UChicago graduate John Jumper wins Nobel Prize for model for predicting protein structures

Editor's note: This story will be updated throughout the day.

University of Chicago graduate John Jumper received a share of the 2024 Nobel Prize in Chemistry on October 9 for developing an AI model that predicts the complex folding structures of proteins.

The Royal Swedish Academy of Sciences honored Jumper, who received his master's degree in 2012 and his Ph.D. received. from the University of Chicago in 2017, along with Demis Hassabis, for their work on “protein structure prediction.” The prize is also shared with Prof. David Baker of the University of Washington “for computational protein design.”

Jumper is the 100th scientist associated with the university to receive a Nobel Prize.

“It’s absolutely extraordinary,” Jumper said. “I have been working on computational biology for a long time and like to say in lectures: We need this to make it work. We need calculations to solve the problems of biology, and I just love that it’s starting to work.”

Jumper and Hassabis are co-inventors of the AlphaFold system, released by a company called Google DeepMind. The Nobel Committee wrote that they “used artificial intelligence to successfully solve a problem that has plagued chemists for over 50 years: predicting the three-dimensional structure of a protein from a sequence of amino acids.”

Scientists around the world have assembled the genetic sequences for everything from corn to tedious E.coli to people. But the genetic sequence is just a starting point – most of the work in a cell is done by proteins, which arise from the genetic sequence but are then folded into complex 3D configurations to carry out their functions. Knowing the shapes of proteins is crucial for understanding how cells work and, for example, for developing drugs to treat diseases. But for decades it remained difficult to predict how a protein would fold based solely on its genetic data.

DeepMind released an open source version of a program called AlphaFold in July 2021 that has proven to be exceptionally good at predicting the shapes of proteins. Since then, loudly Nature, It has been used by more than half a million researchers and led to thousands of papers on topics ranging from antibiotic resistance to crop resilience.

Jumper said: “What I love about all of this is that because of what we learn about the biology in the cell and everything else, we can draw a direct connection between what we do and people's health, and That’s just extraordinary.”

Jumper received his Ph.D. in theoretical chemistry from the University of Chicago in 2017; In his dissertation, he investigated how to apply machine learning techniques to the study of protein dynamics. He was advised by Profs. Karl Freed and Tobin Sosnick and then worked as a postdoctoral researcher in Sosnick's lab before moving to Google DeepMind.

Freed is Henry G. Gale Distinguished Service Professor Emeritus in the Department of Chemistry and the James Franck Institute. Tobin Sosnick is the William B. Graham Professor of Biochemistry and Molecular Biology and currently chairs the department. He is also a member of the Institute for Biophysical Dynamics.