Abstract (EN)

Community detection has become an important research direction for data mining in complex networks. It aims to identify topo-logical structures and discover patterns in complex networks, which presents an important problem of great significance. Prediction of communities from Protein-Protein Interaction (PPI) networks is important problem in system biology as they control different cellular functions. These networks represent a set of proteins that collaborate at the same cellular function. With the increment of genome-scale protein–protein interaction data for different species, various computational methods focus on identifying protein community from PPI networks. In this paper, we are interested in evaluating the proposed genetic algorithm GA-PPI-Net and three clustering methods for community detection. In the computational tests carried out in this work, the proposed genetic algorithm achieved excellent results to detect existing or even new communities from PPI networks.