From the source
Google DeepMind has unveiled AlphaGenome 2, a DNA model that predicts how genetic variants affect individual cell types and states, giving scientists a finer-grained view of disease biology than its predecessor.
- The model was trained on more than 100 million individual cell profiles across 68 tissues, and DeepMind says it identifies nearly twice as many variants that can change gene expression in cells as its previous state-of-the-art model.
- According to the company, AlphaGenome 2 can also make predictions about new cell types and biological states without retraining, and can flag gaps in experimental data to help scientists decide what to investigate next.
- Adam Gayoso, a research scientist involved in the project, told The Verge the big breakthrough is "tying human genetics to cell biology," while genomics lead Žiga Avsec said the granularity matters because drug development targets specific proteins and cell types.
- Avsec said the more detailed predictions come at a computational cost and are "more expensive" than AlphaGenome's, which would have made it impractical for the genome-wide Atlas DeepMind released in September.
- Google says AlphaGenome 2 is available for non-commercial research via the AlphaGenome API from today, with a limited "private preview" for commercial research.