# AlphaGenome 2 finds 30% of causal variants on the TenK10K test, nearly double its predecessor

DeepMind's new model predicts a variant's effect one cell type at a time from a 1-megabase (about 1 million DNA base pair) window of sequence. It was trained on more than 107 million single-cell profiles and is now in private preview for commercial research.

- Published: 2026-11-12T06:18:53.763Z
- Canonical: https://polylog.news/ai/2026-11-12/alphagenome-2-finds-30-of-causal-variants-on-the-tenk10k-tes
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://deepmind.google/blog/alphagenome-2-deciphering-how-cells-read-dna-to-better-understand-disease/), [Polylog editors](https://polylog.news), [MarkTechPost](https://www.marktechpost.com/2026/11/11/google-deepmind-alphagenome-2-cell-type-variant-effects/), [Nature](https://www.nature.com/articles/d41586-026-03673-0)

Google DeepMind released AlphaGenome 2 on November 11. The model predicts how a DNA change affects gene regulation in a specific cell type. The first AlphaGenome made predictions at the level of whole tissues. As the AI Post channel put it,…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-12/alphagenome-2-finds-30-of-causal-variants-on-the-tenk10k-tes (subscription information: https://polylog.news/pricing).