A foundation model for nucleotide sequences
Open Access
- 19 March 2026
- journal article
- research article
- Published by Oxford University Press (OUP) in Nucleic Acids Research
- Vol. 54 (6)
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (32270688)
- National Natural Science Foundation of China (31801117)
- Program for Changjiang Scholars and Innovative Research Team in University in China (IRT_14R40)
- Chinese National Key Research and Development Project (2018YFC1315600)
- Tianjin Science and Technology Committee Foundation (17JCYBJC25300)
- Tianjin Key Medical Discipline Construction Project (TJYXZDXK-3-016C)
- Tianjin Key Medical Discipline Construction Project (TJYXZDXK-3-003A)
This publication has 39 references indexed in Scilit:
- Deep learning sequence-based ab initio prediction of variant effects on expression and disease riskNature Genetics, 2018
- SpliceRover: interpretable convolutional neural networks for improved splice site predictionBioinformatics, 2018
- ClinVar: improving access to variant interpretations and supporting evidenceNucleic Acids Research, 2017
- A global reference for human genetic variationNature, 2015
- The Comprehensive Antibiotic Resistance DatabaseAntimicrobial Agents and Chemotherapy, 2013
- CTCFBSDB 2.0: a database for CTCF-binding sites and genome organizationNucleic Acids Research, 2012
- An integrated encyclopedia of DNA elements in the human genomeNature, 2012
- The International Nucleotide Sequence Database CollaborationNucleic Acids Research, 2011
- Identifying a High Fraction of the Human Genome to be under Selective Constraint Using GERP++PLOS Computational Biology, 2010
- VISTA Enhancer Browser--a database of tissue-specific human enhancersNucleic Acids Research, 2006