EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A foundation model for nucleotide sequences

Xilin Shen iD, Jia Xin Li, Meng Yang, Lei Shi iD, Kexin Chen, Xiangchun Li iD

Nucleic Acids Research · 19.03.2026 · 54 (6)

DOI: 10.1093/nar/gkag083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 19.03.2026. Verfasst von Xilin Shen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Tianjin Cancer Institute, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin Key Laboratory of D…. Hauptthemen laut MEDLINE: Molecular Sequence Annotation, Genomics, Sequence Analysis, DNA. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Program for Changjiang Scholars and Innovative Research Team in University in China, Chinese National Key Research and Development Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation models have demonstrated exceptional performance across diverse downstream tasks. However, in genomics and transcriptomics, the integration of nucleotide sequences with their rich annotations remains underexplored, potentially limiting model generalizability across species and biological contexts. Here, we introduce OmniNA (Omni-applicable foundation model for nucleic acid), a self-supervised generative foundation model trained on 91.7 million nucleotide sequences and their associated annotations, totaling 1076.2 billion bases and 197 million words spanning diverse species. Unlike most existing approaches that focus solely on functional genomic element recognition, OmniNA jointly learns from both sequences and annotations, leveraging their complementarity to enhance semantic understanding and representation learning. We demonstrate that OmniNA captures sequence grammar and annotation semantics, facilitating robust transfer across nucleotide-level tasks. OmniNA can be fine-tuned under natural language paradigms and achieves state-of-the-art or competitive performance in 23 benchmarks, including sequence detection and species classification. Its learned representations also help reveal mutation effects on DNA and RNA processing. We release the model publicly as a community resource for genomics and transcriptomics research. OmniNA represents a step toward advancing foundational modeling by integrating annotation-aware learning, offering a powerful tool for genomics and transcriptomics research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Sequence AnnotationGenomicsSequence Analysis, DNAAnimalsBase SequenceHumansRepresentation Machine Learning

Autor:innen und Institutionen

  • Tianjin Cancer Institute, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin Key Laboratory of Digestive Cancer, State Key Laboratory of Druggability Evaluation and S…
  • Department of Pathology, Tianjin's Clinical Research Center for Cancer, Tianjin Key Laboratory of Digestive Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute & Hospital, T…
  • Key Laboratory of Breast Cancer Prevention and Therapy (Ministry of Education), Key Laboratory of Immune Microenvironment and Disease (Ministry of Education), The Province and Ministry Co-sponsored Collaborative Innovat…
  • Department of Epidemiology and Biostatistics, Key Laboratory of Prevention and Control of Major Diseases in the Population Ministry of Education, Key Laboratory of Molecular Cancer Epidemiology of Tianjin, Tianjin's Cli…

ORCID-Profile: Xilin Shen, Lei Shi, Xiangchun Li

Förderung

  • National Natural Science Foundation of China
  • Program for Changjiang Scholars and Innovative Research Team in University in China
  • Chinese National Key Research and Development Project
  • Tianjin Science and Technology Committee Foundation
  • Tianjin Key Medical Discipline Construction Project

Zitieren

APA

Shen, X., Li, J. X., Yang, M., Shi, L., Chen, K., & Li, X. (2026). A foundation model for nucleotide sequences. Nucleic Acids Research, 54(6). https://doi.org/10.1093/nar/gkag083

Vancouver

Shen X, Li JX, Yang M, Shi L, Chen K, Li X. A foundation model for nucleotide sequences. Nucleic Acids Research. 2026;54(6). doi:10.1093/nar/gkag083

BibTeX
@article{Shen2026,
  author = {Shen, Xilin and Li, Jia Xin and Yang, Meng and Shi, Lei and Chen, Kexin and Li, Xiangchun},
  title = {A foundation model for nucleotide sequences},
  journal = {Nucleic Acids Research},
  year = {2026},
  volume = {54},
  number = {6},
  doi = {10.1093/nar/gkag083}
}
Kostenlos starten →