AlphaGenome is a Google DeepMind AI model that predicts how a stretch of DNA, and small changes to it, affect what happens inside human cells.
In plain words
Small differences in DNA can change how strongly genes are switched on in cells, which helps shape human traits and disease. AlphaGenome takes a DNA sequence as input and predicts those effects. The newest version, AlphaGenome 2, makes predictions for one chosen cell type or cell state at a time instead of broad tissue averages. Google DeepMind says it finds nearly twice as many DNA variants that change gene activity as the earlier model. Scientists reach it through an API that is free for non-commercial use.
A quick example
Imagine a researcher studying a rare disease who has found a single-letter DNA change in a patient. They ask AlphaGenome how that change would affect gene activity in heart muscle cells, and use the prediction to decide which change to test in the lab first.
Where you'll meet it
- Ranking which DNA variants to study in rare-disease research.
- Predicting gene activity in specific cell types.
- Exploring how DNA changes relate to traits and disease.
Related
Sources
- DocsAlphaGenome 2: Deciphering how cells read DNA to better understand disease, Google DeepMind · read 11 Nov 2026
- Docsgoogle-deepmind/alphagenome, GitHub · read 11 Nov 2026
Checked by WhatIsAI against the sources above · 11 Nov 2026. Spotted an error? Report it.