DeepMind releases AlphaGenome Atlas with predictions for 9 billion DNA variants
lucapinello · x · 2026-09-09
Google DeepMind's team (Pushmeet Kohli) announced AlphaGenome Atlas, a petabyte-scale open resource containing AlphaGenome predictions for every possible single-letter DNA change in the human genome — 9 billion in total, freely available to researchers.
Kohli framed it as another step in the mission of deciphering the genome. Team member Anshul Kundaje noted that the team's open-source interpretation tools for deep learning regulatory sequence models (released pre-publication) are already being used to build such resources, and shared pointers for interested researchers.
More from Research
- FrontierCS 2 launches on Kaggle: 48 tasks make agents beat published CS papers — MeganRisdal · 2026-10-27
- LightMTP: lightweight latent multi-token prediction boosts LLM planning in pretraining — gdm3000 · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- EMNLP study: AI literary translation reads fine but varies more, even within one book — tuvllms · 2026-10-27
- Lab monkeys at $30-80K each: a 4-year breeding cycle is the real preclinical drug bottleneck — zebird0 · 2026-10-27
- Custom VQA benchmark under 48GB VRAM: Qwen3.8-Flash-Next leads, Qwen3.8-27B regressed — EmilPi · 2026-10-27