Accurate RNA 5-methylcytosine site prediction based on heuristic physical-chemical properties reduction and classifier ensemble

Abstract

RNA 5-methylcytosine (m⁵C) is an important post-transcriptional modification that plays an indispensable role in biological processes. The accurate identification of m⁵C sites from primary RNA sequences is especially useful for deeply understanding the mechanisms and functions of m⁵C. Due to the difficulty and expensive costs of identifying m⁵C sites with wet-lab techniques, developing fast and accurate machine-learning-based prediction methods is urgently needed. In this study, we proposed a new m⁵C site predictor, called M5C-HPCR, by introducing a novel heuristic nucleotide physicochemical property reduction (HPCR) algorithm and classifier ensemble. HPCR extracts multiple reducts of physical-chemical properties for encoding discriminative features, while the classifier ensemble is applied to integrate multiple base predictors, each of which is trained based on a separate reduct of the physical-chemical properties obtained from HPCR. Rigorous jackknife tests on two benchmark datasets demonstrate that M5C-HPCR outperforms state-of-the-art m⁵C site predictors, with the highest values of MCC (0.859) and AUC (0.962). We also implemented the webserver of M5C-HPCR, which is freely available at http://cslab.just.edu.cn:8080/M5C-HPCR/.

Keywords: Classifier ensemble; Heuristic properties reduction; Pseudo dinucleotide composition; RNA 5-methylcytosine.