Protein complex prediction in large protein–protein interaction network

Abstract

Due to high computational complexity, the detection of protein complexes in large protein–protein interaction (PPI) networks remains a challenging problem. Finding the actual protein complexes from a large PPI network requires a sophisticated algorithm. The protein complexes exhibit in densely connected sub-graphs in a PPI network. This paper presents a novel algorithm based on a metaheuristic method for protein complex prediction in large PPI networks. The algorithm mimics the density-based graph clustering method with biological heuristics to identify the protein complexes. The algorithm is enhanced by a local search algorithm and three repair operators. A new function has been developed for computing cluster density. The method was applied to the yeast and human protein interaction data and compared with the state-of-the-art algorithms. The comparisons demonstrate the best performance of the proposed algorithm in terms of accuracy and f-measure.