Protein complex prediction in large protein–protein interaction network. (2022)

• Record Type: Journal Article
• Authors: Shahidul Islam, Md.; Rafiqul Islam, Md.; Shawkat Ali, A.B.M.
• Is Part Of: Informatics in medicine unlocked. Volume 30(2022)
• Publication Date: 2022
• Subjects: Protein complex prediction -- Chemical reaction optimization -- Protein–protein interaction network -- Clustering; Medical informatics -- Periodicals; 610.285
• DOI: 10.1016/j.imu.2022.100947
• Languages: English
• ISSNs: 2352-9148

Abstract

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. Highlights: We propose an efficient method for the identification of protein complex. Chemical reaction optimization algorithm is used for the prediction. Additional repair operators have been developed to increase prediction accuracy. The proposed method is capable of predicting protein complexes with higher accuracy.