Google DeepMind has introduced AlphaGenome Atlas, a catalogue that predicts the molecular effects of 9 billion single-nucleotide variants across the human genome. A single-nucleotide variant is a change to one DNA letter.
The atlas turns AlphaGenome’s predictions into a large reference map rather than requiring researchers to evaluate variants one at a time. It also includes AVI scores, which are intended to help describe the predicted effects of individual variants.
This is a predictive resource, not clinical proof that a particular variant causes a disease or that a treatment will work. Its practical value is in helping scientists explore and prioritize an enormous search space for further study. Experimental and clinical validation remain necessary before predictions can support medical decisions.