MethyNano: supervised contrastive pretraining enables robust and generalizable methylation detection from nanopore sequencing
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag348 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Jiahui Yan und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China. Hauptthemen laut MEDLINE: Nanopore Sequencing, DNA Methylation, Deep Learning, 5-Methylcytosine. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation 5-Methylcytosine (5mC) plays an important role in gene regulation and development. Although nanopore sequencing has enabled direct detection of 5mC, existing methods still face several limitations, including poor generalization across species and sequence contexts (CpG/CHG/CHH), as well as suboptimal integration of sequence and current signals. Results Here, we present MethyNano, a deep learning framework incorporating a contrastive learning strategy to detect 5mC from nanopore reads. By encouraging more discriminative and stable representations, the contrastive objective improves the model’s sensitivity to rare sequence contexts and reduces its prediction uncertainty in challenging regions. Across datasets from Arabidopsis thaliana, Oryza sativa, and Homo sapiens, our model achieves superior performance on key metrics compared with other existing methods. Extensive cross-species and cross-motif experiments demonstrate the robust generalization performance of MethyNano, while dimensionality-reduction visualizations of learned features provide an intuitive view of the model’s efficient representation capability. Moreover, our ablation studies show that MethyNano’s architecture enables more effective integration of critical features, leading to higher predictive accuracy. Availability and implementation The project code is available at https://github.com/baigeHUI/MethyNano and https://doi.org/10.5281/zenodo.19858400.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China.
- School of Computer Science, Key Laboratory of High Confidence Software Technologies, Peking University, Beijing 100871, China.
ORCID-Profile: Jiahui Yan
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Yan, J., Chen, Y., Gong, Y., Zhang, C., & Yang, J. (2026). MethyNano: supervised contrastive pretraining enables robust and generalizable methylation detection from nanopore sequencing. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag348
Vancouver
Yan J, Chen Y, Gong Y, Zhang C, Yang J. MethyNano: supervised contrastive pretraining enables robust and generalizable methylation detection from nanopore sequencing. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag348
BibTeX
@article{Yan2026,
author = {Yan, Jiahui and Chen, Yujie and Gong, Yucong and Zhang, Cheng and Yang, Jing},
title = {MethyNano: supervised contrastive pretraining enables robust and generalizable methylation detection from nanopore sequencing},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag348}
}
EUVIMED