AlphaGenome 2: Deciphering how cells read DNA to better understand disease
AlphaGenome 2 identified 30% of causal variants in an immune-cell benchmark, up from 16% for its predecessor fine-tuned on single-cell data.
The model predicts DNA effects for a specific tissue, cell type or cell state, helping isolate effects that broad tissue averages can miss. Researchers can supply new single-cell gene activity data to predict variant effects in previously unseen cell states without retraining. Access is available through the AlphaGenome API for non-commercial research, with commercial research in private preview. The model has not been validated or approved for clinical or diagnostic use.
Google DeepMind's note
The model predicts DNA effects for a specific tissue, cell type or cell state, helping isolate effects that broad tissue averages can miss. Researchers can supply new single-cell gene activity data to predict variant effects in previously unseen cell states without retraining. Access is available through the AlphaGenome API for non-commercial research, with commercial research in private preview. The model has not been validated or approved for clinical or diagnostic use.
Google DeepMind's note
score 7