Deep learning for omics data : Application to phenotype prediction based in gene expression data

In the first part of the talk, I will make a quick state of the art of the problems in “omics” data analysis in which deep learning has been used successfully. Then I will present our work on the prediction of phenotype based on gene expression data with a deep neural network. In this task, we focus on two issues: the learning with a small training set and the interpretation of the network. For the small training set problem, we propose methods based on transfer learning and semi-supervised learning. For interpretation, we backpropagate the predictions through the network in order to identify relevant genes and neurons that we associate them to biological knowledge.

Biography

2006: Phd University Paris 13 (Supervised learning for transcriptomic data)
2008 - 2015: Lecturer at the LIPADE laboratory (Univ. Paris Descartes)
Since 2015 : University professor at the IBISC laboratory (univ. Evry)

Field of research :
- Machine learning: Supervised learning, Deep learning, Anomaly detection, Dimension reduction, Biclustering, ensemble methods.
- Applications: Personalized medicine, Ohmic data, Diagnostic system, Autonomous transport, preventive maintenance.
- Current research: Deep learning, Application to genomics and health