Transcriptome-Wide Annotation of mC RNA Modifications Using Machine Learning.

The emergence of epitranscriptome opened a new chapter in gene regulation. 5-methylcytosine (mC), as an important post-transcriptional modification, has been identified to be involved in a variety of biological processes such as subcellular localization and translational fidelity. Though high-throughput experimental technologies have been developed and applied to profile mC modifications under certain conditions, transcriptome-wide studies of mC modifications are still hindered by the dynamic and reversible nature of mC and the lack of computational prediction methods. In this study, we introduced PEA-m5C, a machine learning-based mC predictor trained with features extracted from the flanking sequence of mC modifications. PEA-m5C yielded an average AUC (area under the receiver operating characteristic) of 0.939 in 10-fold cross-validation experiments based on known mC modifications. A rigorous independent testing showed that PEA-m5C (Accuracy [Acc] = 0.835, Matthews correlation coefficient [MCC] = 0.688) is remarkably superior to the recently developed mC predictor iRNAm5C-PseDNC (Acc = 0.665, MCC = 0.332). PEA-m5C has been applied to predict candidate mC modifications in annotated transcripts. Further analysis of these mC candidates showed that 4nt downstream of the translational start site is the most frequently methylated position. PEA-m5C is freely available to academic users at: https://github.com/cma2015/PEA-m5C.