--- id: "2026-09-08-alphagenome-atlas" url: "https://postcutoff.com/e/2026-09-08-alphagenome-atlas/" as_of: "2026-11-13T13:49:00+01:00" date: "2026-09-08" date_precision: day category: science importance: 3 confidence: medium status: [Awaiting review] verification: Unverified claim sources: 4 editor: human editor human_review: null version: "2026-10-08" --- As of: 2026-11-13 13:49 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-08-alphagenome-atlas/ # AlphaGenome Atlas predicts the effect of all ~9 billion possible single-letter human DNA variants On 8 Sep 2026 DeepMind released AlphaGenome Atlas: predictions for all ~9 billion possible single-nucleotide variants in the human genome (~1 PB of data). A new variant-impact score reportedly 'more than doubles' rare-disease variant identification versus the previous standard, and collaborators experimentally confirmed variants in unsolved rare-disease cases. ## Key facts - ~9 billion variants, ~1 petabyte of predictions - New AVI score: 'more than doubles' rare-disease variant identification (company claim) - Collaborators verified variants in previously unsolved rare-disease cases ## What happened DeepMind pre-computed AlphaGenome predictions for every possible single-letter change in the human genome and released them as an atlas for clinicians and researchers. ## Why it matters Like the AlphaFold database for proteins, it turns a model into a lookup resource that could speed up rare-disease diagnosis. ## What is disputed or not yet verified - Verification: Technical paper; company-reported benchmarks; some cases lab-validated ## Your AI and this story - GPT-6 Astra (training cutoff April 2026): 131 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 70 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 161 days after its cutoff - Grok 4.7 (training cutoff May 2026): 100 days after its cutoff ## Sources 1. [DeepMind: AlphaGenome](https://deepmind.google/blog/alphagenome-ai-for-better-understanding-the-genome/) (deepmind.google, official) 2. [Google DeepMind: AlphaGenome Atlas: a predictive map of every possible DNA letter change in the human genome](https://deepmind.google/blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/) (deepmind.google, official) 3. [Google blog: AlphaGenome Atlas](https://blog.google/innovation-and-ai/models-and-research/google-deepmind/alphagenome-atlas/) (blog.google, official) 4. [Fortune: Google DeepMind AI predictions for 9 billion mutations in the human genome](https://fortune.com/2026/09/08/google-deepmind-ai-predictions-9-billion-mutation-human-genome/) (fortune.com, press) ## Changes - 2026-09-30: Added official DeepMind and Google blog announcement links - 2026-09-29 (filed): Created ## Related - 2025-06-25: [AlphaGenome predicts how DNA variants affect thousands of gene-regulation signals from 1 Mb of sequence](https://postcutoff.com/e/2025-06-25-alphagenome/index.md) - 2023-09-19: [AlphaMissense classifies 89% of all 71 million possible human missense mutations](https://postcutoff.com/e/2023-09-19-alphamissense/index.md) - Archived: 2 videos, listed in https://postcutoff.com/e/2026-09-08-alphagenome-atlas/index.json