Jean-Philippe Vert - Machine learning for personalized genomics

Organisé par : 
L’équipe "Keynotes" du LIG
Intervenant : 
Jean-Philippe Vert
Jean-Philippe Vert

Information détaillée : 

Jean-Philippe Vert is director of the Centre for Computational Biology at Mines ParisTech, and deputy director of the laboratory for bioinformatics and computational systems biology of cancer at Institut Curie, Paris, France. He graduated from Ecole Polytechnique (1995), Ecole des Mines de Paris (1998) and holds a PhD in mathematics from Paris 6 University (2001). His research interest focuses on statistics, machine learning and their applications to computational and systems biology. He was awarded the bronze medal of CNRS in 2006, and an ERC starting grant for the project "Statistical machine learning for complex biological data" in 2012.

© UMS MI2S / Djamel Hadji

Résumé : 

The development of DNA sequencing technologies allows us to collect large amounts of molecular data about the genome of each individual, and opens the possibility to precisely evaluate the risk of various diseases from one's molecular identity, or to rationally predict which drug is likely to be effective on a particular cancer. It also raises new challenges related to how to extract knowledge from large amounts of noisy data. In this context, I will discuss some regularization-based machine learning approaches we have developed to estimate complex, high-dimensional predictive models from relatively few samples, in particular in cancer prognosis and toxicogenetics.