EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

DNA language models are powerful predictors of genome-wide variant effects

Gonzalo Benegas iD, Sanjit Singh Batra iD, Yun S Song iD

Proceedings of the National Academy of Sciences · 31.10.2023 · 120 (44)

DOI: 10.1073/pnas.2311219120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 26.10.2023. Verfasst von Gonzalo Benegas und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Group in Computational Biology, University of California, Berkeley, CA 94720. Hauptthemen laut MEDLINE: Arabidopsis. Die Arbeit wurde bisher 166-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, HHS | NIH | National Institute of General Medical Sciences, Koret Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The expanding catalog of genome-wide association studies (GWAS) provides biological insights across a variety of species, but identifying the causal variants behind these associations remains a significant challenge. Experimental validation is both labor-intensive and costly, highlighting the need for accurate, scalable computational methods to predict the effects of genetic variants across the entire genome. Inspired by recent progress in natural language processing, unsupervised pretraining on large protein sequence databases has proven successful in extracting complex information related to proteins. These models showcase their ability to learn variant effects in coding regions using an unsupervised approach. Expanding on this idea, we here introduce the Genomic Pre-trained Network (GPN), a model designed to learn genome-wide variant effects through unsupervised pretraining on genomic DNA sequences. Our model also successfully learns gene structure and DNA motifs without any supervision. To demonstrate its utility, we train GPN on unaligned reference genomes of Arabidopsis thaliana and seven related species within the Brassicales order and evaluate its ability to predict the functional impact of genetic variants in A. thaliana by utilizing allele frequencies from the 1001 Genomes Project and a comprehensive database of GWAS. Notably, GPN outperforms predictors based on popular conservation scores such as phyloP and phastCons. Our predictions for A. thaliana can be visualized as sequence logos in the UCSC Genome Browser ( https://genome.ucsc.edu/s/gbenegas/gpn-arabidopsis ). We provide code ( https://github.com/songlab-cal/gpn ) to train GPN for any given species using its DNA sequence alone, enabling unsupervised prediction of variant effects across the entire genome.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ArabidopsisGenome-Wide Association StudyGenomicsGenomeDNA

Stichwörter der Autor:innen

Arabidopsis thalianagenome-wide association studylanguage modelsmachine learningvariant effect prediction

Substanzen

DNA

Autor:innen und Institutionen

  • Graduate Group in Computational Biology, University of California, Berkeley, CA 94720.
  • Computer Science Division, University of California, Berkeley, CA 94720.
  • Department of Statistics, University of California, Berkeley, CA 94720.
  • Center for Computational Biology, University of California, Berkeley, CA 94720.

ORCID-Profile: Gonzalo Benegas, Sanjit Singh Batra, Yun S Song

Förderung

  • NIGMS NIH HHS
  • HHS | NIH | National Institute of General Medical Sciences
  • Koret Foundation

Zitieren

APA

Benegas, G., Batra, S. S., & Song, Y. S. (2023). DNA language models are powerful predictors of genome-wide variant effects. Proceedings of the National Academy of Sciences, 120(44). https://doi.org/10.1073/pnas.2311219120

Vancouver

Benegas G, Batra SS, Song YS. DNA language models are powerful predictors of genome-wide variant effects. Proceedings of the National Academy of Sciences. 2023;120(44). doi:10.1073/pnas.2311219120

BibTeX
@article{Benegas2023,
  author = {Benegas, Gonzalo and Batra, Sanjit Singh and Song, Yun S},
  title = {DNA language models are powerful predictors of genome-wide variant effects},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2023},
  volume = {120},
  number = {44},
  doi = {10.1073/pnas.2311219120}
}
Kostenlos starten →