ESPCI web site
Learning causal networks with latent variables from multivariate information in genomic data
Learning causal networks from large-scale genomic data remains challenging in absence of time series or controlled perturbation experiments. We have developed and implemented an information-theoretic method which learns a large class of graphical models from purely observational data. The approach unifies causal and non-causal network learning frameworks while including the effects of unobserved latent variables. Starting from a fully connected graph, it iteratively removes dispensable edges, by uncovering significant information contributions from indirect paths, and assesses edge specific confidences from randomization of available data. The remaining edges are then oriented based on the signature of causality in observational data. The approach and associated algorithm outperform earlier methods on a broad range of benchmark networks and have been applied to reconstruct causal networks at different biological size and time scales, from gene regulation in single cells to whole genome duplication in tumor development as well as long term evolution of vertebrates.