AlphaGenome Atlas maps every potential human DNA variant

A new platform provides precomputed predictions for nine billion single-letter DNA changes across the human genome.

2 min read

Abstract 3D topographical map depicting genomic variant data points.
A 3D visualization representing genomic data landscape maps produced by AlphaGenome Atlas.

Understanding how genetic variations affect biology at a molecular level remains a fundamental challenge in life sciences. Testing billions of single-letter DNA changes in a physical laboratory is practically impossible. To address this, researchers have introduced AlphaGenome Atlas, a platform containing precomputed predictions for the effects of 9 billion single-letter mutations in the human genome.

Key facts

Dataset size
1 petabyte
Variant count
9 billion
Coding regions
2%
Non-coding regions
98%
DNA sequence motifs
Over 2,500
UK Biobank participants
Over 54,000
Stylized DNA double helix with a highlighted nucleotide change.
A DNA double helix graphic highlighting single-letter mutations mapped by the platform., Source ↗

A comprehensive genomic map

AlphaGenome Atlas is a massive 1-petabyte dataset, more than 30 times larger than the AlphaFold Database. By precomputing predictions from the underlying artificial intelligence model, the platform charts molecular effects across hundreds of human and mouse cell types and tissues. It covers both coding regions—the two percent of the genome that builds proteins—and non-coding regions, which regulate gene activity.

Clean blue DNA double helix structure against a gradient background.
A clean visual depiction of a genomic strand highlighting the scale of dataset analysis., Source ↗

To help scientists interpret the data, the platform introduces the AlphaGenome Variant Impact score. This metric condenses predictions from both the base model and AlphaMissense into a single number, allowing researchers to quickly rank genetic variants by their potential biological disruption. Additionally, the platform catalogs over 2,500 recurrent DNA sequence motifs to help locate transcription factor binding sites and regulatory elements.

Real-world research applications

External collaborators have already applied the resource to distinct areas of genetics:

  • Rare diseases: Researchers at the Broad Institute used the impact score to prioritize overlooked genetic variants, discovering a variant affecting the DNM1 gene linked to epileptic encephalopathy.
  • Population genetics: An analyst at the University of Exeter examined whole-genome data from over 54,000 UK Biobank participants, uncovering 22 percent more non-coding genetic associations linked to circulating proteins.
  • Gene regulation: Scientists at the Stowers Institute used the DNA motifs to categorize transcription factors and understand how they control gene accessibility and expression.

Availability

The resource is available through an interactive website portal, an application programming interface, and as a tool in Google Antigravity. While currently accessible for academic research, the platform will soon expand to commercial use on Google Cloud.

Source: Original announcement

Worth a read?

Report

Comments