ArticleNature communications2025
Benchmarking DNA foundation models for genomic and genetic tasks.
Article in Nature communications, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 16 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
16 citing papers in PubMed.
- Review
- Generative artificial intelligence in animal genomics for smart agriculture: Applications, challenges, and future prospects.Veterinary and animal science · 2026Review
- Foundation Models for Liquid Chromatography-High-Resolution Mass Spectrometry: A New Era beyond Labeled Datasets.Analytical chemistry · 2026Article
- MOSAIC enables selective transfer and fairness-aware generalization in cross-species DNA methylation prediction.Nucleic acids research · 2026Article
- Foundation models in omics research: a comprehensive survey.Briefings in bioinformatics · 2026Review
- K-attention: a biologically informed attention operator for data-efficient sequence-based omics modeling.Briefings in bioinformatics · 2026Article
- Advancing bioinformatics with language models: components, applications, and perspectives.Briefings in bioinformatics · 2026Review
- iDualG4: A Dual-Channel Deep Learning Framework for Predicting In Vivo G-Quadruplexes.Biomolecules · 2026Article
- Comprehensive review and assessment of multi-species splicing variant prediction: task-specific deep learning models and genomic foundation models.Briefings in bioinformatics · 2026Review
- EPInformer: scalable and integrative prediction of gene expression from promoter-enhancer sequences with multimodal epigenomic profiles.Nature communications · 2026Article
- Harnessing artificial intelligence for genomic variant prediction: advances, challenges, and future directions.GigaScience · 2026Review
- Agentic AI for trustworthy synthetic microbial genomics: a perspective on generation, validation, and governance.Frontiers in bioinformatics · 2026Article
- Pre-training genomic language model with variants for better modeling functional genomics.NPJ artificial intelligence · 2026Article
- Evolving computational paradigms for noncoding variant pathogenicity prediction.Frontiers in molecular biosciences · 2026Review
- Benchmarking DNA foundation models for genomic and genetic tasks.Nature communications · 2025Article
- Pre-training Genomic Language Model with Variants for Better Modeling Functional Genomics.bioRxiv : the preprint server for biology · 2025Article
Corrections and comments
- Update of
Authors and funding
9 authors.
Funding
Abstract
The rapid evolution of DNA foundation models promises to revolutionize genomics, yet comprehensive evaluations are lacking. Here, we present a comprehensive, unbiased benchmark of five models (DNABERT-2, Nucleotide Transformer V2, HyenaDNA, Caduceus-Ph, and GROVER) across diverse genomic and genetic tasks including sequence classification, gene expression prediction, variant effect quantification, and topologically associating domain (TAD) region recognition, using zero-shot embeddings. Our analysis reveals that mean token embedding consistently and significantly improves sequence classification performance, outperforming other pooling strategies. Model performance varies among tasks and datasets; while general purpose DNA foundation models showed competitive performance in pathogenic variant identification, they were less effective in predicting gene expression and identifying putative causal QTLs compared to specialized models. Our findings offer a framework for model selection, highlighting the impact of architecture, pre-training data, and embedding strategies on performance in genomic and genetic tasks.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.