Alphabet

AlphaGenome 2

Research

DeepMind model that predicts how a DNA sequence and its variants affect one cell type or cell state at a time. The Nov. 11, 2026 post says training included over 107 million individual cell profiles. On TenK10K, DeepMind says it identified 30 percent of causal variants, compared with 16 percent for the prior model fine-tuned on single-cell data. Not validated for clinical or diagnostic use.

Latest update Nov 16, 2026

01

Current status

Non-commercial research through the AlphaGenome API. Commercial research is in private preview.

02

In the news1

  1. DeepMind releases AlphaGenome 2 for cell-specific DNA effects

    Google DeepMind said on Nov. 11 that AlphaGenome 2 predicts how a DNA sequence and its variants affect one cell type or cell state at a time, instead of averaging across a tissue. The lab said the model, trained on more than 107 million individual cell profiles, identified 30 percent of causal variants in the TenK10K immune-cell set, compared with 16 percent for the prior model fine-tuned on single-cell data. It is available for non-commercial research through the AlphaGenome API, with a private preview for commercial research, and DeepMind says it is not validated for clinical or diagnostic use.

    deepmind.google + Google DeepMind

03

More from Alphabet8

04

More in Big Tech