Overlapping Functional Modules Detection in PPI Network with Pairwise Constrained Nonnegative Matrix Tri-Factorization

Uncovering functional modules from PPI networks will help us to better understand the mechanism of cellular. Numerous computational algorithms have been designed to identify functional modules automatically in the past decades. However, most community detection methods are unsupervised models and the known protein complexes have not been considered by them. In this paper, we propose a novel semi-supervised model named pairwise constrains nonnegative matrix tri-factorization (PCNMTF), which takes full advantage of the usable well known complexes to find overlapping functional modules based on protein module indicator matrix and module correlation matrix simultaneously from PPI networks. The experiment results demonstrate that PCNMTF gains more precious functional modules by integrating PPI network and known protein complexes than state-of-art methods.