A Review of Machine Learning and Algorithmic Methods for Protein Phosphorylation Sites Prediction

Post-translational modifications (PTMs) have key roles in extending the functional diversity of proteins and as a result, regulating diverse cellular processes in prokaryotic and eukaryotic organisms. Phosphorylation modification is a vital PTM that occurs in most proteins and plays a significant role in many biological processes. Disorders in the phosphorylation process lead to multiple diseases including neurological disorders and cancers. The purpose of this review paper is to organize this body of knowledge associated with phosphorylation site (p-site) prediction to facilitate future research in this field. At first, we comprehensively reviewed all related databases and introduced all steps regarding dataset creation, data preprocessing, and method evaluation in p-site prediction. Next, we investigated p-sites prediction methods which were divided into two computational groups: algorithmic and machine learning (ML). Additionally, it was shown that there are basically two main approaches for p-sites prediction by ML: conventional and end-to-end deep learning methods, which were given an overview for both of them. Moreover, this study introduced the most important feature extraction techniques which have mostly been used in p-site prediction. Finally, we created three test sets from new proteins related to the released version of the dbPTM database in 2022 based on general and human species. Evaluating online p-site prediction tools on new added proteins introduced in the dbPTM 2022 release, distinct from those in the dbPTM 2019 release, revealed their limitations. In other words, the actual performance of these online p-site prediction tools on unseen proteins is notably lower than the results reported in their respective research papers.