Google DeepMind released AlphaGenome Atlas, which predicts the molecular effects of every possible single-letter DNA change in the human genome; the dataset is 1 petabyte and covers about 9 billion single-nucleotide variants, more than 30 times the size of the AlphaFold Database. The Atlas introduces an AlphaGenome Variant Impact (AVI) score that compresses predictions from AlphaGenome and AlphaMissense into a single value for ranking variant effects, along with feature attribution for interpretability. DeepMind says work with the University of Exeter analyzing whole-genome data from more than 54,000 UK Biobank participants surfaced 22% more non-coding genetic associations. The Atlas is available now through a free web portal for academic research, with commercial use coming to Google Cloud; DeepMind states AlphaGenome is not clinically validated or approved for any clinical use.

Editor's note

This summary is based on the primary source. Open the original for full context, data, and qualifying details.