Advancing regulatory variant effect prediction with AlphaGenome

Deep learning models that predict functional genomic measurements from DNA sequences are powerful tools for deciphering the genetic regulatory code. Existing methods involve a trade-off between input sequence length and prediction resolution, thereby limiting their modality scope and performance<sup>1-5</sup>. We present AlphaGenome, a unified DNA sequence model, which takes as input 1 Mb of DNA sequence and predicts thousands of functional genomic tracks up to single-base-pair resolution across diverse modalities. The modalities include gene expression, transcription initiation, chromatin accessibility, histone modifications, transcription factor binding, chromatin contact maps, splice site usage and splice junction coordinates and strength. Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest available external models in 25 of 26 evaluations of variant effect prediction. The ability of AlphaGenome to simultaneously score variant effects across all modalities accurately recapitulates the mechanisms of clinically relevant variants near the TAL1 oncogene<sup>6</sup>. To facilitate broader use, we provide tools for making genome track and variant effect predictions from sequence.

Authors

Institutions

Publication Details

Journal
Nature
Published
2026-01-28
DOI
https://doi.org/10.1038/s41586-025-10014-0
Citations
25
Primary Topic
Genomic variations and chromosomal abnormalities
Type
article
Field-Weighted Citation Impact
773.20
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Advancing regulatory variant effect prediction with AlphaGenome

Lai Hong Wong, Tom Ward, Demis Hassabis, Lauren Nicolaisen et al.
25 citations
Nature
Genomic variations and chromosomal abnormalities
773.20
article

Advancing regulatory variant effect prediction with AlphaGenome

Lai Hong Wong, Tom Ward, Demis Hassabis, Lauren Nicolaisen, Alexander Karollus, Souradeep Basu, Vincent Dutordoir, Taylor Applebaum, Natasha S. Latysheva, Guido Novati, Adam R. Kosiorek, Pushmeet Kohl, Raina W. Thomas, Žiga Avsec, Pavol Drotár, Kyle R. Taylor, S. P. M. Boer De, Jun Cheng, Clare Bycroft, Matteo Perino, Richard Tanburn, Eirini Arvaniti, Anne Mottram, Toby Sargeant, Andrew Senior, Adam Gayoso, Joshua Pan
article en
25 citations

Abstract

Deep learning models that predict functional genomic measurements from DNA sequences are powerful tools for deciphering the genetic regulatory code. Existing methods involve a trade-off between input sequence length and prediction resolution, thereby limiting their modality scope and performance<sup>1-5</sup>. We present AlphaGenome, a unified DNA sequence model, which takes as input 1 Mb of DNA sequence and predicts thousands of functional genomic tracks up to single-base-pair resolution across diverse modalities. The modalities include gene expression, transcription initiation, chromatin accessibility, histone modifications, transcription factor binding, chromatin contact maps, splice site usage and splice junction coordinates and strength. Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest available external models in 25 of 26 evaluations of variant effect prediction. The ability of AlphaGenome to simultaneously score variant effects across all modalities accurately recapitulates the mechanisms of clinically relevant variants near the TAL1 oncogene<sup>6</sup>. To facilitate broader use, we provide tools for making genome track and variant effect predictions from sequence.

NatureVol. 649(8099)
Google DeepMind (United Kingdom) (GB), Google (United Kingdom) (GB)
Partnerships for the goals
Openalex Percentile: Top 0%
Genomic variations and chromosomal abnormalities
773.20
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.