← November 11, 2026 briefing · added in the 00:00 KST update

Google DeepMind unveils AlphaGenome 2 to predict how DNA sequences and variants affect specific human cell types and disease

Announced November 11, 2026

Verified (fact)

Google DeepMind introduced AlphaGenome 2, the successor to AlphaGenome, on its official blog. It said the goal is to decode how cells read DNA, so the model can predict how DNA sequences and their variants affect specific human cell types and how they connect to disease. The collected excerpt does not include performance figures or availability details, such as whether an API or model weights will be offered.

Needs fact-check (claim)

Google DeepMind said the model predicts how DNA sequences and variants affect each cell type, helping researchers understand disease.

Why it matters (interpretation)

Interpreting genomic variants is a bottleneck in rare-disease diagnosis and drug-target discovery. Predicting variant effects at the cell-type level could let researchers screen candidates before running experiments. Actual performance and how much researchers can access still need to be checked in the original announcement.

Sources

More about Google