De-noise biological network from heterogeneous sources via link propagation

Lots of recent bioinformatics works have focused on the inference of various types of biological networks, such as gene coexpression networks, protein-protein interaction networks, signal transduction networks, etc. Unfortunately, these raw biological network data often contain much noise, especially the false positive predictions which in many cases hinder accurate reconstruction of biological networks. In addition, since the labeled data is scarce and expensive, we hope that the knowledge from other domains can help handle this lack of labeled data problem. In order to construct a more robust and reliable biological network, we propose a novel link propagation based algorithm to de-noise false positives from the target biological network through propagating information from few labeled samples and a set of auxiliary domain networks. While comparing with many current state-of-the-art algorithms, our proposed approach has shown good performance in de-noising biological network.