Supervised Inference of Gene Regulatory Networks from Positive and Unlabeled Examples

Elucidating the structure of gene regulatory networks (GRN), i.e., identifying which genes are under control of which transcription factors, is an important challenge to gain insight on a cell’s working mechanisms. We present SIRENE, a method to estimate a GRN from a collection of expression data. Contrary to most existing methods for GRN inference, SIRENE requires as input a list of known regulations, in addition to expression data, and implements a supervised machine-learning approach based on learning from positive and unlabeled examples to account for the lack of negative examples.