AlphaGenome 2 interprets DNA variants at cell-type resolution
Google DeepMind’s new model predicts how DNA changes affect hundreds of human cell types and states; it has not been validated for clinical use.
AT A GLANCE
Key points
- Trained on more than 107 million single-cell profiles from 68 tissues.
- Available through the AlphaGenome API for non-commercial research.
- Not validated or approved for clinical or diagnostic use.
What is changing?
Google DeepMind has announced AlphaGenome 2, a model that predicts how DNA sequences and variants affect specific human cell types. Its conditional architecture takes a one-million-letter DNA sequence together with a target tissue, cell type or state. The model produces outputs such as gene expression, chromatin accessibility, histone modifications and DNA methylation for one biological condition at a time. Its training data includes more than 107 million single-cell profiles from 68 tissues.
In the company’s TenK10K evaluation, AlphaGenome 2 identified 30% of causal variants versus 16% for the previous model and specialized tools, and 43% of directional gene effects versus 23%. The model is available today through the AlphaGenome API for non-commercial research and in private preview for commercial research. DeepMind explicitly says it has not been validated or approved for clinical or diagnostic use.
Explore the original sources
Source date: 11 November 2026.
Published by AI Radar: 11 Nov 2026, 19:12 (Istanbul, UTC+3). Updated: 11 Nov 2026, 19:13.
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…