EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Cross-RNA transferable sequence representation learning for lncRNA m6A site detection via novel deep domain separation networks

Zhixia Teng iD, Zhenjiang Li, Di Liu iD, Chunyu Wang iD, Guohua Wang

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Zhixia Teng und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin, Heilongjiang, China. Hauptthemen laut MEDLINE: RNA, Long Noncoding, Deep Learning, Adenosine, Computational Biology. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Key Technologies Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Heilongjiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

N6-methyladenosine (m6A) is a key epitranscriptomic marker enriched in long noncoding RNAs (lncRNAs) that is closely involved in complex disease mechanisms. Although accurate detection of m6A sites in lncRNAs is essential for understanding disease mechanisms, the development of effective computational predictors remains challenging due to the limited number of annotated sites. Moreover, most existing predictors are specifically designed for messenger RNAs (mRNAs) based on abundant mRNA-specific knowledge, yet they exhibit limited generalizability to lncRNAs. Given the similarities between mRNAs and lncRNAs, a transferable framework capable of leveraging their shared features is critical for advancing m6A site prediction in lncRNAs. To address this challenge, we propose DSNm6A, a deep learning framework that learns cross-RNA transferable sequence representations for effective lncRNA m6A site detection. To comprehensively capture patterns and signals of m6A sites, lncRNA and mRNA sequences are first encoded from complementary multiple facets, including One-Hot encoding, nucleotide physicochemical properties and cumulative frequency, and position-specific propensity. Based on these sequence encodings, a domain separation network integrating CNN, Bi-LSTM, and BERT modules is then employed to explicitly disentangle domain-invariant features shared between mRNAs and lncRNAs from their domain-specific counterparts. The shared features are finally fed into a fully connected layer for accurate lncRNA m6A sites prediction. Cross-validation and independent test results demonstrate that DSNm6A consistently outperforms existing methods across nearly all performance metrics, attributed to its superior capacity to learn transferable m6A-related features across RNA types. In addition, DSNm6A exhibits strong robustness and generalization across species.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNA, Long NoncodingDeep LearningAdenosineComputational BiologyHumansRNA, Messenger

Stichwörter der Autor:innen

domain separation networklncRNA methylationm6A site predictionrepresentation learningtransfer learning

Substanzen

RNA, Long NoncodingN-methyladenosineAdenosineRNA, Messenger

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin, Heilongjiang, China.
  • School of Computing, Harbin Institute of Technology, No. 92 Xidazhi Street, Nangang District, Harbin, Heilongjiang, China.

ORCID-Profile: Zhixia Teng, Di Liu, Chunyu Wang

Förderung

  • Key Technologies Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Heilongjiang Province

Zitieren

APA

Teng, Z., Li, Z., Liu, D., Wang, C., & Wang, G. (2025). Cross-RNA transferable sequence representation learning for lncRNA m6A site detection via novel deep domain separation networks. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf651

Vancouver

Teng Z, Li Z, Liu D, Wang C, Wang G. Cross-RNA transferable sequence representation learning for lncRNA m6A site detection via novel deep domain separation networks. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf651

BibTeX
@article{Teng2025,
  author = {Teng, Zhixia and Li, Zhenjiang and Liu, Di and Wang, Chunyu and Wang, Guohua},
  title = {Cross-RNA transferable sequence representation learning for lncRNA m6A site detection via novel deep domain separation networks},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf651}
}
Kostenlos starten →