DeepMind releases AlphaGenome Atlas with predictions for 9 billion DNA variants
pushmeet · x · 2026-09-08
Google DeepMind has released AlphaGenome Atlas, a petabyte-scale resource containing AlphaGenome predictions for every possible single-letter DNA change in the human genome — about 9 billion variants in total — billed as the most comprehensive catalogue of how mutations affect molecular biology.
Key points:
- By precomputing AlphaGenome's predictions at scale, the atlas lets researchers survey variant effects genome-wide without testing each mutation in the lab.
- A new AVI (AlphaGenome Variant Impact) score combines AlphaMissense and AlphaGenome into a single metric to help prioritize high-impact variants and unravel disease mechanisms.
- Built on the experience of the AlphaFold Database, the atlas is freely available to researchers worldwide for non-commercial use via a web portal.
- In early access, scientists are already using it to accelerate rare disease research and identify causal phenotypes.
More from Research
- AutoResearch agent produces weird 'forking' loss curves, and the team dug into the science — ZimingLiu11 · 2026-10-27
- No π0 weights changed: Motoniq layer lifts real-robot precision fitting from 0/10 to 9/10 — hbouammar · 2026-10-27
- MICE paper pushes cross-encoders from re-ranking to end-to-end retrieval — antoine_chaffin · 2026-10-27
- JockeyBench uses Japanese horse racing to test LLM agents — all betting strategies lose money — Zhongwei Xie · 2026-10-27
- Stanford's PaperFormalizer turns research papers into Lean-verified versions with author in the loop — StanfordUniversity · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27