Google's AlphaGenome Atlas precomputes effects of all ~9 billion human single-base mutations
aigclink · x · 2026-09-09
Google DeepMind released AlphaGenome Atlas, precomputing the predicted impact of every possible single-letter change across the human genome (9 billion single-base mutations) into a queryable map aimed at rare disease, complex disease, and drug target research.
- The 1 PB dataset is 30x larger than the AlphaFold database; no-code web access plus API and skill.
- Validated via three real case studies (rare disease, a +22% population association, transcription factor classification), showing it produces experimentally verifiable findings, not just a database.
- Free for academic use.
More from Research
- 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
- Hugging Face TRL makes score centering + masked importance sampling default in async GRPO — _lewtun · 2026-10-27
- EMNLP 2026: sub-billion-parameter LMs show superhuman entity tracking, human-like fleeting memory — GretaTuckute · 2026-10-27
- 10-year study documents first 'unnatural gradient' phonotactic restriction in Tarma Quechua — begusgasper · 2026-10-27