AthMethPre: a web server for the prediction and query of mRNA m6A sites in Arabidopsis thaliana

Abstract

N ⁶-Methyladenosine (m⁶A) is the most prevalent and abundant modification in mRNA that has been linked to many key biological processes. High-throughput experiments have generated m⁶A-peaks across the transcriptome of A. thaliana, but the specific methylated sites were not assigned, which impedes the understanding of m⁶A functions in plants. Therefore, computational prediction of mRNA m⁶A sites becomes emergently important. Here, we present a method to predict the m⁶A sites for A. thaliana mRNA sequence(s). To predict the m⁶A sites of an mRNA sequence, we employed the support vector machine to build a classifier using the features of the positional flanking nucleotide sequence and position-independent k-mer nucleotide spectrum. Our method achieved good performance and was applied to a web server to provide service for the prediction of A. thaliana m⁶A sites. The server also provides a comprehensive database of predicted transcriptome-wide m⁶A sites and curated m⁶A-seq peaks from the literature for query and visualization. The AthMethPre web server is the first web server that provides a user-friendly tool for the prediction and query of A. thaliana mRNA m⁶A sites, which is freely accessible for public use at http://bioinfo.tsinghua.edu.cn/AthMethPre/index.html.