Imma Perfetto
Cosmos science journalist
A trio of scientists have been awarded the Nobel Prize in Chemistry for their groundbreaking work using computing and artificial intelligence to unlock the secrets of protein structure.
“One of the discoveries being recognised this year concerns the construction of spectacular proteins,” says Heiner Linke, Chair of the Nobel Committee for Chemistry.
“The other is about fulfilling a 50-year-old dream: predicting protein structures from their amino acid sequences. Both of these discoveries open up vast possibilities.”
David Baker, Professor at the University of Washington and Howard Hughes Medical Institute, USA, has been recognised for designing a computer program, Rosetta, and using it to create new proteins never seen before in nature.
He shares the award with Demis Hassabis and John M. Jumper of Google DeepMind in the UK for their work developing the AI model AlphaFold2, which predicts the 3-dimensional structure of proteins from their sequence of amino acids.
Proteins are essential components of life, carrying out a vast array of functions within living organisms – from driving chemical reactions, to responding to stimuli, to providing structures to cells, and more.
They are built from endless combinations of 20 amino acids, which are strung together like beads on a string. This string of amino acids folds up to form a distinct 3-dimensional structure which gives the protein its function.
Scientists have used several techniques, such as X-ray crystallography, to solve the structures of proteins. But these methods are expensive and can take years of research, if they are successful at all.
The goal has always been to find a way to predict the final structure of a protein from simply it’s amino acid sequence, and Hassabis and Jumper largely solved the problem in 2020 with AlphaFold2.
Since then, the AI program has predicted the structures of the more than 200 million proteins known to science and, as the code is publicly available, has been used by more than 2 million people from 190 countries for their own research.
Baker is recognised for largely solving the opposite problem: “de novo” protein structure design.
“There’s always been 2 sides to the protein folding problem, going from sequence to structure and then back from structure to sequence. And I think it’s neat that that there’s a Noble Prize for them together,” Baker said in an interview for Nobel Prize website.
Baker showed that you could design an entirely new protein structure.
He used his Rosetta computer program which could compute the amino acid sequence that would produce such an outcome and in 2003, Baker and his team generated an entirely new protein – Top7.
Since then, Baker’s laboratory has produced many more new proteins loaded with new functions. They have also released the code for Rosetta for the wider research community to use and further develop.
“Now with the ability to design new proteins, specifically to solve problems, there’s just so many possibilities. It’s really exciting,” said Baker.
A feature on AlphaFold 2 and its most recent iteration, AlphaFold3, appears in the latest issue of the Cosmos print magazine edition 104 in the article: “Solving life’s origami: the protein structure problem”
