Deep learning modeling m6A deposition reveals the importance of downstream cis-element sequences

• Published in: Nature communications 2022-05, Vol.13 (1), p.2720-2720, Article 2720
• Main Authors: Luo, Zhiyuan, Zhang, Jiacheng, Fei, Jingyi, Ke, Shengdong
• Format: Article
• Language: English
• Subjects: 13/106; 45/15; 45/43; 45/77; 45/90; 45/91; 49/91; 631/114; 631/337/1645/2570; 64/60; Chromatin; Codons; Deep learning; Deposition; Enhancers; Evolutionary conservation; Humanities and Social Sciences; Methylation; Modelling; multidisciplinary; Mutation; N6-methyladenosine; Nucleotide sequence; Nucleotides; Regulatory mechanisms (biology); RNA modification; Science; Science (multidisciplinary); Sequences; Stop codon; Teaching methods
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-022-30209-7

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 ( i ntelligent 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. The site specificity of m6A mRNA modification is a fundamental RNA biology question. Here, Luo et al., develop the iM6A, a deep learning method to model this process, showing that its site-specificity is determined by the primary nucleotide sequence.