Discriminative Random Walks with Restart (DRaWR)
DRaWR is a network-based method for ranking genes or properties related to a given gene set that is designed to operate on large, heterogeneous networks of biological information. Our method involves a random walk with restarts, performed on an initial network with multiple node and edge types that preserves more of the original, specific property information than homogeneous networks typically utilized by related methods. In this first stage of our algorithm, we find the property nodes that are the most relevant to the given gene set and extract a subnetwork of the original network, comprising only the relevant properties. We then rerank genes by their similarity to the given gene set, based on a second random walk with restarts, performed on the relavent subnetwork. We demonstrate the effectiveness of this algorithm for ranking genes related to Drosophila embryonic development and aggressive responses in the brains of social animals.