m6A-FORM: An m6A-focused Foundation Model for Decoding m6A Regulatory Function

Abstract

N6-methyladenosine (m6A) regulates mRNA fate through site-specific methylation, reader recognition and downstream effects on RNA stability and decay. However, current computational approaches focus mainly on site prediction, leaving unresolved the broader challenge of inferring m6A regulatory context and function from epitranscriptomic profiles. Here we present m6A-FORM, an m6A-focused foundation model for for regulatory discovery. Pretrained on 24.9 million RNA sequence windows from 22.5 million MeRIP-seq regions across 143 human studies, m6A-FORM learns reusable representations of m6A-associated transcript contexts. We adapt this encoder to single-nucleotide m6A discovery, regulator-binding prediction, YTHDF2-associated decay prediction and tissue-scale epitranscriptomic mapping. m6A-FORM predicts binding of 19 m6A readers, writers and erasers and identifies sequence and RBP-context features associated with YTHDF2-mediated RNA degradation. Applied to 67 datasets from 24 human tissues, it identifies tissue-conserved m6A sites linked to stronger methylation, reader binding, RBP occupancy and decay propensity.