22/03 - Laurent Tichit (IMM) : Random Walk with Restart on Multilayer Biological Networks

Random walk with restart is the state-of-the-art guilt-by-association approach. It explores the network vicinity of gene/protein seeds to study their functions, based on the premise that nodes related to similar functions tend to lie close to each other in the networks.

We extended the RWR algorithm to multilayer networks. The walk can now explore different layers of physical and functional interactions between genes and proteins. It can also jump to a network containing different sets of edges and nodes, such as phenotype similarities between diseases. We devised a leave-one-out cross-validation strategy to evaluate the algorithms abilities to predict disease-associated genes. Finally, we applied the algorithm to predict candidate genes for two genetic diseases: the Wiedemann-Rautenstrauch progeroid syndrome and the SHORT syndrome.