@article{info:hdl:2013/388988,

title = {On many-objective feature selection and the need for interpretability},

author = {Uchechukwu U. F. Njoku and Alberto Abelló and Besim Bilalli and Gianluca Bontempi},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/388988/1/doi_372632.pdf},

year  = {2025},

date = {2025-01-01},

journal = {Expert systems with applications},

volume = {267},

abstract = {Big data comes with the challenge of containing irrelevant and redundant information (i.e., features). Given that a single objective cannot fully capture a feature's relevance, a Many-Objective Feature Selection (MOFS) approach able to accommodate various relevant perspectives is preferred for identifying the most appropriate features in a given context. However, MOFS produces a large set of solutions whose interpretability has been largely overlooked. First, we demonstrate the relevance of MOFS and establish its necessity by considering up to six objectives using a genetic algorithm and Naive Bayes on ten datasets for classification tasks. Then, we propose a novel methodology to improve the interpretability of MOFS results in order to support the data scientist in selecting the subset of features pertinent to their use case. Our methodology is instantiated as an intuitive and interactive dashboard that provides insights into the results beyond the pure numerical representation of the objectives being considered and evaluated with 50 participants. The outcome shows that it addresses the need for a methodological approach and comprehensive visualization to achieve interoperability.},

note = {DOI: 10.1016/j.eswa.2024.126191},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/372845,

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}

}

@article{info:hdl:2013/372844,

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}

}

@article{info:hdl:2013/370795,

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}

}

@article{info:hdl:2013/372242,

title = {The role of diversity and ensemble learning in credit card fraud detection},

author = {Gian Marco Paldino and Bertrand Lebichot and Yann-Aël Le Borgne and Wissam Siblini and Frédéric Oblé and Giacomo Boracchi and Gianluca Bontempi},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/372242/1/elsevier_355886.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Advances in Data Analysis and Classification},

volume = {18},

number = {1},

pages = {193-217},

abstract = {The number of daily credit card transactions is inexorably growing: the e-commerce market expansion and the recent constraints for the Covid-19 pandemic have significantly increased the use of electronic payments. The ability to precisely detect fraudulent transactions is increasingly important, and machine learning models are now a key component of the detection process. Standard machine learning techniques are widely employed, but inadequate for the evolving nature of customers behavior entailing continuous changes in the underlying data distribution. his problem is often tackled by discarding past knowledge, despite its potential relevance in the case of recurrent concepts. Appropriate exploitation of historical knowledge is necessary: we propose a learning strategy that relies on diversity-based ensemble learning and allows to preserve past concepts and reuse them for a faster adaptation to changes. In our experiments, we adopt several state-of-the-art diversity measures and we perform comparisons with various other learning approaches. We assess the effectiveness of our proposed learning strategy on extracts of two real datasets from two European countries, containing more than 30 M and 50 M transactions, provided by our industrial partner, Worldline, a leading company in the field.},

note = {DOI: 10.1007/s11634-022-00515-5},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/373455,

title = {Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality},

author = {Cédric Simar and Martin Colot and Ana Maria Cebolla Alvarez and Mathieu Petieau and Guy Chéron and Gianluca Bontempi},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/373455/1/doi_357099.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Frontiers in Neuroscience},

volume = {18},

abstract = {Myoelectric prostheses have recently shown significant promise for restoring hand function in individuals with upper limb loss or deficiencies, driven by advances in machine learning and increasingly accessible bioelectrical signal acquisition devices. Here, we first introduce and validate a novel experimental paradigm using a virtual reality headset equipped with hand-tracking capabilities to facilitate the recordings of synchronized EMG signals and hand pose estimation. Using both the phasic and tonic EMG components of data acquired through the proposed paradigm, we compare hand gesture classification pipelines based on standard signal processing features, convolutional neural networks, and covariance matrices with Riemannian geometry computed from raw or xDAWN-filtered EMG signals. We demonstrate the performance of the latter for gesture classification using EMG signals. We further hypothesize that introducing physiological knowledge in machine learning models will enhance their performances, leading to better myoelectric prosthesis control. We demonstrate the potential of this approach by using the neurophysiological integration of the “move command" to better separate the phasic and tonic components of the EMG signals, significantly improving the performance of sustained posture recognition. These results pave the way for the development of new cutting-edge machine learning techniques, likely refined by neurophysiology, that will further improve the decoding of real-time natural gestures and, ultimately, the control of myoelectric prostheses.},

note = {DOI: 10.3389/fnins.2024.1329411},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/371938,

title = {Instance-based meta-learning for conditionally dependent univariate multi-step forecasting},

author = {Vitor Cerqueira and Luis Torgo and Gianluca Bontempi},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/371938/3/ijf.meta2.pdf},

year  = {2024},

date = {2024-01-01},

journal = {International journal of forecasting},

abstract = {Multi-step prediction is a key challenge in univariate forecasting. However, forecasting accuracy decreases as predictions are made further into the future. This is caused by the decreasing predictability and the error propagation along the horizon. In this paper, we propose a novel method called Forecasted Trajectory Neighbors (FTN) for multi-step forecasting with univariate time series. FTN is a meta-learning strategy that can be integrated with any state-of-the-art multi-step forecasting approach. It works by using training observations to correct the errors made during multiple predictions. This is accomplished by retrieving the nearest neighbors of the multi-step forecasts and averaging these for prediction. The motivation is to introduce, in a lightweight manner, a conditional dependent constraint across the forecasting horizons. Such a constraint, not always taken into account by most strategies, can be considered as a sort of regularization element. We carried out extensive experiments using 7795 time series from different application domains. We found that our method improves the performance of several state-of-the-art multi-step forecasting methods. An implementation of the proposed method is publicly available online, and the experiments are reproducible.},

note = {DOI: 10.1016/j.ijforecast.2023.12.010},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/385906,

title = {DOME Registry: implementing community-wide recommendations for reporting supervised machine learning in biology},

author = {Omar Abdelghani Attafi and Damiano Clementel and Konstantinos Kyritsis and Emidio Capriotti and Gavin Farrell and Styliani-Christina Fragkouli and Leyla Jael Castro and András Hatos and Tom Lenaerts and Stanislav Mazurenko and Soroush Mozaffari and Franco Pradelli and Patrick Ruch and Castrense Savojardo and Maria Paola Turina and Federico Zambelli and Damiano Piovesan and Alexander Miguel Monzon and Fotis F. E. Psomopoulos and Silvio S. C. E. Tosatto},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/385906/3/giae094-2.pdf},

year  = {2024},

date = {2024-01-01},

journal = {GigaScience},

volume = {13},

pages = {8},

abstract = {Abstract Supervised machine learning (ML) is used extensively in biology and deserves closer scrutiny. The Data Optimization Model Evaluation (DOME) recommendations aim to enhance the validation and reproducibility of ML research by establishing standards for key aspects such as data handling and processing, optimization, evaluation, and model interpretability. The recommendations help to ensure that key details are reported transparently by providing a structured set of questions. Here, we introduce the DOME registry (URL: registry.dome-ml.org), a database that allows scientists to manage and access comprehensive DOME-related information on published ML studies. The registry uses external resources like ORCID, APICURON, and the Data Stewardship Wizard to streamline the annotation process and ensure comprehensive documentation. By assigning unique identifiers and DOME scores to publications, the registry fosters a standardized evaluation of ML methods. Future plans include continuing to grow the registry through community curation, improving the DOME score definition and encouraging publishers to adopt DOME standards, and promoting transparency and reproducibility of ML in the life sciences.},

note = {DOI: 10.1093/gigascience/giae094},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/374860,

title = {Undiagnosed RASopathies in infertile men},

author = {Anna Grete Juchnewitsch and Kristjan Pomm and Avirup Dutta and Erik Tamp and Anu Valkna and Kristiina Lillepea and Eisa Mahyari and Stanislav Tjagur and Galina Belova and Viljo Kübarsepp and Helen Castillo-Madeen and Antoni Riera-Escamilla and Lisanna Põlluaas and Liina Nagirnaja and Olev Poolamets and Vladimir Vihljajev and Mailis Sütt and Nassim Versbraegen and Sofia Papadimitriou and Robert Ian McLachlan and Keith Allen Jarvi and Peter P. N. Schlegel and Sven Tennisberg and Paul Korrovits and Katinka Vigh-Conrad and Moira M. K. O’Bryan and Kenneth Ivan Aston and Tom Lenaerts and Donald D. F. Conrad and Laura Kasak and Margus Punab and Maris Laan},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/374860/1/doi_358504.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Frontiers in endocrinology},

volume = {15},

abstract = {RASopathies are syndromes caused by congenital defects in the Ras/mitogen-activated protein kinase (MAPK) pathway genes, with a population prevalence of 1 in 1,000. Patients are typically identified in childhood based on diverse characteristic features, including cryptorchidism (CR) in >50% of affected men. As CR predisposes to spermatogenic failure (SPGF; total sperm count per ejaculate 0–39 million), we hypothesized that men seeking infertility management include cases with undiagnosed RASopathies. Likely pathogenic or pathogenic (LP/P) variants in 22 RASopathy-linked genes were screened in 521 idiopathic SPGF patients (including 155 CR cases) and 323 normozoospermic controls using exome sequencing. All 844 men were recruited to the ESTonian ANDrology (ESTAND) cohort and underwent identical andrological phenotyping. RASopathy-specific variant interpretation guidelines were used for pathogenicity assessment. LP/P variants were identified in PTPN11 (two), SOS1 (three), SOS2 (one), LZTR1 (one), SPRED1 (one), NF1 (one), and MAP2K1 (one). The findings affected six of 155 cases with CR and SPGF, three of 366 men with SPGF only, and one (of 323) normozoospermic subfertile man. The subgroup “CR and SPGF” had over 13-fold enrichment of findings compared to controls (3.9% vs. 0.3%; Fisher’s exact test},

note = {DOI: 10.3389/fendo.2024.1312357},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/367025,

title = {Toward a Solid Acceptance of the Decentralized Web of Personal Data: Societal and Technological Convergence},

author = {Ana Pop Stefanija and Bart Buelens and Elfi Goesaert and Tom Lenaerts and Jean René Pierson and Jan Van Bussche},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/367025/4/3624555.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Communications of the ACM},

volume = {67},

number = {1},

pages = {43-46},

abstract = {Giving individuals more control of their personal data.},

note = {DOI: 10.1145/3624555},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/372022,

title = {Evolution of a theory of mind},

author = {Tom Lenaerts and Marco Saponara and Jorge J. M. Pacheco and Francisco C. Santos},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/372022/1/doi_355666.pdf},

year  = {2024},

date = {2024-01-01},

journal = {iScience},

volume = {27},

number = {2},

abstract = {Even though the Theory of Mind in upper primates has been under investigation for decades, how it may evolve remains an open problem. We propose here an evolutionary game theoretical model where a finite population of individuals may use reasoning strategies to infer a response to the anticipated behavior of others within the context of a sequential dilemma, i.e., the Centipede Game. We show that strategies with bounded reasoning evolve and flourish under natural selection, provided they are allowed to make reasoning mistakes and a temptation for higher future gains is in place. We further show that non-deterministic reasoning co-evolves with an optimism bias that may lead to the selection of new equilibria, closely associated with average behavior observed in experimental data. This work reveals both a novel perspective on the evolution of bounded rationality and a co-evolutionary link between the evolution of Theory of Mind and the emergence of misbeliefs.},

note = {DOI: 10.1016/j.isci.2024.108862},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/371876,

title = {The art of compensation: How hybrid teams solve collective-risk dilemmas},

author = {Ines Terrucha and Elias Fernández Domingos and Francisco C. Santos and Pieter Simoens and Tom Lenaerts},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/371876/1/doi_355520.pdf},

year  = {2024},

date = {2024-01-01},

journal = {PloS one},

volume = {19},

number = {2 February},

abstract = {It is widely known how the human ability to cooperate has influenced the thriving of our species. However, as we move towards a hybrid human-machine future, it is still unclear how the introduction of artificial agents in our social interactions affect this cooperative capacity. In a one-shot collective risk dilemma, where enough members of a group must cooperate in order to avoid a collective disaster, we study the evolutionary dynamics of cooperation in a hybrid population. In our model, we consider a hybrid population composed of both adaptive and fixed behavior agents. The latter serve as proxies for the machine-like behavior of artificially intelligent agents who implement stochastic strategies previously learned offline. We observe that the adaptive individuals adjust their behavior in function of the presence of artificial agents in their groups to compensate their cooperative (or lack of thereof) efforts. We also find that risk plays a determinant role when assessing whether or not we should form hybrid teams to tackle a collective risk dilemma. When the risk of collective disaster is high, cooperation in the adaptive population falls dramatically in the presence of cooperative artificial agents. A story of compensation, rather than cooperation, where adaptive agents have to secure group success when the artificial agents are not cooperative enough, but will rather not cooperate if the others do so. On the contrary, when risk of collective disaster is low, success is highly improved while cooperation levels within the adaptive population remain the same. Artificial agents can improve the collective success of hybrid teams. However, their application requires a true risk assessment of the situation in order to actually benefit the adaptive population (i.e. the humans) in the long-term.},

note = {DOI: 10.1371/journal.pone.0297213},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/374647,

title = {Prioritization of oligogenic variant combinations in whole exomes},

author = {Barbara Gravel and Alexandre Renaux and Sofia Papadimitriou and Guillaume Smits and Ann Nowe and Tom Lenaerts},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/374647/1/doi_358291.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Bioinformatics},

volume = {40},

number = {4},

abstract = {Motivation: Whole exome sequencing (WES) has emerged as a powerful tool for genetic research, enabling the collection of a tremendous amount of data about human genetic variation. However, properly identifying which variants are causative of a genetic disease remains an important challenge, often due to the number of variants that need to be screened. Expanding the screening to combinations of variants in two or more genes, as would be required under the oligogenic inheritance model, simply blows this problem out of proportion. Results: We present here the High-throughput oligogenic prioritizer (Hop), a novel prioritization method that uses direct oligogenic information at the variant, gene and gene pair level to detect digenic variant combinations in WES data. This method leverages information from a knowledge graph, together with specialized pathogenicity predictions in order to effectively rank variant combinations based on how likely they are to explain the patient’s phenotype. The performance of Hop is evaluated in cross-validation on 36 120 synthetic exomes for training and 14 280 additional synthetic exomes for independent testing. Whereas the known pathogenic variant combinations are found in the top 20 in approximately 60% of the cross-validation exomes, 71% are found in the same ranking range when considering the independent set. These results provide a significant improvement over alternative approaches that depend simply on a monogenic assessment of pathogenicity, including early attempts for digenic ranking using monogenic pathogenicity scores.},

note = {DOI: 10.1093/bioinformatics/btae184},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/374767,

title = {Toward clinical exomes in diagnostics and management of male infertility},

author = {Kristiina Lillepea and Anna Grete Juchnewitsch and Laura Kasak and Anu Valkna and Avirup Dutta and Kristjan Pomm and Olev Poolamets and Liina Nagirnaja and Erik Tamp and Eisa Mahyari and Vladimir Vihljajev and Stanislav Tjagur and Sofia Papadimitriou and Antoni Riera-Escamilla and Nassim Versbraegen and Ginevra Farnetani and Helen Castillo-Madeen and Mailis Sütt and Viljo Kübarsepp and Sven Tennisberg and Paul Korrovits and Csilla Krausz and Kenneth Ivan Aston and Tom Lenaerts and Donald D. F. Conrad and Margus Punab and Maris Laan},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/374767/3/Lillepeaetal.pdf},

year  = {2024},

date = {2024-01-01},

journal = {American journal of human genetics},

volume = {111},

number = {5},

pages = {877-895},

abstract = {Infertility, affecting ∼10% of men, is predominantly caused by primary spermatogenic failure (SPGF). We screened likely pathogenic and pathogenic (LP/P) variants in 638 candidate genes for male infertility in 521 individuals presenting idiopathic SPGF and 323 normozoospermic men in the ESTAND cohort. Molecular diagnosis was reached for 64 men with SPGF (12%), with findings in 39 genes (6%). The yield did not differ significantly between the subgroups with azoospermia (20/185, 11%), oligozoospermia (18/181, 10%), and primary cryptorchidism with SPGF (26/155, 17%). Notably, 19 of 64 LP/P variants (30%) identified in 28 subjects represented recurrent findings in this study and/or with other male infertility cohorts. NR5A1 was the most frequently affected gene, with seven LP/P variants in six SPGF-affected men and two normozoospermic men. The link to SPGF was validated for recently proposed candidate genes ACTRT1, ASZ1, GLUD2, GREB1L, LEO1, RBM5, ROS1, and TGIF2LY. Heterozygous truncating variants in BNC1, reported in female infertility, emerged as plausible causes of severe oligozoospermia. Data suggested that several infertile men may present congenital conditions with less pronounced or pleiotropic phenotypes affecting the development and function of the reproductive system. Genes regulating the hypothalamic-pituitary-gonadal axis were affected in >30% of subjects with LP/P variants. Six individuals had more than one LP/P variant, including five with two findings from the gene panel. A 4-fold increased prevalence of cancer was observed in men with genetic infertility compared to the general male population (8% vs. 2%; p = 4.4 ?x 10−3). Expanding genetic testing in andrology will contribute to the multidisciplinary management of SPGF.},

note = {DOI: 10.1016/j.ajhg.2024.03.013},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/374632,

title = {DUVEL: an active-learning annotated biomedical corpus for the recognition of oligogenic combinations},

author = {Charlotte Nachtegael and Jacopo De Stefani and Anthony Cnudde and Tom Lenaerts},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/374632/1/doi_358276.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Database},

volume = {2024},

number = {2024},

abstract = {Abstract While biomedical relation extraction (bioRE) datasets have been instrumental in the development of methods to support biocuration of single variants from texts, no datasets are currently available for the extraction of digenic or even oligogenic variant relations, despite the reports in literature that epistatic effects between combinations of variants in different loci (or genes) are important to understand disease etiologies. This work presents the creation of a unique dataset of oligogenic variant combinations, geared to train tools to help in the curation of scientific literature. To overcome the hurdles associated with the number of unlabelled instances and the cost of expertise, active learning (AL) was used to optimize the annotation, thus getting assistance in finding the most informative subset of samples to label. By pre-annotating 85 full-text articles containing the relevant relations from the Oligogenic Diseases Database (OLIDA) with PubTator, text fragments featuring potential digenic variant combinations, i.e. gene–variant–gene–variant, were extracted. The resulting fragments of texts were annotated with ALAMBIC, an AL-based annotation platform. The resulting dataset, called DUVEL, is used to fine-tune four state-of-the-art biomedical language models: BiomedBERT, BiomedBERT-large, BioLinkBERT and BioM-BERT. More than 500 000 text fragments were considered for annotation, finally resulting in a dataset with 8442 fragments, 794 of them being positive instances, covering 95% of the original annotated articles. When applied to gene–variant pair detection, BiomedBERT-large achieves the highest F1 score (0.84) after fine-tuning, demonstrating significant improvement compared to the non-fine-tuned model, underlining the relevance of the DUVEL dataset. This study shows how AL may play an important role in the creation of bioRE dataset relevant for biomedical curation applications. DUVEL provides a unique biomedical corpus focusing on 4-ary relations between two genes and two variants. It is made freely available for research on GitHub and Hugging Face. Database URL: https://huggingface.co/datasets/cnachteg/duvel or https://doi.org/10.57967/hf/1571},

note = {DOI: 10.1093/database/baae039},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/373750,

title = {Voluntary versus mandatory information disclosure in the sequential prisoner’s dilemma},

author = {Georg Kirchsteiger and Tom Lenaerts and Remi Suchon},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/373750/3/s00199-024-01563-y.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Economic theory},

abstract = {In sequential social dilemmas with stranger matching, initiating cooperation is inherently risky for the first mover. The disclosure of the second mover’s past actions may be necessary to instigate cooperation. We experimentally compare the effect of mandatory and voluntary disclosure with non-disclosure in a sequential prisoner’s dilemma situation. Our results confirm the positive effects of disclosure on cooperation. We also find that voluntary disclosure is as effective as mandatory disclosure, which runs counter to the results of existing literature on this topic. With voluntary disclosure, second movers who have a good track record chose to disclose, suggesting that they anticipate non-disclosure would signal non-cooperativeness. First movers interpret non-disclosure correctly as a signal of non-cooperativeness. Therefore, they cooperate less than half as often when the second mover decides not to disclose.},

note = {DOI: 10.1007/s00199-024-01563-y},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/374814,

title = {Committing to the wrong artificial delegate in a collective-risk dilemma is better than directly committing mistakes},

author = {Ines Terrucha and Elias Fernández Domingos and Pieter Simoens and Tom Lenaerts},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/374814/1/doi_358458.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Scientific reports},

volume = {14},

number = {1},

abstract = {While autonomous artificial agents are assumed to perfectly execute the strategies they are programmed with, humans who design them may make mistakes. These mistakes may lead to a misalignment between the humans’ intended goals and their agents’ observed behavior, a problem of value alignment. Such an alignment problem may have particularly strong consequences when these autonomous systems are used in social contexts that involve some form of collective risk. By means of an evolutionary game theoretical model, we investigate whether errors in the configuration of artificial agents change the outcome of a collective-risk dilemma, in comparison to a scenario with no delegation. Delegation is here distinguished from no-delegation simply by the moment at which a mistake occurs: either when programming/choosing the agent (in case of delegation) or when executing the actions at each round of the game (in case of no-delegation). We find that, while errors decrease success rate, it is better to delegate and commit to a somewhat flawed strategy, perfectly executed by an autonomous agent, than to commit execution errors directly. Our model also shows that in the long-term, delegation strategies should be favored over no-delegation, if given the choice.},

note = {DOI: 10.1038/s41598-024-61153-9},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/384388,

title = {Effects of light regimes on circadian gene co‐expression networks in Arabidopsis thaliana},

author = {Quentin Rivière and Virginie Raskin and Romário Melo and Stéphanie Boutet and Massimiliano Corso and Matthieu Defrance and Alex A. R. Webb and Nathalie Verbruggen and Djoro Armand Anoman},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/384388/3/Plant-Direct-2024.pdf},

year  = {2024},

date = {2024-01-01},

journal = {Plant Direct},

volume = {8},

number = {8},

abstract = {Abstract Light/dark (LD) cycles are responsible for oscillations in gene expression, which modulate several aspects of plant physiology. Those oscillations can persist under constant conditions due to regulation by the circadian oscillator. The response of the transcriptome to light regimes is dynamic and allows plants to adapt rapidly to changing environmental conditions. We compared the transcriptome of Arabidopsis under LD and constant light (LL) for 3 days and identified different gene co‐expression networks in the two light regimes. Our studies yielded unforeseen insights into circadian regulation. Intuitively, we anticipated that gene clusters regulated by the circadian oscillator would display oscillations under LD cycles. However, we found transcripts encoding components of the flavonoid metabolism pathway that were rhythmic in LL but not in LD. We also discovered that the expressions of many stress‐related genes were significantly increased during the dark period in LD relative to the subjective night in LL, whereas the expression of these genes in the light period was similar. The nocturnal pattern of these stress‐related gene expressions suggested a form of “skotoprotection.” The transcriptomics data were made available in a web application named Cyclath , which we believe will be a useful tool to contribute to a better understanding of the impact of light regimes on plants.},

note = {DOI: 10.1002/pld3.70001},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/359132b,

title = {Scale Transfer in 1849: Heinrich Schwabe to Rudolf Wolf},

author = {Shreya Bhattacharya and Laure Lefèvre and Hisashi Hayakawa and Maarten Jansen and Frédéric L. Clette},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/359132/3/2210.03362.pdf},

year  = {2023},

date = {2023-01-01},

journal = {Solar physics},

volume = {298},

number = {1},

pages = {1-12},

note = {Language of publication: fr},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{info:hdl:2013/359639,

title = {Discussion on: ``A scale-free approach for false discovery rate control in generalized linear models'' by Dai, Lin, Zing, Liu.},

author = {G. Claeskens and Maarten Jansen and Jing Zhou},

url = {https://dipot.ulb.ac.be/dspace/bitstream/2013/359639/3/ClaeskensJansenZhou-jasadiscussion.pdf},

year  = {2023},

date = {2023-01-01},

journal = {Journal of the American Statistical Association},

volume = {118},

number = {543},

pages = {1573-1577},

note = {Language of publication: fr},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}