Google DeepMind Launches AlphaGenome Atlas
Google DeepMind launched AlphaGenome Atlas, a database that predicts the effects of every possible single nucleotide variant in the human genome. The system is designed to help researchers prioritize variants with the AlphaGenome Variant Impact score and access the results through a website portal, with supporting workflows in Google Antigravity.
- The Atlas precomputes regulatory effects across 9 billion single-letter changes and packages them into a dataset Google describes as 1 petabyte.
- Google frames the release around the hard part of genomics: the 98% non-coding genome where researchers still have limited understanding of how variants alter biology.
- Early research examples include rare disease variant prioritization and a UK Biobank analysis that found 22% more associations among non-coding variants linked to complex traits.
