AlphaGenome Atlas maps effects of 9 billion human DNA variants
Google DeepMind has introduced AlphaGenome Atlas, a platform containing predictions for the molecular effects of 9 billion possible single-nucleotide variants in the human genome. The resource is intended to address the difficulty of experimentally testing every possible single-letter DNA change and is available for academic research through a free website portal.
The Atlas precomputes thousands of predictions for each variant across gene-regulation processes and hundreds of human and mouse cell types and tissues. It also includes the AlphaGenome Variant Impact (AVI) score, which combines predictions from AlphaGenome and AlphaMissense, along with feature attributions showing whether effects are linked to processes such as RNA splicing or gene expression. The dataset is about 1 petabyte in size and includes more than 2,500 recurring DNA sequence motifs.
Collaborators used the system to prioritize variants in unsolved rare-disease research and to identify additional non-coding genetic associations in UK Biobank data. The platform is accessible through its website, the AlphaGenome API and Google Antigravity. Non-commercial access is available through the website, while commercial use on Google Cloud is planned.
Written by Sakhanda Wire AI from reporting by DeepMind. Facts, quotes and full context are in the original article below.