EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evo2VED: a database of DNA large language model-derived scores for variant interpretation

Rui Zhu, Xiaopu Zhou iD, Ivy Liang, Marla Mendes, Worrawat Engchuan, Nickie Safarian, Hang Zhou, Haoyu Cheng, Brett Trost iD, Elemi Breetvelt, Jacob Vorstman, Haixu Tang iD und 3 weitere

Nucleic Acids Research · 13.11.2026

DOI: 10.1093/nar/gkag1076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 13.11.2026. Verfasst von Rui Zhu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics & Data Science, School of Medicine, Yale University, New Haven CT 06510, United States. Die Arbeit nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: CIHR, Hospital for Sick Children (SickKids) Foundation, University of Toronto McLaughlin Centre.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Evo2 Variant Effect Database (Evo2VED; https://dnallmved.org/) is a publicly accessible resource cataloging precomputed Evo2-derived variant effect scores, defined as allelic score differences, for 6.48 million human variants common in the gnomAD non-Finnish European population. Evo2VED includes scores from the 7B and 40B models under three scoring schemes, alongside annotations of variant function, evolutionary constraint, allele age, and disease associations. It integrates genome-wide association study (GWAS) data from UK Biobank, FinnGen, and the Million Veteran Program. Three complementary modules support variant-level interpretation, regional and region-set exploration, and trait-level analysis through flexible queries, interactive visualizations, and downloadable results. Evo2VED also catalogs associations between Evo2 annotations and per-SNP heritability across thousands of traits from these biobanks. A guided workflow connects GWAS with associated regions and individual variant evidence. Case studies of hypertension and depression illustrate how regional comparisons of Evo2 scores and GWAS signals can guide candidate variant prioritization. Evaluations using massively parallel reporter assays, molecular QTLs, fine-mapping probabilities, and clinical annotations assess associations with Evo2 scores alone and their added value beyond conservation and regulatory annotations. By providing accessible scores, contextual annotations, and comparative analyses, Evo2VED facilitates exploration and application of genomic language model predictions in human genetics research.

Autor:innen und Institutionen

  • Department of Biomedical Informatics & Data Science, School of Medicine, Yale University, New Haven CT 06510, United States.
  • The Centre for Applied Genomics, The Hospital for Sick Children, Toronto, ON M5G 0A4, Canada.
  • Genetics and Genome Biology Program, The Hospital for Sick Children, Toronto, ON M5G 0A4, Canada.
  • Molecular Medicine Program, The Hospital for Sick Children, Toronto, ON M5G 0A4, Canada.
  • Department of Psychiatry, School of Medicine, Yale University, New Haven, CT 06511, United States.
  • Department of Molecular Genetics, University of Toronto, Toronto, ON M5G 0A4, Canada.

ORCID-Profile: Xiaopu Zhou, Brett Trost, Haixu Tang, Stephen W Scherer

Förderung

  • CIHR
  • Hospital for Sick Children (SickKids) Foundation
  • University of Toronto McLaughlin Centre
  • Northbridge Chair in Paediatric Research
  • The Hospital for Sick Children and University of Toronto
  • SickKids Psychiatry Associates Chair in Developmental Psychopathology
  • Canadian Institutes of Health Research

Zitieren

APA

Zhu, R., Zhou, X., Liang, I., Mendes, M., Engchuan, W., Safarian, N., Zhou, H., Cheng, H., Trost, B., Breetvelt, E., Vorstman, J., Tang, H., O'Brien, S. J., Scherer, S. W., & Ohno-Machado, L. (2026). Evo2VED: a database of DNA large language model-derived scores for variant interpretation. Nucleic Acids Research. https://doi.org/10.1093/nar/gkag1076

Vancouver

Zhu R, Zhou X, Liang I, Mendes M, Engchuan W, Safarian N, et al. Evo2VED: a database of DNA large language model-derived scores for variant interpretation. Nucleic Acids Research. 2026. doi:10.1093/nar/gkag1076

BibTeX
@article{Zhu2026,
  author = {Zhu, Rui and Zhou, Xiaopu and Liang, Ivy and Mendes, Marla and Engchuan, Worrawat and Safarian, Nickie and Zhou, Hang and Cheng, Haoyu and Trost, Brett and Breetvelt, Elemi and Vorstman, Jacob and Tang, Haixu and O'Brien, Stephen J and Scherer, Stephen W and Ohno-Machado, Lucila},
  title = {Evo2VED: a database of DNA large language model-derived scores for variant interpretation},
  journal = {Nucleic Acids Research},
  year = {2026},
  doi = {10.1093/nar/gkag1076}
}
Kostenlos starten →