Google DeepMind Releases AlphaGenome 2 for Cell-Specific Genomics Research

What happened

Google DeepMind has released AlphaGenome 2, a genomics model that predicts how genetic variants affect specific human cell types. Trained on more than 107 million cell profiles from 68 human and mouse tissues, it identified about 30 percent of causal variants on the TenK10K benchmark, compared with 16 percent for a fine-tuned AlphaGenome 1. It is available for noncommercial research through an API; commercial access is in a closed preview.

Read next

• More changes in today’s briefingGoogle DeepMind Introduces Gemini 4 Hydrogen for Fast Agentic Workflows

Reported by 6 sources

The story so far

Google DeepMind has released AlphaGenome 2, a model that predicts how DNA variants affect specific human cell types and states. The model is available through the AlphaGenome API for non-commercial research, while commercial research access is in a closed private preview. Google says it is intended for research and has not been validated or approved for clinical or diagnostic use. Google says AlphaGenome 2 was trained on more than 107 million cell profiles. On the TenK10K benchmark, it identified nearly twice as many causal variants as the original AlphaGenome; The Decoder reports about 30 percent for AlphaGenome 2 versus 16 percent for a fine-tuned AlphaGenome 1.