Inferring Multiple Regulation Networks
Julien Chiquet, Yves Grandvalet and Christophe Ambroise
In: MLCB 2010, 10 Dec 2010, Whistler, Canada.
Gaussian Graphical Models provide a convenient framework for representing dependencies between variables. Recently, this tool has received a high interest for the discovery of biological networks. The literature focuses on the case where a single network is inferred from a set of measurements, but, as data is typically scarce, several assays, where the experimental conditions affect interactions, are usually merged to infer a single network. In this paper, we describe an approach for estimating several related networks, by rendering the closeness assumption into group penalties. We provide quantitative results demonstrating the benefits of the proposed approach on artificial and real data.