m6A-TCPred: a web server to predict tissue-conserved human m6A sites using machine learning approach
Gang Tu, Xuan Wang, Rong Xia, Bowen Song
Abstract
Abstract Background N6-methyladenosine (m 6 A) is the most prevalent post-transcriptional modification in eukaryotic cells that plays a crucial role in regulating various biological processes, and dysregulation of m 6 A status is involved in multiple human diseases including cancer contexts. A number of prediction frameworks have been proposed for high-accuracy identification of putative m 6 A sites, however, none have targeted for direct prediction of tissue-conserved m 6 A modified residues from non-conserved ones at base-resolution level. Results We report here m6A-TCPred, a computational tool for predicting tissue-conserved m 6 A residues using m 6 A profiling data from 23 human tissues. By taking advantage of the traditional sequence-based characteristics and additional genome-derived information, m6A-TCPred successfully captured distinct patterns between potentially tissue-conserved m 6 A modifications and non-conserved ones, with an average AUROC of 0.871 and 0.879 tested on cross-validation and independent datasets, respectively. Conclusion Our results have been integrated into an online platform: a database holding 268,115 high confidence m 6 A sites with their conserved information across 23 human tissues; and a web server to predict the conserved status of user-provided m 6 A collections. The web interface of m6A-TCPred is freely accessible at: www.rnamd.org/m6ATCPred .