RNAMethPre: A Web Server for the Prediction and Query of mRNA m6A Sites

• DOI: 10.1371/journal.pone.0162707
• Publication Date: 2016-10-10T13:39:02Z
• Authors: Shunian Xiang; Ke Liu; Zhangming Yan; Yaou Zhang; Zhirong Sun
• Keywords: 0303 health sciences; Adenosine; Sequence Analysis, RNA; Science; Q; R; Mice; 03 medical and health sciences; Databases, Genetic; Medicine; Animals; Humans; RNA, Messenger; RNA Processing, Post-Transcriptional; Transcriptome; Software; Research Article

N6-Methyladenosine (m6A) is the most common mRNA modification; it occurs in a wide range of taxon and associated with many key biological processes. High-throughput experiments have identified m6A-peaks sites across transcriptome, but studies m6A at transcriptome-wide scale are limited to few species tissue types. Therefore, computational prediction has become an important strategy. In this study, we integrated multiple features (flanking sequences, local secondary structure information, relative position information) trained SVM classifier predict mammalian sequences. Our method achieves ideal performance both cross-validation tests rigorous independent dataset tests. The server also provides comprehensive database predicted curated m6A-seq peaks from literature for human mouse, these can be queried visualized genome browser. RNAMethPre web user-friendly tool query sites, which freely accessible public use http://bioinfo.tsinghua.edu.cn/RNAMethPre/index.html.