Bringing AI Into the Fold to Probe Protein Potential

These two Gairdner Award-winning scientists are using artificial intelligence to understand protein structures and move medical research forward.

 |  Transcript [PDF]

Proteins are the molecular machinery of life. They have many functions, and that diversity comes mainly from how they fold into unique 3D structures.

Demis Hassabis and John Jumper of Google DeepMind created AlphaFold to help predict these structures for almost every protein known to science, providing a solution that promises to accelerate biological and medical research.

For this breakthrough, they have been awarded the 2023 Canada Gairdner International Award.

“I’ve been working pretty much my entire career on artificial intelligence and trying to progress the state of the art in artificial intelligence, but I always had the aim to build it as a tool to accelerate scientific discovery,” says Hassabis, founder and CEO of DeepMind, and project leader on the AlphaFold project since its inception.

“AlphaFold is a deep learning system, a type of AI system, which predicts something called protein structures that biologists do to understand what goes on in the cell and what goes wrong, for example, when you have a disease,” adds Jumper, AlphaFold lead and senior staff research scientist at DeepMind.

This was a major advance on the state of the art because proteins are large, complex, and dynamic molecules. Prior to AlphaFold, uncovering the native structure of a protein under biological conditions experimentally was a costly and time-consuming process.

By contrast, AlphaFold takes the amino acid sequence of a protein and predicts its 3D structure in just minutes with atomic accuracy.

“Since we have so many proteins — we have, you know, 20,000 protein-coding genes — there’s this enormous set of problems that we need to solve to get this whole picture, really, to get a kind of parts list of the cell so that we can do more science and better science on top of it,” says Jumper.

“When we completed AlphaFold, we actually open sourced the code, and we folded all 200 million proteins pretty much known to science and made it freely available and accessible to any researcher in the world for any purpose,” adds Hassabis.

Reflecting on being notified about their Gairdner win, Jumper recalls getting a ‘mysterious’ email from Gairdner president Janet Rossant, asking to schedule a call.

“And a call with no details is either very good or very bad, so I was thrilled that it was about the Gairdner,” says Jumper.

“Canada itself created a lot of the new AI booms,” adds Hassabis.

“A lot of the researchers responsible for that were based in Canada and still are. So it’s sort of quite poignant, I think, that it’s a Canadian award for what essentially is applying AI to a Grand Challenge in biology.”

‹ Previous post
Next post ›

John Jumper received his PhD in Chemistry from the University of Chicago, where he developed machine learning methods to simulate protein dynamics. Prior to that, he worked at D.E. Shaw Research on molecular dynamics simulations of protein dynamics and supercooled liquids. He also holds an MPhil in Physics from the University of Cambridge and a B.S. in Physics and Mathematics from Vanderbilt University. At DeepMind, Jumper is leading the development of new methods to apply machine learning to protein biology.

Demis Hassabis is the Founder and CEO of DeepMind, the world’s leading AI research company, and now a part of Alphabet. Founded in 2010, DeepMind has been at the forefront of the field ever since, producing landmark research breakthroughs such as AlphaGo, the first program to beat the world champion at the complex game of Go, and AlphaFold, which was heralded as a solution to the 50-year grand challenge of protein folding.

A chess and programming child prodigy, Hassabis coded the classic AI simulation game Theme Park aged 17. After graduating from Cambridge University in computer science with a double first, he founded pioneering videogames company Elixir Studios, and completed a PhD in cognitive neuroscience at UCL investigating memory and imagination processes.

His work has been cited over 100,000 times and has featured in Science’s top 10 Breakthroughs of the Year on 4 separate occasions. He is a Fellow of the Royal Society, and the Royal Academy of Engineering. In 2017 he featured in the Time 100 list of most influential people, and in 2018 he was awarded a CBE.

Research2Reality is a groundbreaking initiative that shines a spotlight on world-class scientists engaged in innovative and leading edge research in Canada. Our video series is continually updated to celebrate the success of researchers who are establishing the new frontiers of science and to share the impact of their discoveries with the public.