Protein complex prediction via cost-based clustering
Bioinformatics
Iterative Cluster Analysis of Protein Interaction Data
Bioinformatics
ACOPIN: An ACO Algorithm with TSP Approach for Clustering Proteins from Protein Interaction Network
EMS '08 Proceedings of the 2008 Second UKSIM European Symposium on Computer Modeling and Simulation
Protein Interaction Networks: Computational Analysis
Protein Interaction Networks: Computational Analysis
Graph Partitioning Method for Functional Module Detections of Protein Interaction Network
ICCTD '09 Proceedings of the 2009 International Conference on Computer Technology and Development - Volume 01
Bootstrapping the interactome: unsupervised identification of protein complexes in yeast
RECOMB'08 Proceedings of the 12th annual international conference on Research in computational molecular biology
IEEE Computational Intelligence Magazine
Ant colony system: a cooperative learning approach to the traveling salesman problem
IEEE Transactions on Evolutionary Computation
Ant system: optimization by a colony of cooperating agents
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A multiagent genetic algorithm for global numerical optimization
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
ICICA'12 Proceedings of the Third international conference on Information Computing and Applications
| Hi-index | 0.01 |
Mining functional modules in a protein-protein interaction (PPI) network contributes greatly to the understanding of biological mechanism, thus how to effectively detect functional modules in a PPI network has a significant application. In this paper, we present a hybrid approach using ant colony optimization and multi-agent evolution for detection functional modules in PPI networks. The proposed algorithm enhances the performance of ant colony optimization by incorporating multi-agent evolution for detecting functional modules. In the ant colony optimization process, a new heuristic, which merges topological characteristics with functional information function, is introduced to effectively conduct ants searching in finding optimal results. Thereafter, the multi-agent evolutionary process based on an energy function is performed to move out of local optima and obtain some enclosed connecting subgraphs which represent functional modules mined in a PPI network. Finally, systematic experiments have been conducted on four benchmark testing sets of yeast networks. Experimental results show that the hybrid approach is more effective compared to several other existing algorithms.