Google DeepMind releases AlphaGenome Atlas: a predictive map of every possible DNA letter change in the human genome
Google DeepMind introduces AlphaGenome Atlas, a catalogue predicting molecular effects for 9 billion single-nucleotide variants across the human genome, accompanied by the AlphaGenome Variant Impact (AVI) score. The platform is available through a website portal, an API, and a Google Antigravity skill, free for academic research.
What happened
Event details
Google DeepMind announced AlphaGenome Atlas, a catalogue predicting the molecular effects of all 9 billion single-nucleotide variants in the human genome, described as the most comprehensive catalogue of how genetic mutations affect molecular biology. The release includes the AlphaGenome Variant Impact (AVI) score, which combines AlphaGenome and AlphaMissense predictions into a single number for ranking variants. AlphaGenome Atlas is a 1-petabyte dataset, more than 30 times larger than the AlphaFold Database. The platform is available through a website portal, the AlphaGenome API, and as a skill in Google Antigravity, free for academic research. According to the official announcement, external collaborators have already used AlphaGenome Atlas to identify and experimentally verify key variants in unsolved rare disease research and to find rare variants associated with common traits.
Assessment
Why it matters
This is a distinct, materially important scientific release from Google DeepMind: a platform cataloguing predictions for all 9 billion possible single-nucleotide variants in the human genome, introducing the AVI score, far exceeding the AlphaFold Database in scale, and already used by external collaborators in rare disease and common trait research.
Availability
Access notes
The official blog states the platform is available through a website portal, the AlphaGenome API, and a Google Antigravity skill, free for academic research.