Google DeepMind Releases AlphaGenome 2 AI Model for Cell-Specific DNA Analysis

Google DeepMind released AlphaGenome 2, an AI model that predicts how DNA variants affect specific cell types to help scientists understand disease. Trained on over 100 million profiles across 68 tissues, it identifies nearly twice as many gene-regulating mutations as its predecessor. The model is available for non-commercial research via API and Colab tutorials.
Event version 1.
Key insights
Cell-specific DNA analysis
AlphaGenome 2 focuses on one cell type at a time rather than whole tissues, predicting how the same DNA sequence is read differently from cell to cell. This approach addresses how a single-letter DNA change can affect disease in some cells while sparing others.
Improved mutation detection
Trained on more than 100 million profiles across 68 tissues, the model spots nearly twice as many mutations that turn genes on and off compared with the previous model.
Adapts without retraining
The model adapts to lab experiments on the fly with no retraining needed. Researchers can plug in data from just a few dozen cells to observe DNA changes in specific contexts such as immune cells responding to a vaccine, gut cells driving inflammatory disease, or stem cells maturing into blood cells.
Availability for research
AlphaGenome 2 is available now for non-commercial research via API and interactive Colab tutorials.