Differences in how patients experience disease can be explained in great part by their genomic differences. Enabling precision medicine hence requires identifying genomic features associated with disease risk, prognosis or response to treatment. This is often achieved using genome-wide association studies (GWAS), which look for associations between single nucleotide polymorphisms (SNPs) and a phenotype. However, for many complex traits, the SNPs they uncovered account for little of the known heritable variation.

SCAPHE builds on the hypothesis that this is due to the effect of non-additive interactions between SNPs, together with a lack of robustness stemming from the relatively small sample sizes. This last issue can be alleviated by integrating biological networks to GWAS. Hence SCAPHE proposes to develop novel machine learning algorithms for GWAS, integrating biological networks and modeling non-additive SNP effects, to robustly detect SNP combinations associated with a phenotype.

SCAPHE was funded by ANR JCJC 2018, a program by the French National Research Agency to fund Young Researchers.

You can find the full text of the proposal here (pdf) and a summary of what we did here (pdf).

logo « financé par l'ANR »

People

People who took part in SCAPHE:

Publications, preprints

  • Héctor Climente-González, Chloé-Agathe Azencott, Makoto Yamada. A network-guided protocol to discover susceptibility genes in genome-wide association studies using stability selection. [link] (2023).
  • Diane Duroux, Héctor Climente-González, Chloé-Agathe Azencott and Kristel Van Steen. Interpretable network-guided epistasis detection. [link] (2022).
  • Asma Nouira, Stable feature selection for multi-locus Genome-Wide Association Studies, PhD dissertation, Paris Sciences et Lettres Research University [theses.fr] [pdf] (2022).
  • Asma Nouira and Chloé-Agathe Azencott. Multitask group Lasso for Genome Wide Association Studies in diverse populations. [link] [biorxiv] (2022).
  • Lotfi Slim, Hélène de Foucauld, Clément Chatelain and Chloé-Agathe Azencott. A systematic analysis of gene-gene interaction in multiple sclerosis. [link] (2022).
  • Lotfi Slim, Clément Chatelain, and Chloé-Agathe Azencott. Nonlinear post-selection inference for genome-wide association studies. [link] [biorxiv] (2022).
  • Héctor Climente-González, Christine Lonjou, Fabienne Lesueur, GENESIS Study collaborators, Dominique Stoppa-Lyonnet, Nadine Andrieu, Chloé-Agathe Azencott. Boosting GWAS using biological networks: A study on susceptibility to familial breast cancer, PLoS Computational Biology (2021).
  • Héctor Climente-González, Chloé-Agathe Azencott. martini: an R package for genome-wide association studies using SNP networks BioRxiv (2021).

Code

Events

SCAPHE allowed us to attend ISMB/ECCB 2019, ProbGen 2019, ISMB/ECCB 2021 and PSB 2022.

Data

SCAPHE allowed us to work with data from the UK BioBank.

Talks and posters

  • Lotfi Slim, Clément Chatelain, and Chloé-Agathe Azencott. Nonlinear post-selection inference for genome-wide association studies, PSB, Hawaii, United States, 2022 (contributed).
  • Asma Nouira and Chloé-Agathe Azencott. Multitask group Lasso for Genome Wide Association Studies in diverse populations, PSB, Hawaii, United States, 2022 (contributed). [slides]
  • Asma Nouira, Multitask group Lasso for Genome Wide Association Studies in diverse populations, NutriOmics Seminar, Paris, France, 2021 (invited) [slides]
  • Chloé-Agathe Azencott. Network-guided genome-wide association studies, UCSF BBC Seminar Series, San Francisco, United States, 2021 (online, invited)
  • Asma Nouira and Chloé-Agathe Azencott. Multitask group Lasso for Genome Wide Association Studies in diverse populations, MLCSB track at ISMB, 2021 (oral and poster, contributed) [poster]
  • Lotfi Slim, Clément Chatelain and Chloé-Agathe Azencott. Nonlinear post-selection inference for genome-wide association studies, MLCB, 2020 (spotlight, contributed)
  • Chloé-Agathe Azencott. AI for Genomic - Machine learning and high-dimensional genomic data, AI for Health, 2020 (online)
  • Asma Nouira, Chloé-Agathe Azencott, Multitask group lasso for genome-wide association studies, SMPGD 2020, 2020 (poster, contributed) [poster]
  • Chloé-Agathe Azencott. Non-linear feature selection in high-dimensional genomic data sets , Neyman Seminar, Berkeley, CA, USA, 2019 (invited). [slides].
  • Chloé-Agathe Azencott. Feature selection in high-dimensional genomic data, France is AI 2019, Paris, France, 2019 (invited). [slides].
  • Lotfi Slim, Clément Chatelain, Chloé-Agathe Azencott and Jean-Philippe Vert. kernelPSI: a powerful post-selection inference framework for nonlinear association testing in genome-wide association studies, ProbGen, 2019 (oral, contributed)
  • Héctor Climente-González, Chloé-Agathe Azencott, Samuel Kaski and Makoto Yamada. Block HSIC Lasso: model-free biomarker detection for ultra-high dimensional data. ISMB/ECCB, 2019 (oral, contributed)
  • Chloé-Agathe Azencott. Structured feature selection for biomarker discovery in precision medicine, JOBIM 2019, Nantes, France, 2019 (invited). [slides]