Structure-aware deep learning enhances m6A prediction and reveals cell type-associated RNA structural signatures
PLOS Computational Biology · 2026
DOI: 10.1371/journal.pcbi.1014649 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Mingze Sun und 3 weiteren Autor:innen. Beteiligte Einrichtung: Yingcai Honors College, University of Electronic Science and Technology of China, Chengdu, Sichuan, China. Hauptthemen laut MEDLINE: Deep Learning, Adenosine, RNA. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, National Natural Science Foundation of China, National Key R&D Program of China.
Abstract (Originalsprache)
N6-methyladenosine (m6A), the most abundant mRNA modification in eukaryotes, plays essential roles in gene regulation and disease pathogenesis. Computational prediction of m6A sites offers a scalable alternative to costly experimental approaches, yet current methods rely predominantly on linear sequence features. This overlooks potentially informative RNA structural context, which is associated with local methylation patterns and may provide complementary predictive information beyond linear sequence motifs. To incorporate this complementary information, we propose SMART-m6A ( S equence–structure M ultifeature A ttention R NA T ransformer for m6A), a deep learning framework that integrates sequence and structural information through parallel convolutional feature extraction and structure-guided attention for multifeature fusion. SMART-m6A achieves superior predictive performance compared to existing methods, with particularly clear advantages in sequence-ambiguous candidates. Beyond prediction accuracy, learned attention patterns reveal strong concordance with experimentally validated m6A-binding protein recognition sites and identify potentially novel regulatory motifs. Through systematic ablation studies and targeted structural-input perturbation analyses, we show that sequence and structure provide complementary predictive information, and that sites with greater prediction sensitivity to structural perturbation exhibit distinct local structural profiles between cell lines. Collectively, this work demonstrates the predictive value of sequence-derived structural features in m6A modeling and provides a multifeature deep learning framework for accurate and interpretable structure-aware epitranscriptomic prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Yingcai Honors College, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
- Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies, Chengdu, Sichuan, China.
- Center for Quantitative Biology and Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China.
- The MOE Key Laboratory of Cell Proliferation and Differentiation, School of Life Sciences, Peking University, Beijing, China.
ORCID-Profile: Yihan Lin
Förderung
- Sichuan Science and Technology Program
- National Natural Science Foundation of China
- National Key R&D Program of China
- Ministry of Education of China
Zitieren
APA
Sun, M., Zhang, D., Li, Z., & Lin, Y. (2026). Structure-aware deep learning enhances m6A prediction and reveals cell type-associated RNA structural signatures. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014649
Vancouver
Sun M, Zhang D, Li Z, Lin Y. Structure-aware deep learning enhances m6A prediction and reveals cell type-associated RNA structural signatures. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1014649
BibTeX
@article{Sun2026,
author = {Sun, Mingze and Zhang, Di and Li, Zhiyuan and Lin, Yihan},
title = {Structure-aware deep learning enhances m6A prediction and reveals cell type-associated RNA structural signatures},
journal = {PLOS Computational Biology},
year = {2026},
doi = {10.1371/journal.pcbi.1014649}
}
EUVIMED