AlphaGenome 2: Teaching AI to read the entire human genome

According to the description, Hannah Fry talks with Google DeepMind's Ziga Avsec and Adam Gayoso about AlphaGenome, the AlphaGenome Atlas and AlphaGenome 2, which read non-coding DNA down to single-cell resolution to pinpoint disease-causing mutations.

Why it matters

The same thing, for different readers.

What it means for you

Google DeepMind says its new AI can help explain how DNA outside protein-coding regions causes disease, which could speed up medical research.

For researchers

DeepMind reports AlphaGenome 2 working at single-cell resolution on non-coding DNA; results are the company's own and not independently assessed in the description.

The record

Questions
How is AI changing childhood, health and daily life? · How fast is AI advancing, and where is it heading?
People
Hannah Fry (Speaks, Professor) · Ziga Avsec (Speaks, Google DeepMind) · Adam Gayoso (Speaks, Google DeepMind)
What we read
We have read only the description the publisher gives. No quotations until someone reads the source itself.
Found by
The Radar, run of November 12, 2026, via yt-google-deepmind (tier 1: the source’s own channel or an official record)
Cite this
Google DeepMind, “AlphaGenome 2: Teaching AI to read the entire human genome”, November 11, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/deepmind-2026-11-11-alphagenome-2-podcast
Our notesLight lane: description only; this is a company-produced podcast.