TargetM6A: Identifying N6-Methyladenosine Sites From RNA Sequences via Position-Specific Nucleotide Propensities and a Support Vector Machine

As one of the most ubiquitous post-transcriptional modifications of RNA, N-6-methyladenosine (m(6)A) plays an essential role in many vital biological processes. The identification of m(6)A sites in RNAs is significantly important for both basic biomedical research and practical drug development. In this study, we designed a computational-based method, called TargetM(6)A, to rapidly and accurately target m(6)A sites solely from the primary RNA sequences. Two new features, i. e., positionspecific nucleotide/dinucleotide propensities (PSNP/PSDP), are introduced and combined with the traditional nucleotide composition (NC) feature to formulate RNA sequences. The extracted features are further optimized to obtain a much more compact and discriminative feature subset by applying an incremental feature selection (IFS) procedure. Based on the optimized feature subset, we trained TargetM(6)A on the training dataset with a support vector machine (SVM) as the prediction engine. We compared the proposed TargetM(6)A method with existing methods for predicting m(6)A sites by performing stringent jackknife tests and independent validation tests on benchmark datasets. The experimental results show that the proposed TargetM(6)A method outperformed the existing methods for predicting m(6)A sites and remarkably improved the prediction performances, with MCC = 0.526 and AUC = 0.818. We also provided a user-friendly web server for TargetM(6)A, which is publicly accessible for academic use at http://csbio. njust. edu. cn/bioinf/TargetM(6)A.