Essential Protein Prediction Based on Shuffled Frog‐Leaping Algorithm

Abstract

Essential proteins are integral parts of living organisms. The prediction of essential proteins facilitates to discover disease genes and drug targets. The prediction precision and robustness of most of existing identification methods are not satisfactory. In this paper, we propose a novel essential proteins prediction method (EPSFLA), which applies Shuffled frog-leaping algorithm (SFLA), and integrates several biological information with network topological structure to identify essential proteins. Specifically, the topological property and several biological properties (function annotation, subcellular localization, protein complex, and orthology) are integrated and utilized to weight protein-protein interaction networks. Then the position of a frog is encoded and denotes a candidate essential protein set. The frog population continuously evolve by means of local exploration and global exploration until termination criteria for algorithm are satisfied. Finally, those proteins contained in the best frog are regarded as predicted essential proteins. The experimental results show that EPSFLA outperforms some well-known prediction methods in terms of various criteria. The proposed method aims to provide a new perspective for essential protein prediction.