Two Google DeepMind scientists and an American biochemist have been awarded the 2024 Nobel Prize in Chemistry for their groundbreaking work in predicting and designing protein structures.
Demis Hassabis, DeepMind's UK founder, and John Jumper, who led the development of the company's AI model AlphaFold, which predicts the structure of proteins based on their chemical sequences, will share half of the prize.
The other half was awarded to Professor David Baker of the University of Washington. His computational research has led to the creation of entirely new classes of proteins, including applications in vaccines, nanomaterials, and small sensors.
The winners will be announced by the Royal Swedish Academy of Sciences in Stockholm and will share a prize of 11 million Swedish krona (£810,000). Computer-aided protein design and protein structure prediction.
Heiner Linke, Chairman of the Nobel Committee for Chemistry, said: “One of the discoveries made this year concerns the construction of amazing proteins.The other is the prediction of protein structures from amino acid sequences. It's about realizing an old dream. Both of these discoveries offer vast possibilities.”
At a press conference shortly after the announcement, Baker said he woke up to a phone call from the Academy informing him of the win, and explained how his ambition to create an entirely new protein began as a dream more than 20 years ago. Advances in computing and scientific understanding during this time have paved the way for this vision to have a meaningful impact on the world, including designing new vaccines for the coronavirus, he said.
“We initially got a glimpse that it might be possible to create a whole new world of proteins that would address many of the problems facing humanity in the 21st century,” Baker said. “Now it's becoming possible.”
Proteins control and drive all chemical reactions that are the basis of life. They function as hormones, antibodies, and building blocks for various tissues. Baker's mission was to design a new protein that does not exist in nature, and he succeeded in 2003. Since then, his group has produced novel proteins that have a wide range of applications in medicine and materials science.
After newsletter promotion
Proteins are typically made up of 20 different amino acids that are linked and folded into long strings to form three-dimensional structures. It is these structures and chemical compositions that determine how proteins interact and whether they bind to drugs in the body, among other things. Since the 1970s, scientists have been trying to predict the three-dimensional structure of proteins from their chemical sequences, but the problem is notoriously difficult and progress has been slow.
Four years ago, something groundbreaking happened. In 2020, Hassabis and Jumper announced the development of an AI model called AlphaFold 2. With its help, researchers were able to predict the structure of almost all of the 200m proteins they identified. Since its breakthrough, AlphaFold 2 has been used by more than 2 million people in 190 countries for applications such as understanding antibiotic resistance and developing enzymes that can break down plastic.
Dr Annette Doherty, President of the Royal Society of Chemistry, said: We are confident that their work will serve as an inspiration to future generations, just as the discoveries of our predecessors with this most prestigious of honors. ”
