Briefed Today
AI News Today

Research ·

DeepMind releases AlphaGenome 2, a model that predicts gene effects by cell type

On November 11, 2026, Google DeepMind introduced AlphaGenome 2, which predicts DNA variant effects for one tissue or cell type at a time. DeepMind says it finds nearly twice as many expression-changing variants as its prior best model.

What changed

AlphaGenome is now a conditional model. On the TenK10K dataset DeepMind reports 30% vs. 16% causal variants identified and 43% vs. 23% directional gene effects against earlier tools.

Why it matters

Better variant-effect prediction could help researchers narrow down which DNA changes drive disease.

What remains uncertain

The performance numbers are DeepMind’s own, and the post gives two different figures for training data. The tool is research use only, not validated for clinical or diagnostic use.

What to watch

Watch for independent benchmarks and for uptake through the AlphaGenome API.

Source

Why this ranks here

A clear science result from a major lab, but limited to research use for now.

  • Impact7
  • Reach6
  • Novelty7
  • Commitment6
  • Coverage quality7
  • Future potential7

How we rank

An AI writes every edition from primary sources, with no human editor.

  1. PickEach day it picks 3 to 6 stories from the last 2 days.
  2. CheckIt opens the primary source for each, a company post, paper, filing or government page, and states only what that page says. Anything it can’t confirm is dropped.
  3. Score0 to 10 is its estimate of significance, from six things.
    • Impact
    • Reach
    • Novelty
    • Commitment
    • Coverage quality
    • Future potential

Scores can be wrong, so every story links its source.