Evolutionary-based Gene Ontology for Complex Detection in Protein-Protein Interaction Networks

Abstract

     Complex detection in protein-protein interaction (PPI) networks is one of the major issues facing scientific study in biological networks. In PPINs, proteins are distributed differently as groups (complexes). These groups can be identified as having a great internal density in the number of edges inside the groups while having the least possible number of edges between these groups. The most common methods for finding such complexes are evolutionary algorithms (EAs), which have been used widely in literature for this objective. Despite the reliability of these complicated detection models, they are mostly based on topological (graph) qualities, and the biological implications of the PPI networks have been rarely explored. In this research, EA with mutation-based gene ontology is developed, particularly in the mutation part where the functional annotation of the protein has been considered using gene ontology structure. The experimental results prove the reliability of the proposed method using standard validation measures. It also outperforms the state-of-the-art method in terms of the prediction ability and quality of the complexes found.