Title: ACC-FMD: ant colony clustering for functional module detection in protein-protein interaction networks

Authors: Junzhong Ji; Hongxin Liu; Aidong Zhang; Zhijun Liu; Chunnian Liu

Addresses: College of Computer Science and Technology, Beijing University of Technology, Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing 100124, China ' College of Computer Science and Technology, Beijing University of Technology, Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing 100124, China ' Department of Computer Science and Engineering, The State University of New York at Buffalo, Buffalo 14260, USA ' College of Computer Science and Technology, Beijing University of Technology, Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing 100124, China ' College of Computer Science and Technology, Beijing University of Technology, Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing 100124, China

Abstract: Mining functional modules in Protein-Protein Interaction (PPI) networks is a very important research for revealing the structure-functionality relationships in biological processes. More recently, some swarm intelligence algorithms have been successfully applied in the field. This paper presents a new nature-inspired approach, ACC-FMD, which is based on ant colony clustering to detect functional modules. First, some proteins with the higher clustering coefficients are, respectively, selected as ant seed nodes. And then, the picking and dropping operations based on ant probabilistic models are developed and employed to assign proteins into the corresponding clusters represented by seeds. Finally, the best clustering result in each generation is used to perform the information transmission by updating the similarly function. Experimental results on some benchmarked datasets show that ACC-FMD outperforms the CFinder and MCODE algorithms and has comparative performance with the MINE, COACH, DPClus and Core algorithms in terms of the general evaluation metrics.

Keywords: protein-protein interaction; PPI networks; functional module detection; ant colony optimisation; ACO; clustering algorithms; picking model; dropping model; similarity function; bioinformatics; data mining.

DOI: 10.1504/IJDMB.2015.067323

International Journal of Data Mining and Bioinformatics, 2015 Vol.11 No.3, pp.331 - 363

Received: 20 Sep 2012
Accepted: 25 Mar 2013
Published online: 05 Feb 2015 *

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