MAE-FMD: multi-agent evolutionary method for functional module detection in protein-protein interaction networks.

Jun Zhong Ji,Jia Wei Lv,Lang Jiao,Cui Cui Yang,Ai Dong Zhang

doi:10.1186/1471-2105-15-325

Abstract

BackgroundStudies of functional modules in a Protein-Protein Interaction (PPI) network contribute greatly to the understanding of biological mechanisms. With the development of computing science, computational approaches have played an important role in detecting functional modules.ResultsWe present a new approach using multi-agent evolution for detection of functional modules in PPI networks. The proposed approach consists of two stages: the solution construction for agents in a population and the evolutionary process of computational agents in a lattice environment, where each agent corresponds to a candidate solution to the detection problem of functional modules in a PPI network. First, the approach utilizes a connection-based encoding scheme to model an agent, and employs a random-walk behavior merged topological characteristics with functional information to construct a solution. Next, it applies several evolutionary operators, i.e., competition, crossover, and mutation, to realize information exchange among agents as well as solution evolution. Systematic experiments have been conducted on three benchmark testing sets of yeast networks. Experimental results show that the approach is more effective compared to several other existing algorithms.ConclusionsThe algorithm has the characteristics of outstanding recall, F-measure, sensitivity and accuracy while keeping other competitive performances, so it can be applied to the biological study which requires high accuracy.

Highlights

Studies of functional modules in a Protein-Protein Interaction (PPI) network contribute greatly to the understanding of biological mechanisms
Basic ideas we describe a global search algorithm based on a multi-agent evolutionary method for functional module detection, which consists of two phases: (1) the solution construction phase, and (2) the solution evolution phase
This benchmark set, which consists of 428 protein functional modules, is constructed from three main sources: the MIPS [27], Aloy et al [39] and the SGD database [40] based on the Gene Ontology (GO) notations

Summary

Introduction

Studies of functional modules in a Protein-Protein Interaction (PPI) network contribute greatly to the understanding of biological mechanisms. Proteomics is the systematic study of the diverse properties of proteins to provide detailed descriptions of the structure, function and control of biological systems in health and disease [2], where the analysis of underlying relationships in protein data can potentially yield and considerably expand useful insights into roles of proteins in biological processes. There has been a number of new emerging approaches [19,20,21], which employs novel computational models to identify functional modules in a PPI network. Though using computational approaches to detect protein functional modules in PPI networks has received considerable attention and researchers have proposed many detection ideas and schemes over the past few years [1], how to efficiently identify functional modules by means of novel computational approaches is still a vital and challenging scientific problem in computational biology

Methods

Results

Conclusion