AlphaGenome 2 predicts DNA effects in specific cell types
AlphaGenome 2 is a new DNA-sequence model designed to predict how genetic variants influence gene activity in particular human cell types and states. Its developers say the system links single-cell biology with human genetics, helping researchers investigate cellular mechanisms associated with disease.
The model was trained on more than 107 million individual cell profiles from human and mouse samples across 68 tissues. Unlike the earlier version, which produced parallel predictions for broad tissues and cell lines, AlphaGenome 2 conditions its analysis on one tissue, cell type or biological state at a time. It can also use a small single-cell experiment to represent previously unseen states without retraining, and can estimate missing measurements such as chromatin accessibility from available gene-activity data.
On the TenK10K dataset of 28 primary immune cell types, the developers report that AlphaGenome 2 identified 30% of causal variants, compared with 16% for the previous model, and detected directional gene effects at rates of 43% versus 23%. The model is available through the AlphaGenome API for non-commercial research and in private preview for commercial research. It has not been validated or approved for clinical or diagnostic use.
Written by Sakhanda Wire AI from reporting by DeepMind. Facts, quotes and full context are in the original article below.