tendencies of the E pit /log( jpit ) and E pass /log( jpass ) distributions. Descriptors estimated using conditional mean or median curves were compared to their central tendency values, with the conditional medians providing more accurate results. Due to their lower sensitivity to high outliers, the conditional medians were more robust representations of the log( j ) vs. E distributions. An observed trend of passive range shortening with increasing testing aggressiveness was attributed to delayed stabilisation of the passive film, rather than early passivity breakdown.},
note = {DOI: 10.1038/s41529-023-00403-z},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Salamanca, Eva Muñoz; Dave, Himanshu; D’Alessio, Giuseppe; Bontempi, Gianluca; Parente, Alessandro; Clainche, Soledad Le
Extraction and analysis of flow features in planar synthetic jets using different machine learning techniques Journal Article
In: Physics of fluids, vol. 35, 2023, (DOI: https://doi.org/10.1063/5.0163833).
@article{info:hdl:2013/363688,
title = {Extraction and analysis of flow features in planar synthetic jets using different machine learning techniques},
author = {Eva Muñoz Salamanca and Himanshu Dave and Giuseppe D'Alessio and Gianluca Bontempi and Alessandro Parente and Soledad Le Clainche},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/363688/3/POF_dimensionality_reduction_comparison.pdf},
year = {2023},
date = {2023-01-01},
journal = {Physics of fluids},
volume = {35},
note = {DOI: https://doi.org/10.1063/5.0163833},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Coelho, Léonardo Bertolucci; Morillo, Daniel Torres; Bernal, Miguel; Paldino, Gian Marco; Bontempi, Gianluca; Troyano, Jon Ustarroz
Probing the randomness of the local current distributions of 316 L stainless steel corrosion in NaCl solution Journal Article
In: Corrosion science, vol. 217, pp. 111104, 2023, (DOI: 10.1016/j.corsci.2023.111104).
@article{info:hdl:2013/358502,
title = {Probing the randomness of the local current distributions of 316 L stainless steel corrosion in NaCl solution},
author = {Léonardo Bertolucci Coelho and Daniel Torres Morillo and Miguel Bernal and Gian Marco Paldino and Gianluca Bontempi and Jon Ustarroz Troyano},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/358502/3/BertolucciCoelho2023_PostPrint.pdf},
year = {2023},
date = {2023-01-01},
journal = {Corrosion science},
volume = {217},
pages = {111104},
abstract = {This investigation proposes using Scanning Electrochemical Cell Microscopy (SECCM) as a high throughput tool to collect corrosion activity from randomly probed locations on 316 L SS. In the presence of chloride, potentiodynamic polarisation tests triggered the development of pitting corrosion. Data science methods were deployed to handle and explore 955 j Vs E curves. Normality tests and fitting with theoretical functions were used to understand the conditional log(j) distributions at different potentials. Unimodal and uniform distributions were assigned to the passive and pitting regions. Our “big-data” local strategy revealed a potential-dependent distribution of log(j), with the randomness increasing with testing aggressiveness. Data availability: All data generated or analysed during this study are included in this published article (and its supplementary information files) and are available in the Mendeley Data repository, [https://data.mendeley.com/datasets/78rz8vw46x/2]. Code availability: The code required to reproduce these findings is included in this published article (and its supplementary information files) and is available to download from GitHub: https://github.com/bcoelho-leonardo/Data-driven-analysis-of-the-local-current-distributions-of-316L-corrosion-in-NaCl-solution/blob/4efff485b115468840b25ea56ad81b31711c0f51/local%20current%20distributions%20of%20316L%20corrosion.ipynb.},
note = {DOI: 10.1016/j.corsci.2023.111104},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Verhelst, Theo; Mercier, Denis; Shrestha, Jeevan; Bontempi, Gianluca
Partial counterfactual identification and uplift modeling: theoretical results and real-world assessment Journal Article
In: Machine learning, 2023, (DOI: 10.1007/s10994-023-06317-w).
@article{info:hdl:2013/367639,
title = {Partial counterfactual identification and uplift modeling: theoretical results and real-world assessment},
author = {Theo Verhelst and Denis Mercier and Jeevan Shrestha and Gianluca Bontempi},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367639/3/MLJ.pdf},
year = {2023},
date = {2023-01-01},
journal = {Machine learning},
abstract = {Counterfactuals are central in causal human reasoning and the scientific discovery process. The uplift, also called conditional average treatment effect, measures the causal effect of some action, or treatment, on the outcome of an individual. This paper discusses how it is possible to derive bounds on the probability of counterfactual statements based on uplift terms. First, we derive some original bounds on the probability of counterfactuals and we show that tightness of such bounds depends on the information of the feature set on the uplift term. Then, we propose a point estimator based on the assumption of conditional independence between the counterfactual outcomes. The quality of the bounds and the point estimators are assessed on synthetic data and a large real-world customer data set provided by a telecom company, showing significant improvement over the state of the art.},
note = {DOI: 10.1007/s10994-023-06317-w},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lunghi, Daniele; Paldino, Gian Marco; Caelen, Olivier; Bontempi, Gianluca
An Adversary Model of Fraudsters’ Behavior to Improve Oversampling in Credit Card Fraud Detection Journal Article
In: IEEE access, vol. 11, pp. 136666-136679, 2023, (DOI: 10.1109/ACCESS.2023.3337635).
@article{info:hdl:2013/367638,
title = {An Adversary Model of Fraudsters’ Behavior to Improve Oversampling in Credit Card Fraud Detection},
author = {Daniele Lunghi and Gian Marco Paldino and Olivier Caelen and Gianluca Bontempi},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367638/1/doi_351282.pdf},
year = {2023},
date = {2023-01-01},
journal = {IEEE access},
volume = {11},
pages = {136666-136679},
abstract = {Imbalanced learning jeopardizes the accuracy of traditional classification models, particularly for what concerns the minority class, which is often the class of interest. This paper addresses the issue of imbalanced learning in credit card fraud detection by introducing a novel approach that models fraudulent behavior as a time-dependent process. The main contribution is the design and assessment of an oversampling strategy, called 'Adversary-based Oversampling' (ADVO), which relies on modeling the temporal relationship among frauds. The strategy is implemented by two learning approaches: first, an innovative regression-based oversampling model that predicts subsequent fraudulent activities based on previous fraud features. Second, the adaptation of the state-of-the-art TimeGAN oversampling algorithm to the context of credit card fraud detection. This adaptation involves treating a sequence of frauds from the same card as a time series, from which artificial frauds' time series are generated. Experiments have been conducted using real credit card transaction data from our industrial partner, Worldline S.A, and a synthetic dataset generated by a transaction simulator for reproducibility purposes. Our findings show that an oversampling approach incorporating time-dependent modeling of frauds provides competitive results, measured against common fraud detection metrics, compared to traditional oversampling algorithms.},
note = {DOI: 10.1109/ACCESS.2023.3337635},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Claeskens, G.; Jansen, Maarten
Comments on: Statistical inference and large-scale multiple testing for high-dimensional regression models Journal Article
In: Test, vol. 32, no. 4, pp. 1177-1179, 2023, (DOI: 10.1007/s11749-023-00896-5).
@article{info:hdl:2013/371479,
title = {Comments on: Statistical inference and large-scale multiple testing for high-dimensional regression models},
author = {G. Claeskens and Maarten Jansen},
url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/371479/3/ClaeskensJansen-TEST-noformat.pdf},
year = {2023},
date = {2023-01-01},
journal = {Test},
volume = {32},
number = {4},
pages = {1177-1179},
note = {DOI: 10.1007/s11749-023-00896-5},
keywords = {},
pubstate = {published},
tppubtype = {article}
}