Google DeepMind releases AlphaGenome 2: DNA variant prediction for specific cell types

Google DeepMind announced AlphaGenome 2 on November 11, 2026, a next-generation DNA sequence model that predicts how DNA sequences and their variants affect specific human cell types and states, such as a heart muscle cell or an immune cell fighting an infection. AlphaGenome 2 is available today for non-commercial research via the AlphaGenome API, and in private preview for commercial research, with interactive Colab tutorials for expression conditioning. DeepMind says it is intended for research use only and has not been validated or approved for clinical or diagnostic use.

Unlike the first AlphaGenome, which predicted molecular activity across broad tissues all at once, AlphaGenome 2 is a conditional model: alongside a DNA sequence of up to one million letters it takes one biological condition, a tissue, cell type or state, from a reference catalog or generated from a scientist's own single-cell experiment, and predicts gene expression, chromatin accessibility, histone marks and DNA methylation for that condition. DeepMind trained it on bulk and single-cell data from human and mouse samples, including more than 107 million individual cell profiles across 68 tissues.

On TenK10K, a single-cell map of 28 primary immune cell types, AlphaGenome 2 recovered 30% of putatively causal expression-linked variants at 90% precision, compared with 16% for AlphaGenome 1 fine-tuned on single-cell data, in DeepMind's own evaluation. It also reproduced a published inflammatory bowel disease finding, singling out the causal variant that boosts the ETS2 gene in gut macrophages. Because the model separates a cell's biological state from its outputs, it can also predict unmeasured properties, such as chromatin accessibility, from a single measurement like single-cell gene activity.