Since May 2025, I have been a postdoctoral researcher in bioinformatics at the Autorité de Sûreté Nucléaire et de Radioprotection (ASNR) , in collaboration with the CEA and EDF. My research focuses on studying the impact of low radiation doses on the development of thyroid cancer using multi-omics data.

From March 2023 to March 2025, I was a postdoctoral researcher at the BioSTM lab, Faculté de Pharmacie de Paris, Université Paris Cité under the supervision of Marie Verbanck . My research focuses on developing machine learning methods to explore pleiotropy in human genetic architecture and create a comprehensive map of pleiotropic effects. Before that, I have been a PhD Student in Computational Biology at CBIO team in MINES ParisTech and Institut Curie . I was working under the supervision of Chloé-Agathe Azencott.

About me

I defended my PhD on July 13th, 2022, and my thesis manuscript is online here . The main goal of my thesis is to develop a stable framework for biomarker discovery in multi-locus Genome-Wide Association Studies (GWAS) using Machine Learning, essentially feature selection models to deal with high-dimensional data. The aim is to find an association between the genotype and the phenotype, particularly in breast cancer. I addressed key challenges such as genetic population stratification, linkage disequilibrium patterns clustering, and the stability of the feature selection... In 2017, I obtained my engineering diploma in embedded systems at the National Engineering School of Sousse (ENISo), Tunisia. I later completed a Master's degree in Intelligent Communicating Systems in 2018 at the same school. I did an internship at the East Paris Institute of Chemistry and Materials Science (ICMPE) in Paris, where I applied Machine learning techniques to discover new chemical compounds for hydrogen storage. This project was supervised by Jean-Claude Crivello and Nataliya Sokolovoska .

Research Interests

My research lies at the intersection of machine learning, statistical genetics and computational biology. I am particularly interested in developing interpretable machine learning and statistical methods for the analysis of high-dimensional multi-omics data to better understand complex diseases.

  • Machine Learning for Computational Biology
  • Statistical Genetics and Genome-Wide Association Studies (GWAS)
  • Multi-omics Data Integration
  • Graphical Models and Network Inference
  • Feature Selection in High-dimensional Data
  • Pleiotropy and Human Genetic Architecture

Talks and Posters

  • 30 June-1 July, 2026. Latent Differential Graphical model for Multi-Tissue and Multi-Omics integration to model molecular interaction networks under multiple Radiation Exposure groups. JOBIM 2026, Strasbourg (France) [Talk]
  • January 30, 2025. Machine Learning and Statistical Methods for Identifying Causal Variants While Accounting for Linkage Disequilibrium and Population Stratification. AMIB(IO) seminar, Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Orsay. [Invited talk]
  • March 17, 2022. Multi-task group Lasso for Genome-Wide Association Studies. The Junior Seminar in Artificial Intelligence and Digital Healthcare, Paris (France). [Invited talk]
  • February 3, 2022. Multi-task group Lasso for Genome-Wide Association Studies in diverse populations. Institut Curie, Paris (France). [Talk]
  • January 6, 2022. Multi-task group Lasso for Genome-Wide Association Studies in diverse populations. Pacific Symposium on Biocomputing (PSB 2022), Hawaii (USA). [Talk]
  • October 25, 2021. Multi-task group Lasso for Genome-Wide Association Studies in diverse populations. NutriOmics seminar. [Invited talk]
  • July 29, 2021. Multi-task group Lasso for admixed populations in Genome-Wide Association Studies. Intelligent Systems for Molecular Biology (ISMB 2021), MLCSB COSI. [Talk] [Poster]
  • January 28, 2021. Stable Multi-task feature selection approach for Genome-Wide Association Studies. Institut Curie, Paris (France). [Talk]
  • March 11, 2020. Multi-task group Lasso correcting for population stratification in Genome-Wide Association Studies. Institut Curie, Paris (France).[Talk]
  • January 23, 2020. Multi-task group lasso for Genome-Wide Association Studies. Statistical Methods for Post Genomic Data (SMPGD 2020), Institut Pasteur, Paris (France). [Poster]

Publications

  • Ory. C., Jouannet. C., Panunzi. L., Nouira. A. et al., Post-Chornobyl thyroid papillary carcinomas display distinct past 131I exposure and radiation-associated carcinogenesis molecular signatures at low and high thyroid doses. Scientific Reports 2026 [Full paper].

  • Nouira. A., Tournaire. M., Favre Moiron. M., Verbanck M., Deriving LD-adjusted GWAS summary statistics through linkage disequilibrium deconvolution. preprint 2026. [Full paper].

  • Nouira. A., Azencottt. C-A, Sparse multitask group Lasso for genome-wide association studies. PLOS Computational Biology 2025. [Full paper].

  • Tournaire. M., Nouira. A., Favre Moiron. M., Rozenholc. Y., Verbanck M., Inferring genetic variant networks by leveraging pleiotropy shows trait relationships drive massive pleiotropy in GWAS. preprint 2024. [Full paper].

  • Nouira. A., Azencottt. C-A, Multi-task group lasso for Genome-Wide Association Studies in diverse populations. Pacific Symposium on Biocomputing (PSB) 2022. [Full paper] [Supplementary Materials]

GitHub Repositories

  • Multi-DiffNet : Latent Differential Graphical model for Multi-Tissue and Multi-Omics integration.
  • SMuGLasso : Sparse Multitask group lasso for Genome-Wide Association Studies in diverse populations.
  • MuGLasso_GWAS : Multitask group lasso for Genome-Wide Association Studies in diverse populations.
  • GWAS-admixed-population-simulator : Simulating case-control admixed-population GWAS data in PLINK format.
  • CrystalGAN : Learning to Discover Crystallographic Structures with Generative Adversarial Networks.
  • Crystal-tools : Useful tools for the preprocessing of CrystalGAN.

Teaching