This SemoVi was held in Grenoble, amphi 22 de l'IM2AG, 60 rue de la chimie, BP 53, 38041 Grenoble cedex 09.
| 14h00 - 15h00 |
Jean-Philippe Vert, More information on the Jean-Philippe Vert website |
Machine learning for personalized genomics |
|---|---|---|
| 15h00 - 15h30 | Pause café | |
| 15h30 - 16h30 |
Laurent Jacob, LBBE Gérard Benoit, CGPHIMC |
Statistical inference on large feature sets for biological sequences Retinoic Acid Receptors: where and when to interact with DNA? |
| 16h30 - 17h00 | Discussion Générale |
Jean-Philippe Vert
Machine learning for personalized genomics
The genomic characterization of individual biological samples paves the way to personalized approaches to health care, such as deciding which treatment to give for cancer treatment, or predicting the toxicity of a chemical on an individual. I will discuss a few machine learning-based approaches that we developed to build such predictive models.
Gérard Benoit
Retinoic Acid Receptors: Where and when to interact with DNA?
Since the early days of molecular biology, understanding how genetic information is selectively expressed in living organisms is an issue that mobilizes a large part of the biologist community. As a consequence, the early concepts derived from prokaryotic models were progressively refine to propose a more complex and dynamic view of the intricate molecular mechanisms supporting transcriptional regulation in eucaryotic systems. The introduction of cistromic and transcriptomic analyses now offers the possibility to explore this issue at a the genomic level and shed new light on this fundamental biological mechanisms.
Laurent Jacob
Statistical inference on large feature sets for biological sequences
Several estimation problems in computational biology involving sequences lead to considering sets of features with size exponential in the sequence length. These feature sets correspond to combinations of sequence elements. They are typically too large to be explicitly described and manipulated, but can be represented as a set of paths on particular graphs. We use this implicit representation to make estimation possible.
Download poster here
THIS SEMINAR IS SPONSORED BY :
