A Multi-Objective Evolutionary Approach to Evaluate the Designing Perspective of Protein-Protein Interaction Network

Proteins interact with each other in a highly specific manner, and protein interactions play a key role in many cellular processes. Since protein interactions determine the outcome of most cellular processes, so identifying and characterizing Protein– Protein interactions and their networks are essential for understanding the mechanisms of biological processes on a molecular level. This paper explores the application of Nondominated Sorting Bee Colony (NSBC) optimization algorithm to the ProteinProtein Interaction (PPI) identification problem. In this work, PPI is formulated as a multi-objective optimization problem. The proposed scheme determines an optimal solution based on the binding energy, mismatch in phylogenetic profiles of two bound proteins and clustering coefficients. Results are demonstrated for three different networks both numerically and pictorially. Experimental results reveal that the proposed method outperforms Differential Evolution for Multi-objective Optimization (DEMO), Multi-Objective Particle Swarm Optimization (MOPSO), Non-dominated Sorting Genetic Algorithm-II (NSGA-II), Artificial Bee Colony (ABC), and Differential Evolution (DE). Keywords-protein-protein interaction; phylogenetic profile; CHARMM energy; non dominated sorting bee colony optimization;clustering coefficient.