Deep analysis of RNA N(6)-adenosine methylation (m(6)A) patterns in human cells

N(6)-adenosine methylation (m(6)A) is the most abundant internal RNA modification in eukaryotes, and affects RNA metabolism and non-coding RNA function. Previous studies suggest that m(6)A modifications in mammals occur on the consensus sequence DRACH (D = A/G/U, R = A/G, H = A/C/U). However, only about 10% of such adenosines can be m(6)A-methylated, and the underlying sequence determinants are still unclear. Notably, the regulation of m(6)A modifications can be cell-type-specific. In this study, we have developed a deep learning model, called TDm6A, to predict RNA m(6)A modifications in human cells. For cell types with limited availability of m(6)A data, transfer learning may be used to enhance TDm6A model performance. We show that TDm6A can learn common and cell-type-specific motifs, some of which are associated with RNA-binding proteins previously reported to be m(6)A readers or anti-readers. In addition, we have used TDm6A to predict m(6)A sites on human long non-coding RNAs (lncRNAs) for selection of candidates with high levels of m(6)A modifications. The results provide new insights into m(6)A modifications on human protein-coding and non-coding transcripts.