Interpretability-guided RNA N6-methyladenosine modification site prediction with invertible neural networks

Abstract As one of the most common and abundant post-transcriptional modifications, N6-methyladenosine (m6A) has been extensively studied for its essential regulatory role in gene expression and cell functions. The location of m6A RNA modification sites, however, remains a challenging problem, becau...

Full description

Saved in:
Bibliographic Details
Main Authors: Guodong Li, Xiaorui Su, Yue Yang, Dongxu Li, Ziwen Cui, Xun Deng, Pengwei Hu, Lun Hu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Communications Biology
Online Access:https://doi.org/10.1038/s42003-025-08265-8
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract As one of the most common and abundant post-transcriptional modifications, N6-methyladenosine (m6A) has been extensively studied for its essential regulatory role in gene expression and cell functions. The location of m6A RNA modification sites, however, remains a challenging problem, because of the inability to characterize m6A modified sites at a multi-scale level in their native RNA context. Here, we introduce an interpretability-guided invertible neural network (m6A-IIN), a deep learning model to accurately identify m6A RNA modification sites by integrating both primary and secondary structure information under an invertible coupling framework. Compared to existing methods, m6A-IIN achieves state-of-the-art performance in the prediction of m6A RNA modification sites across 11 benchmark datasets collected from different species and tissues. Furthermore, we find evidence indicating high consistency in methylation-related regions between primary and secondary structure of RNA, providing novel insights into m6A biology from the phylogenetic perspective. By analyzing conserved methylation-related regions identified by m6A-IIN across tissues, m6A-IIN facilitates the identification of novel pan-cancer genes, providing valuable contributions to cancer biology. Our results underscore the interpretability and predictive accuracy of m6A-IIN, opening an avenue towards the understanding of m6A RNA modification mechanisms.
ISSN:2399-3642