Base by Base explores advances in genetics and genomics, with a focus on gene-disease associations, variant interpretation, protein structure, and insights from exome and genome sequencing. Each episode breaks down key studies and their clinical relevance—one base at a time.
Powered by AI, Base by Base offers a new way to learn on the go. Special thanks to authors who publish under CC BY 4.0, making open-access science faster to share and easier to explore.
All content for Base by Base is the property of Gustavo Barra and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
Base by Base explores advances in genetics and genomics, with a focus on gene-disease associations, variant interpretation, protein structure, and insights from exome and genome sequencing. Each episode breaks down key studies and their clinical relevance—one base at a time.
Powered by AI, Base by Base offers a new way to learn on the go. Special thanks to authors who publish under CC BY 4.0, making open-access science faster to share and easier to explore.
️ Episode 245: Benchmarking DNA foundation models
In this episode of PaperCast Base by Base, we explore A comprehensive, unbiased benchmark compares five DNA foundation models across 57 datasets and multiple tasks, finding mean token embeddings improve classification and that model strengths vary by task and pre-training.
Study Highlights:The study evaluated DNABERT-2, NT-v2, HyenaDNA, Caduceus-Ph, and GROVER on 57 datasets spanning sequence classification, gene expression prediction, variant effect quantification, and TAD recognition. Mean token embedding consistently and significantly outperformed summary-token and max pooling for sequence classification. Model performance was task-dependent: Caduceus-Ph excelled at human TFBS and promoter tasks, NT-v2 led pathogenic variant identification, HyenaDNA scaled efficiently and benefited from multi-species pre-training, while specialized models outperformed general foundations on QTL prediction. Zero-shot embeddings provided modest gene expression prediction and NT-v2 attention patterns did not reveal inherent TAD recognition.
Conclusion:Mean token pooling yields more robust sequence-level representations and model choice should align with task, input length, and pre-training data for best genomic performance
Music:Enjoy the music based on this article at the end of the episode.
Reference:Feng H, Wu L, Zhao B, Huff C, Zhang J, Wu J, Lin L, Wei P & Wu C. Benchmarking DNA foundation models for genomic and genetic tasks. Nat Commun. 2025;16:10780. https://doi.org/10.1038/s41467-025-65823-8
License:This episode is based on an open-access article published under the Creative Commons Attribution 4.0 International License (CC BY 4.0) – https://creativecommons.org/licenses/by/4.0/
Support:Base by Base – Stripe donations: https://donate.stripe.com/7sY4gz71B2sN3RWac5gEg00
Official website https://basebybase.com
Castos player https://basebybase.castos.com
On PaperCast Base by Base you’ll discover the latest in genomics, functional genomics, structural genomics, and proteomics.
Episode link: https://basebybase.castos.com/episodes/dna-foundation-models-benchmark
Episode Slug: dna-foundation-models-benchmark
Keywords: DNA foundation models, mean token embedding, sequence classification, variant effect, gene expression
Base by Base
Base by Base explores advances in genetics and genomics, with a focus on gene-disease associations, variant interpretation, protein structure, and insights from exome and genome sequencing. Each episode breaks down key studies and their clinical relevance—one base at a time.
Powered by AI, Base by Base offers a new way to learn on the go. Special thanks to authors who publish under CC BY 4.0, making open-access science faster to share and easier to explore.
