Deep learning modeling m(6)A deposition reveals the importance of downstream cis-element sequences

The N(6)-methyladenosine (m(6)A) modification is deposited to nascent transcripts on chromatin, but its site-specificity mechanism is mostly unknown. Here we model the m(6)A deposition to pre-mRNA by iM6A (intelligent m(6)A), a deep learning method, demonstrating that the site-specific m(6)A methylation is primarily determined by the flanking nucleotide sequences. iM6A accurately models the m(6)A deposition (AUROC = 0.99) and uncovers surprisingly that the cis-elements regulating the m(6)A deposition preferentially reside within the 50 nt downstream of the m(6)A sites. The m(6)A enhancers mostly include part of the RRACH motif and the m(6)A silencers generally contain CG/GT/CT motifs. Our finding is supported by both independent experimental validations and evolutionary conservation. Moreover, our work provides evidences that mutations resulting in synonymous codons can affect the m(6)A deposition and the TGA stop codon favors m(6)A deposition nearby. Our iM6A deep learning modeling enables fast paced biological discovery which would be cost-prohibitive and unpractical with traditional experimental approaches, and uncovers a key cis-regulatory mechanism for m(6)A site-specific deposition.