Title: A graph-based integrative method of detecting consistent protein functional modules from multiple data sources

Authors: Yuan Zhang; Yue Cheng; Liang Ge; Nan Du; Kebin Jia; Aidong Zhang

Addresses: Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China ' Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China ' Department of Computer Science and Engineering, State University of New York, Buffalo, NY 14260, USA ' Department of Computer Science and Engineering, State University of New York, Buffalo, NY 14260, USA ' Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China ' Department of Computer Science and Engineering, State University of New York, Buffalo, NY 14260, USA

Abstract: Many clustering methods have been developed to identify functional modules in Protein-Protein Interaction (PPI) networks but the results are far from satisfaction. To overcome the noise and incomplete problems of PPI networks and find more accurate and stable functional modules, we propose an integrative method, bipartite graph-based Non-negative Matrix Factorisation method (BiNMF), in which we adopt multiple biological data sources as different views that describe PPIs. Specifically, traditional clustering models are adopted as preliminary analysis of different views of protein functional similarity. Then the intermediate clustering results are represented by a bipartite graph which can comprehensively represent the relationships between proteins and intermediate clusters and finally overlapping clustering results are achieved. Through extensive experiments, we see that our method is superior to baseline methods and detailed analysis has demonstrated the benefits of integrating diverse clustering methods and multiple biological information sources.

Keywords: PPI networks; protein-protein interaction; multiple data sources; biological data integration; consensus mining; functional module detection; non-negative matrix factorisation; bioinformatics; protein functional similarity; bipartite graphs.

DOI: 10.1504/IJDMB.2015.071534

International Journal of Data Mining and Bioinformatics, 2015 Vol.13 No.2, pp.122 - 140

Received: 16 Jul 2013
Accepted: 24 Jun 2014
Published online: 31 Aug 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article