AlphaFold – The Most Useful Thing AI Has Ever Done
The biggest problems in the world might be solved by tiny molecules unlocked using AI. This film looks at AlphaFold, the AI system from Google DeepMind that predicts the three-dimensional structure of proteins — a problem biologists had struggled with for decades.
Derek Muller explains how to determine protein structures, why proteins are so complicated, and how the CASP competition and DeepMind’s work led to AlphaFold. With John Jumper and Kathryn Tunyasuvunakool at Google DeepMind, and David Baker at the Institute for Protein Design at the University of Washington, he shows how AlphaFold works — including the transformer architecture and the structure module — and what three ways of getting better AI might look like.
AlphaFold 2 went on to win the Nobel Prize, and the film looks at what comes next: designing entirely new proteins with tools like RF Diffusion, and the future of AI in science.
Key Themes & Topics Examined
- Why predicting protein structures is so hard
- The CASP competition and DeepMind
- How AlphaFold works: transformers and the structure module
- AlphaFold 2 and the Nobel Prize
- Designing new proteins with RF Diffusion
Archival & Investigative Sources
- John Jumper and Kathryn Tunyasuvunakool at Google DeepMind.
- David Baker and the Institute for Protein Design at the University of Washington.
- The CASP competition and AlphaFold’s breakthrough.
Recommended Companion Viewing
Explore authoritative investigative documentaries on related historical events and investigative subjects.
Frequently Asked Questions
What is this documentary about?
It explains how AlphaFold, the AI system from Google DeepMind, predicts the structure of proteins.
Who explains AlphaFold in the film?
Derek Muller, with John Jumper and Kathryn Tunyasuvunakool at Google DeepMind and David Baker at the University of Washington.
What recognition did AlphaFold 2 receive?
It won the Nobel Prize.







