1.
Njoku, Uchechukwu U. F.; Abelló, Alberto; Bilalli, Besim; Bontempi, Gianluca
On many-objective feature selection and the need for interpretability Journal Article
In: Expert systems with applications, vol. 267, 2025, (DOI: 10.1016/j.eswa.2024.126191).
@article{info:hdl:2013/388988b,
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}
}
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.
2.
Njoku, Uchechukwu U. F.; Abelló, Alberto; Bilalli, Besim; Bontempi, Gianluca
On many-objective feature selection and the need for interpretability Journal Article
In: Expert systems with applications, vol. 267, 2025, (DOI: 10.1016/j.eswa.2024.126191).
@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}
}
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.
3.
Nachtegael, Charlotte
Active learning for biomedical relation extraction, the oligogenic use case PhD Thesis
2024.
@phdthesis{nokey,
title = {Active learning for biomedical relation extraction, the oligogenic use case},
author = {Nachtegael, Charlotte},
url = {https://difusion.ulb.ac.be/vufind/Record/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/375304/Holdings},
year = {2024},
date = {2024-06-28},
abstract = {In a context where technological advancements have enabled increased availability of genetic data through high-throughput sequencing technologies, the complexity of genetic diseases has become increasingly apparent. Oligogenic diseases, characterised by a combination of genetic variants in two or more genes, have emerged as a crucial research area, challenging the traditional model of "one genotype, one phenotype". Thus, understanding the underlying mechanisms and genetic interactions of oligogenic diseases has become a major priority in biomedical research. This context underlines the importance of developing dedicated tools to study these complex diseases.Our first major contribution, OLIDA, is an innovative database designed to collect data on variant combinations responsible for these diseases, filling significant gaps in the current knowledge, focused up until now on the digenic diseases. This resource, accessible via a web platform, adheres to FAIR principles and represents a significant advancement over its predecessor, DIDA, in terms of data curation and quality assessment.Furthermore, to support the biocuration of oligogenic diseases, we used active learning to construct DUVEL, a biomedical corpus focused on digenic variant combinations. To achieve this, we first investigated how to optimise these methods across numerous biomedical relation extraction datasets and developed a web-based platform, ALAMBIC, for text annotation using active learning. Our results and the quality of the corpus obtained demonstrate the effectiveness of active learning methods in biomedical relation annotation tasks.By establishing a curation pipeline for oligogenic diseases, as well as a standards for integrating active learning methods into biocuration, our work represents a significant advancement in the field of biomedical natural language processing and the understanding of oligogenic diseases.
},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
In a context where technological advancements have enabled increased availability of genetic data through high-throughput sequencing technologies, the complexity of genetic diseases has become increasingly apparent. Oligogenic diseases, characterised by a combination of genetic variants in two or more genes, have emerged as a crucial research area, challenging the traditional model of "one genotype, one phenotype". Thus, understanding the underlying mechanisms and genetic interactions of oligogenic diseases has become a major priority in biomedical research. This context underlines the importance of developing dedicated tools to study these complex diseases.Our first major contribution, OLIDA, is an innovative database designed to collect data on variant combinations responsible for these diseases, filling significant gaps in the current knowledge, focused up until now on the digenic diseases. This resource, accessible via a web platform, adheres to FAIR principles and represents a significant advancement over its predecessor, DIDA, in terms of data curation and quality assessment.Furthermore, to support the biocuration of oligogenic diseases, we used active learning to construct DUVEL, a biomedical corpus focused on digenic variant combinations. To achieve this, we first investigated how to optimise these methods across numerous biomedical relation extraction datasets and developed a web-based platform, ALAMBIC, for text annotation using active learning. Our results and the quality of the corpus obtained demonstrate the effectiveness of active learning methods in biomedical relation annotation tasks.By establishing a curation pipeline for oligogenic diseases, as well as a standards for integrating active learning methods into biocuration, our work represents a significant advancement in the field of biomedical natural language processing and the understanding of oligogenic diseases.
4.
Versbraegen, Nassim
Discovering multivariant pathogenic patterns among patients with rare diseases PhD Thesis
2024.
@phdthesis{nokey,
title = {Discovering multivariant pathogenic patterns among patients with rare diseases},
author = {Versbraegen, Nassim},
url = {https://difusion.ulb.ac.be/vufind/Record/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/375378/Holdings},
year = {2024},
date = {2024-06-24},
abstract = {Increasing evidence points to the complex interplay of multiple genetic variants as a major contributing factor in many human diseases. Oligogenic diseases, in which a small set of genes collaborate to cause a pathology, present a compelling example of this phenomenon and necessitate a shift away from traditional single-gene inheritance models. Our work aimed to develop robust methods for pinpointing pathogenic combinations of genetic variants across patient cohorts, ultimately improving disease understanding and potentially guiding future diagnostic approaches.We began by developing a novel machine learning framework that integrates explainable AI (XAI) techniques and game-theoretic concepts. This framework allows us to classify and characterise different types of oligogenic effects, providing insights into the specific mechanisms by which multiple genes interact to drive disease. Next, we focused on refining existing computational methods used to predict the pathogenicity of variant combinations. Our emphasis was two-fold: improving computational efficiency for handling the expansive datasets associated with cohort analysis, and critically, reducing false-positive rates to ensure the reliability of our results. With these tools in hand, we developed a specialised cohort analysis approach tailored to investigating diseases with complex genetic origins. To demonstrate the capabilities of our methodology, we delved into a Marfan syndrome cohort. Marfan syndrome is a hereditary condition affecting the body's connective tissue. Our analysis successfully uncovered potential modifier mutations that appear to interact with the primary disease-causing variant, offering new clues about the intricate genetic landscape of this condition.
},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Increasing evidence points to the complex interplay of multiple genetic variants as a major contributing factor in many human diseases. Oligogenic diseases, in which a small set of genes collaborate to cause a pathology, present a compelling example of this phenomenon and necessitate a shift away from traditional single-gene inheritance models. Our work aimed to develop robust methods for pinpointing pathogenic combinations of genetic variants across patient cohorts, ultimately improving disease understanding and potentially guiding future diagnostic approaches.We began by developing a novel machine learning framework that integrates explainable AI (XAI) techniques and game-theoretic concepts. This framework allows us to classify and characterise different types of oligogenic effects, providing insights into the specific mechanisms by which multiple genes interact to drive disease. Next, we focused on refining existing computational methods used to predict the pathogenicity of variant combinations. Our emphasis was two-fold: improving computational efficiency for handling the expansive datasets associated with cohort analysis, and critically, reducing false-positive rates to ensure the reliability of our results. With these tools in hand, we developed a specialised cohort analysis approach tailored to investigating diseases with complex genetic origins. To demonstrate the capabilities of our methodology, we delved into a Marfan syndrome cohort. Marfan syndrome is a hereditary condition affecting the body's connective tissue. Our analysis successfully uncovered potential modifier mutations that appear to interact with the primary disease-causing variant, offering new clues about the intricate genetic landscape of this condition.
5.
Abels, Axel
2024.
@phdthesis{nokey,
title = {Resolving Knowledge Limitations for Improved Collective Intelligence: A novel online machine learning approach},
author = {Abels, Axel},
url = {https://difusion.ulb.ac.be/vufind/Record/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/373334/Holdings},
year = {2024},
date = {2024-04-23},
urldate = {2024-04-23},
abstract = {One of the reasons human groups struggle to make the best decisions is that they are inherently biased in their beliefs. In essence, our perception of what is true is often distorted by individual and social biases, including stereotypes. When individuals deliberate about a decision, they tend to transmit these beliefs to others, thereby steering the entire group away from the best decision. For example, a senior doctor could spread a misinterpretation of symptoms to junior doctors, resulting in inappropriate treatments. The primary objective of this thesis is to mitigate the impact of such biases on group decision-making in domains such as medical diagnostics, policy-making, and crowdsourced fact-checking. We propose to achieve this by having humans interact through a collective decision-making platform in charge of handling the aggregation of group knowledge. The key hypothesis here is that by carefully managing the collectivization of knowledge through this platform, it will be substantially harder for humans to impose their biases on the final decision. The core of our work involves the development and analysis of algorithms for decision-making systems. These algorithms are designed to effectively aggregate diverse expertise while addressing biases. We thus focus on aggregation methods that use online learning to foster collective intelligence more effectively. In doing so, we take into account the nuances of individual expertise and the impact of biases, aiming to filter out noise and enhance the reliability of collective decisions. Our theoretical analysis of the proposed algorithms is complemented by rigorous testing in both simulated and online experimental environments to validate the system’s effectiveness. Our results demonstrate a significant improvement in performance and reduction in bias influence. These findings not only highlight the potential of technology-assisted decision-making but also underscore the value of addressing human biases in collaborative environments.
},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
One of the reasons human groups struggle to make the best decisions is that they are inherently biased in their beliefs. In essence, our perception of what is true is often distorted by individual and social biases, including stereotypes. When individuals deliberate about a decision, they tend to transmit these beliefs to others, thereby steering the entire group away from the best decision. For example, a senior doctor could spread a misinterpretation of symptoms to junior doctors, resulting in inappropriate treatments. The primary objective of this thesis is to mitigate the impact of such biases on group decision-making in domains such as medical diagnostics, policy-making, and crowdsourced fact-checking. We propose to achieve this by having humans interact through a collective decision-making platform in charge of handling the aggregation of group knowledge. The key hypothesis here is that by carefully managing the collectivization of knowledge through this platform, it will be substantially harder for humans to impose their biases on the final decision. The core of our work involves the development and analysis of algorithms for decision-making systems. These algorithms are designed to effectively aggregate diverse expertise while addressing biases. We thus focus on aggregation methods that use online learning to foster collective intelligence more effectively. In doing so, we take into account the nuances of individual expertise and the impact of biases, aiming to filter out noise and enhance the reliability of collective decisions. Our theoretical analysis of the proposed algorithms is complemented by rigorous testing in both simulated and online experimental environments to validate the system’s effectiveness. Our results demonstrate a significant improvement in performance and reduction in bias influence. These findings not only highlight the potential of technology-assisted decision-making but also underscore the value of addressing human biases in collaborative environments.
6.
Verhelst, Theo
2024.
@phdthesis{nokey,
title = {Causal and predictive modeling of customer churn - Lessons learned from empirical and theoretical research},
author = {Theo Verhelst},
url = {https://difusion.ulb.ac.be/vufind/Record/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/368384/Holdings},
year = {2024},
date = {2024-01-29},
urldate = {2024-01-29},
abstract = {Customer churn is an important concern for large companies, especially in the
telecommunications sector. Customer retention campaigns are often used to mitigate
churn, but targeting the right customers based on their historical profiles
presents an important challenge. Companies usually have recourse to two datadriven
approaches: churn prediction and uplift modeling. In churn prediction,
customers are selected on the basis of their propensity to churn in the near future.
In uplift modeling, only customers who react positively to the campaign
are considered. Uplift modeling is used in various other domains, such as marketing,
healthcare, and finance. Despite the theoretical appeal of uplift modeling, its
added value with respect to conventional machine learning approaches has rarely
been quantified in the literature.
This doctoral thesis is the result of a collaborative research project between
the Machine Learning Group (ULB) and Orange Belgium, funded by Innoviris.
This collaboration offers a unique research opportunity to assess the added value
of causal-oriented strategies to address customer churn in the telecommunication
sector. Following the introduction, we give the necessary background in probability
theory, causality theory, and machine learning, and we describe the state of
the art in uplift modeling and counterfactual identification. Then, we present the
contributions of this thesis:
• An empirical comparison of various predictive and causal models for selecting
customers in churn prevention campaigns. We perform several benchmarks
of different state-of-the-art approaches on real-world datasets and in
live campaigns with our industrial partner, we propose a new approach that
exploits domain knowledge to improve predictions, and we make available
the first public churn dataset for uplift modeling, whose unique characteristics
make it more challenging than the few other public uplift datasets.
• Counterfactual identification allows one to classify the different behaviors
of customers in response to a marketing incentive. This can be used to establish
profiles of customers sensitive to the campaign, and subsequently
improve marketing operations. We derive novel bounds and point estimators
on the probability of counterfactual statements based on uplift models.
• A comprehensive comparison of predictive and uplift modeling, starting
from firm theoretical foundations and highlighting the parameters that influence
the performance of both approaches. In particular, we provide a new
formulation of the measure of profit, a formal proof of the convergence of
the uplift curve to the measure of profit, and an illustration, through simulations,
of the conditions under which predictive approaches still outperform
uplift modeling.
Our theoretical and empirical assessments of uplift modeling suggest that it often
fails to deliver the anticipated advantages over predictive modeling, especially in
scenarios such as customer churn within the telecom sector, characterized by class
imbalance, limited separability, and cost-benefit considerations. These results are
broadly aligned with the practical experience of our industrial partner and with
the existing scientific literature. Our counterfactual probability estimators allow
us to characterize customers at a level inaccessible to conventional predictive modeling,
revealing new insights on the behavior and preferences of customers.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Customer churn is an important concern for large companies, especially in the
telecommunications sector. Customer retention campaigns are often used to mitigate
churn, but targeting the right customers based on their historical profiles
presents an important challenge. Companies usually have recourse to two datadriven
approaches: churn prediction and uplift modeling. In churn prediction,
customers are selected on the basis of their propensity to churn in the near future.
In uplift modeling, only customers who react positively to the campaign
are considered. Uplift modeling is used in various other domains, such as marketing,
healthcare, and finance. Despite the theoretical appeal of uplift modeling, its
added value with respect to conventional machine learning approaches has rarely
been quantified in the literature.
This doctoral thesis is the result of a collaborative research project between
the Machine Learning Group (ULB) and Orange Belgium, funded by Innoviris.
This collaboration offers a unique research opportunity to assess the added value
of causal-oriented strategies to address customer churn in the telecommunication
sector. Following the introduction, we give the necessary background in probability
theory, causality theory, and machine learning, and we describe the state of
the art in uplift modeling and counterfactual identification. Then, we present the
contributions of this thesis:
• An empirical comparison of various predictive and causal models for selecting
customers in churn prevention campaigns. We perform several benchmarks
of different state-of-the-art approaches on real-world datasets and in
live campaigns with our industrial partner, we propose a new approach that
exploits domain knowledge to improve predictions, and we make available
the first public churn dataset for uplift modeling, whose unique characteristics
make it more challenging than the few other public uplift datasets.
• Counterfactual identification allows one to classify the different behaviors
of customers in response to a marketing incentive. This can be used to establish
profiles of customers sensitive to the campaign, and subsequently
improve marketing operations. We derive novel bounds and point estimators
on the probability of counterfactual statements based on uplift models.
• A comprehensive comparison of predictive and uplift modeling, starting
from firm theoretical foundations and highlighting the parameters that influence
the performance of both approaches. In particular, we provide a new
formulation of the measure of profit, a formal proof of the convergence of
the uplift curve to the measure of profit, and an illustration, through simulations,
of the conditions under which predictive approaches still outperform
uplift modeling.
Our theoretical and empirical assessments of uplift modeling suggest that it often
fails to deliver the anticipated advantages over predictive modeling, especially in
scenarios such as customer churn within the telecom sector, characterized by class
imbalance, limited separability, and cost-benefit considerations. These results are
broadly aligned with the practical experience of our industrial partner and with
the existing scientific literature. Our counterfactual probability estimators allow
us to characterize customers at a level inaccessible to conventional predictive modeling,
revealing new insights on the behavior and preferences of customers.
telecommunications sector. Customer retention campaigns are often used to mitigate
churn, but targeting the right customers based on their historical profiles
presents an important challenge. Companies usually have recourse to two datadriven
approaches: churn prediction and uplift modeling. In churn prediction,
customers are selected on the basis of their propensity to churn in the near future.
In uplift modeling, only customers who react positively to the campaign
are considered. Uplift modeling is used in various other domains, such as marketing,
healthcare, and finance. Despite the theoretical appeal of uplift modeling, its
added value with respect to conventional machine learning approaches has rarely
been quantified in the literature.
This doctoral thesis is the result of a collaborative research project between
the Machine Learning Group (ULB) and Orange Belgium, funded by Innoviris.
This collaboration offers a unique research opportunity to assess the added value
of causal-oriented strategies to address customer churn in the telecommunication
sector. Following the introduction, we give the necessary background in probability
theory, causality theory, and machine learning, and we describe the state of
the art in uplift modeling and counterfactual identification. Then, we present the
contributions of this thesis:
• An empirical comparison of various predictive and causal models for selecting
customers in churn prevention campaigns. We perform several benchmarks
of different state-of-the-art approaches on real-world datasets and in
live campaigns with our industrial partner, we propose a new approach that
exploits domain knowledge to improve predictions, and we make available
the first public churn dataset for uplift modeling, whose unique characteristics
make it more challenging than the few other public uplift datasets.
• Counterfactual identification allows one to classify the different behaviors
of customers in response to a marketing incentive. This can be used to establish
profiles of customers sensitive to the campaign, and subsequently
improve marketing operations. We derive novel bounds and point estimators
on the probability of counterfactual statements based on uplift models.
• A comprehensive comparison of predictive and uplift modeling, starting
from firm theoretical foundations and highlighting the parameters that influence
the performance of both approaches. In particular, we provide a new
formulation of the measure of profit, a formal proof of the convergence of
the uplift curve to the measure of profit, and an illustration, through simulations,
of the conditions under which predictive approaches still outperform
uplift modeling.
Our theoretical and empirical assessments of uplift modeling suggest that it often
fails to deliver the anticipated advantages over predictive modeling, especially in
scenarios such as customer churn within the telecom sector, characterized by class
imbalance, limited separability, and cost-benefit considerations. These results are
broadly aligned with the practical experience of our industrial partner and with
the existing scientific literature. Our counterfactual probability estimators allow
us to characterize customers at a level inaccessible to conventional predictive modeling,
revealing new insights on the behavior and preferences of customers.
7.
Terrucha, Ines; Domingos, Elias Fernandez; Suchon, Remi; Santos, Francisco C; Simoens, Pieter; Lenaerts, Tom
Humans program artificial delegates to accurately solve collective-risk dilemmas, but lack precision Miscellaneous
2024, (Conference: Machine+behavior Conference(Berlin, Allemagne)).
@misc{info:hdl:2013/385912b,
title = {Humans program artificial delegates to accurately solve collective-risk dilemmas, but lack precision},
author = {Ines Terrucha and Elias Fernandez Domingos and Remi Suchon and Francisco C Santos and Pieter Simoens and Tom Lenaerts},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/385912},
year = {2024},
date = {2024-01-01},
note = {Conference: Machine+behavior Conference(Berlin, Allemagne)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
8.
Kirchsteiger, Georg; Lenaerts, Tom; Suchon, Remi
Growing cooperation Miscellaneous
2024, (Conference: Conference of the French Experimental Economics Association(14: grenoble, France)).
@misc{info:hdl:2013/385911b,
title = {Growing cooperation},
author = {Georg Kirchsteiger and Tom Lenaerts and Remi Suchon},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/385911},
year = {2024},
date = {2024-01-01},
note = {Conference: Conference of the French Experimental Economics Association(14: grenoble, France)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
9.
Bosch, Inas; Gravel, Barbara; Lenaerts, Tom
Knowledge graph embeddings for the prediction of pathogenic gene pairs Miscellaneous
2024, (Conference: European Conference on Computational Biology.(23: 16/09-20/09/2024: Turku, Finland)).
@misc{info:hdl:2013/385910b,
title = {Knowledge graph embeddings for the prediction of pathogenic gene pairs},
author = {Inas Bosch and Barbara Gravel and Tom Lenaerts},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/385910},
year = {2024},
date = {2024-01-01},
note = {Conference: European Conference on Computational Biology.(23: 16/09-20/09/2024: Turku, Finland)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
10.
Gravel, Barbara; Renaux, Alexandre; Papadimitriou, Sofia; Smits, Guillaume; Nowé, Ann; Lenaerts, Tom
Prioritization of variant combinations in whole exomes Miscellaneous
2024, (Conference: European Conference on Computational Biology.(23: 16/09-20/09/2024: Turku, Finland)).
@misc{info:hdl:2013/385909b,
title = {Prioritization of variant combinations in whole exomes},
author = {Barbara Gravel and Alexandre Renaux and Sofia Papadimitriou and Guillaume Smits and Ann Nowé and Tom Lenaerts},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/385909},
year = {2024},
date = {2024-01-01},
note = {Conference: European Conference on Computational Biology.(23: 16/09-20/09/2024: Turku, Finland)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
11.
Abels, Axel; Lenaerts, Tom; Trianni, Vito; Nowé, Ann
Dealing with Expert Bias in Collective Decision-making Miscellaneous
2024, (Conference: European Conference on Artificial Intelligence(27: 19/10-24/10/2024: Santiago de Compostella)).
@misc{info:hdl:2013/385908b,
title = {Dealing with Expert Bias in Collective Decision-making},
author = {Axel Abels and Tom Lenaerts and Vito Trianni and Ann Nowé},
url = {http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/385908},
year = {2024},
date = {2024-01-01},
note = {Conference: European Conference on Artificial Intelligence(27: 19/10-24/10/2024: Santiago de Compostella)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
12.
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:2013/385907b,
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}
}
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.
13.
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:2013/370546b,
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}
}
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.
14.
Attafi, Omar Abdelghani; Clementel, Damiano; Kyritsis, Konstantinos; Capriotti, Emidio; Farrell, Gavin; Fragkouli, Styliani-Christina; Castro, Leyla Jael; Hatos, András; Lenaerts, Tom; Mazurenko, Stanislav; Mozaffari, Soroush; Pradelli, Franco; Ruch, Patrick; Savojardo, Castrense; Turina, Maria Paola; Zambelli, Federico; Piovesan, Damiano; Monzon, Alexander Miguel; Psomopoulos, Fotis F. E.; Tosatto, Silvio S. C. E.
DOME Registry: implementing community-wide recommendations for reporting supervised machine learning in biology Journal Article
In: GigaScience, vol. 13, pp. 8, 2024, (DOI: 10.1093/gigascience/giae094).
@article{info:hdl:2013/385906b,
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}
}
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.
15.
Juchnewitsch, Anna Grete; Pomm, Kristjan; Dutta, Avirup; Tamp, Erik; Valkna, Anu; Lillepea, Kristiina; Mahyari, Eisa; Tjagur, Stanislav; Belova, Galina; Kübarsepp, Viljo; Castillo-Madeen, Helen; Riera-Escamilla, Antoni; Põlluaas, Lisanna; Nagirnaja, Liina; Poolamets, Olev; Vihljajev, Vladimir; Sütt, Mailis; Versbraegen, Nassim; Papadimitriou, Sofia; McLachlan, Robert Ian; Jarvi, Keith Allen; Schlegel, Peter P. N.; Tennisberg, Sven; Korrovits, Paul; Vigh-Conrad, Katinka; O’Bryan, Moira M. K.; Aston, Kenneth Ivan; Lenaerts, Tom; Conrad, Donald D. F.; Kasak, Laura; Punab, Margus; Laan, Maris
Undiagnosed RASopathies in infertile men Journal Article
In: Frontiers in endocrinology, vol. 15, 2024, (DOI: 10.3389/fendo.2024.1312357).
@article{info:hdl:2013/374860b,
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}
}
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
16.
Stefanija, Ana Pop; Buelens, Bart; Goesaert, Elfi; Lenaerts, Tom; Pierson, Jean René; den Bussche, Jan Van
Toward a Solid Acceptance of the Decentralized Web of Personal Data: Societal and Technological Convergence Journal Article
In: Communications of the ACM, vol. 67, no. 1, pp. 43-46, 2024, (DOI: 10.1145/3624555).
@article{info:hdl:2013/367025b,
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 den 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}
}
Giving individuals more control of their personal data.
17.
Lenaerts, Tom; Saponara, Marco; Pacheco, Jorge J. M.; Santos, Francisco C.
Evolution of a theory of mind Journal Article
In: iScience, vol. 27, no. 2, 2024, (DOI: 10.1016/j.isci.2024.108862).
@article{info:hdl:2013/372022b,
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}
}
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.
18.
Terrucha, Ines; Domingos, Elias Fernández; Santos, Francisco C.; Simoens, Pieter; Lenaerts, Tom
The art of compensation: How hybrid teams solve collective-risk dilemmas Journal Article
In: PloS one, vol. 19, no. 2 February, 2024, (DOI: 10.1371/journal.pone.0297213).
@article{info:hdl:2013/371876b,
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}
}
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.
19.
Gravel, Barbara; Renaux, Alexandre; Papadimitriou, Sofia; Smits, Guillaume; Nowe, Ann; Lenaerts, Tom
Prioritization of oligogenic variant combinations in whole exomes Journal Article
In: Bioinformatics, vol. 40, no. 4, 2024, (DOI: 10.1093/bioinformatics/btae184).
@article{info:hdl:2013/374647b,
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}
}
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.
20.
Lillepea, Kristiina; Juchnewitsch, Anna Grete; Kasak, Laura; Valkna, Anu; Dutta, Avirup; Pomm, Kristjan; Poolamets, Olev; Nagirnaja, Liina; Tamp, Erik; Mahyari, Eisa; Vihljajev, Vladimir; Tjagur, Stanislav; Papadimitriou, Sofia; Riera-Escamilla, Antoni; Versbraegen, Nassim; Farnetani, Ginevra; Castillo-Madeen, Helen; Sütt, Mailis; Kübarsepp, Viljo; Tennisberg, Sven; Korrovits, Paul; Krausz, Csilla; Aston, Kenneth Ivan; Lenaerts, Tom; Conrad, Donald D. F.; Punab, Margus; Laan, Maris
Toward clinical exomes in diagnostics and management of male infertility Journal Article
In: American journal of human genetics, vol. 111, no. 5, pp. 877-895, 2024, (DOI: 10.1016/j.ajhg.2024.03.013).
@article{info:hdl:2013/374767b,
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}
}
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.