Google DeepMind has released AlphaGenome Atlas, a platform containing predictions for the effects of 9 billion single-nucleotide variants across the entire human genome. This resource aims to accelerate biological understanding by providing a comprehensive map of how genetic mutations affect molecular biology.

  • The dataset is a massive 1-petabyte collection, more than 30 times larger than the AlphaFold Database.
  • It includes thousands of molecular effect predictions for each variant across hundreds of human and mouse cell types.
  • Google DeepMind also released the AlphaGenome Variant Impact (AVI) score, which combines AlphaGenome and AlphaMissense predictions into a single number to rank variant impact.
  • AVI feature attributions highlight specific biological processes disrupted by each variant, such as RNA splicing or gene expression.
  • External collaborators have already used the tool to identify causal variants in rare diseases and uncover non-coding genetic associations in population data.

AlphaGenome Atlas is available for academic research through a website portal, API, and Google Antigravity skill, with commercial access coming soon via Google Cloud.