AlphaGenome: DeepMind’s AI Maps the Genome’s Hidden Rules
TL;DR
DeepMind’s AlphaGenome trains an AI on vast molecular data to forecast how mutations and regulatory DNA elements alter gene activity, extending the AlphaFold-era breakthrough from proteins to the genome; experts see it as a major engineering advance with potential for cancer and disease research, but stress it remains a predictive tool—its scope is limited to single mutations in a given genome, its predictions don’t capture all splice-site complexities, and clinical use still requires lab validation.
- With AlphaGenome, Researchers Are Using A.I. to Decode the Human Blueprint The New York Times
- Google DeepMind launches AI tool to help identify genetic drivers of disease The Guardian
- AI model from Google's DeepMind reads recipe for life in DNA BBC
- DeepMind releases AlphaGenome source code, aiming to improve its AI predictions of gene regulation statnews.com
- DeepMind's New AI Can Read a Million DNA Letters at Once—and Actually Understand Them Gizmodo
Want the full story? Read the original reporting
Read on The New York Times