A Novel Kinase-substrate Relation Prediction Method Based on Substrate Sequence Similarity and Phosphorylation Network

Abstract Protein phosphorylation catalyzed by kinases plays essential roles in various intracellular processes. Therefore, the identification of potential relations between kinases and substrates is one of the key areas in post-translational modifications. Although a number of computational approaches have been designed, most existing kinase-substrate relation (KSR) prediction methods only focus on protein sequence information without considering kinase-substrate network. In this paper, we proposed a novel KSR prediction method called HeteSim-S based both substrate sequence similarity and phosphorylation heterogeneous network through HeteSim algorithm, which has been used in previous studies of similar search. Experiment results in kinase-substrate heterogeneous network show that our method can effectively predict kinase-substrate relations with the AUC measure achieving 0.842. Besides, the AUC performance on specific kinases is up to 0.971. The result demonstrates that HeteSim-S can remarkably improve the identification accuracy by incorporating substrate sequence similarity information in kinasesubstrate heterogeneous networks