Accurate Identification of Human Phosphorylated Proteins by Ensembling Supervised Kernel Self‐organizing Maps

Abstract

Protein phosphorylation is a vital physiological process, which plays a critical role in controlling survival differentiation, cell growth, metabolism and apoptosis. The accurate identification of whether a protein will be phosphorylated solely from protein sequence is especially useful for both basic research and drug development. In this study, a new predictor specifically designed for the prediction of human phosphorylated proteins is proposed. The proposed method first train two supervised kernel self‐organizing maps (SKSOMs): one is trained with feature from protein physiochemical composition view, while the other is trained with feature from protein evolutionary information view. Then, the two trained SKSOMs are ensembled to perform the final prediction. Rigorous computational experiments show that the proposed method achieves 78.75 % and 0.561 on ACC and MCC, which are 6.96 % and 12.5 % higher than that of the state‐of‐the‐art predictor. Overall, the study demonstrated a new sensitive avenue to identify human phosphorylated proteins and could be readily extended to recognize phosphorylated proteins for other species.

An integrated model for medical expense system optimization during diagnosis process based on artificial intelligence algorithm

“…They used a SOM-based clustering approach to improve the accuracy and scalability of prediction, and nine clusters were detected with the best SOM map quality for clustering. Concentrating on the issue of accurate identification of human phosphorylated proteins, Cui and Ding ( 2020 ) first trained two supervised kernel self-organizing maps (SKSOMs), the two trained SKSOMs were than ensembled to perform the final prediction. This study demonstrated a new sensitive avenue to identify human phosphorylated proteins and could be readily extended to recognize phosphorylated proteins for other species.…”