We have announced the winners of the Idea DREAM Challenge! Now looking forward to seeing these two new DREAM Challenges happen.

I'm currently working on a series of online machine learning courses in French, as part of OpenClassrooms's Data Scientist path.

Magnus Rattray and are I organizing the 11th Machine Learning for Systems Biology workshop as a special session at ISMB/ECCB 2017 in Prague on July 25.

I am a researcher at the Centre for Computational Biology (CBIO) of ARMINES/MINES ParisTech, Institut Curie and INSERM (which are all part of PSL Research University). My research interests revolve around machine learning techniques for therapeutic research.

Research interests

I focus on the development of methods for efficient multi-locus biomarker discovery. Essentially, my goal is to make sense of data with a small number of samples and a large number of variables. These variables can be clinical variables (such as age, cholesterol levels or smoking history) or genetic variables (such as gene expression, mutations, or epigenetic markers). How can we find out which of them play a role in a particular biological process or pathology? My work has numerous applications, in particular in precision medicine, where we try to develop treatments that are adapted to the (genetic) specificities of patients, by contrast with a classical one-size-fits-all approach.

I am interested in the incorporation of additional (structured) information, for example as biological networks; in multi-task approaches, where one addresses multiple related problems simultaneously; and in the development of fast but accurate techniques to address these issues. In terms of machine learning, a lot of my work is linked to structured sparsity. This has led for example to the development of SConES (Selecting CONected Explanatory SNPs), a method for network-guided multi-locus association mapping based on graph cuts.

I am also currently working on projects involving the analysis of various types of biological networks, as well as on a project to suggest the mechanisms of action of drug candidates from the results of a biological screen.

Short bio

Previously I have worked in the area of chemoinformatics and drug design (more particularly, virtual high-throughput screening) during my PhD at UC Irvine with Pierre Baldi. I switched my focus to the other side of the coin during my postdoctoral stay at the Max Planck Institutes for Developmental Biology and Intelligent Systems in Tübingen, where I worked with Karsten Borgwardt as a member of the Machine Learning and Computational Biology (MLCB) research group on methods for genome-wide association studies. I joined CBIO in December 2013.


Are you trying to organize a gender-balanced machine learning event, but find yourself unable to find women speakers? WiML has a great list of women active in machine learning.


  • Víctor Bellón
    Adverse drug reaction discovery
    PhD student at MINES ParisTech since January 2014
    Joint supervision with Véronique Stoven.
  • Christophe Le Priol
    Systemic analysis of the micro-RNAs involved in epithelial cancers
    PhD student at CEA since January 2016
    Joint supervision with Xavier Gidrol.
  • Héctor Climente González
    Integrating structural constraints in multi-locus genome-wide association studies
    PhD student since October 2016
    Joint supervision with Véronique Stoven.
  • Lotfi Slim
    Detection of epistasis in genome-wide association studies with machine learning methods for biomarkers and therapeutic target identification
    PhD student since December 2016
    Joint supervision with Jean-Philippe Vert and Clément Chatelain



I teach lectures related to bioinformatics, machine learning and drug discovery at several places, including MINES ParisTech, Centrale Paris and Paris-Diderot. I'm also teaching online courses (in French) at OpenClassrooms. See my teaching page for more details.