Machine learning and causal inference for -omics data

I am interested in machine learning and causal inference methods to better understand structure, function, regulation, and evolution of genomes. I develop methods to discover hidden patterns in large datasets, often related to next-generation sequencing technologies.

Some of the projects that are currently keeping me busy are:

• Machine learning methods to discover novel secretion system types, with Sophie Abby.

• Understanding how proteins evolve, through the development of unsupervised learning techniques to uncover patterns of co-evolution in protein sequences, with Ivan Junier.

• Transcriptomic-guided inference of proteomic missing data, with Lucas Etourneau and Thomas Burger

About me

I am a CNRS research faculty at the Université Grenoble Alpes’s TIMC laboratory, in the TrEE team. Specifically, I am part of the CompBio subgroup TrEE, also known as CompBio@TrEE. TrEE is a large interdisciplinary team interested in anything related to evolution, from the evolution of specific pathways to experimental evolution (via the study of the Long Term E. coli Evolution Experiment). The CompBio@TrEE is composed of three permanent researchers (Sophie Abby, Ivan Junier, and myself) as well as many postdocs, PhD students, and interns.

Scientific computing activities

I am a contributor in a number of scientific computing libraries in Python including:

• scikit-learn - Machine learning in Python.
• matplotlib - a python 2D plotting library.

Joining the lab

We’re always looking for students from a wide range of background (statistics, computer science, biology) to join our lab for internships! If the possibility of being a part of our community interests you, don’t hesitate to look at our current internship, PhD, and postdoc opportunities or simply reaching out to me directly (e-mail: firstname [dot] lastname [at] univ-grenoble-alpes [dot] fr), detailing your profile and what you are interested in.