Sparse graphical models in genomics: inference and network enrichment
Veronica Vinciotti (Brunel University London)
Friday 8th December, 2017 15:00-16:00 Maths 311B
Regularized inference of networks using graphical modelling approaches has seen many applications in biology, for example in the inference of regulatory networks from high-dimensional gene expression data. Various extensions to the standard approach have been proposed, such as dynamic graphical models and hierarchical models. In this talk, I will focus on a latest extension to censored graphical models in order to deal with typically censored data such as qPCR data. We propose an EM-like algorithm for the estimation of the conditional independence graph at a reasonable computational cost. Finally, I will discuss a network enrichment test to facilitate the validation of the large networks that are produced by these approaches.