Skip to content

AlphaGenome 2: Google DeepMind's AI reads non-coding DNA to spot disease

Google DeepMind · · 30-second read

Share

Top comments from YouTube.

    This story is from November 11, 2026. For the latest, see today's news.

    November 11, 2026 · AI Tech

    Google DeepMind released AlphaGenome 2, an AI system that analyzes the 98% of human DNA responsible for controlling how cells function, rather than building proteins directly. The model uses transformer architecture to read non-coding DNA at single-cell resolution, identifying mutations that cause disease and explaining why most new drugs fail in clinical trials.

    In a video interview, DeepMind researchers Žiga Avsec and Adam Gayoso discuss how AlphaGenome works, the AlphaGenome Atlas resource it created, and how the technology pinpoints disease-causing variants. The model represents a shift toward understanding the molecular blueprint of human life by decoding regulatory DNA sequences that were previously difficult to interpret computationally.

    Read the full story at Google DeepMind

    This is an AI-written summary. The original reporting belongs to Google DeepMind. How we write these · Spot a mistake?

    Get the AI brief every morning.

    The five AI stories that matter each morning: startups, money, jobs, tech and what's coming next. Free, and one click to unsubscribe. See our Privacy Policy.