200mprotein structures AlphaFold has predicted, roughly every known proteinDesignPrize09.10.24
Chemistry Nobel rewards the tools now used to design peptide binders
David Baker shares the 2024 prize for computational protein design with Demis Hassabis and John Jumper for AlphaFold.
Amino Weekly science desk9 Oct 20242 min read
The prize
The Royal Swedish Academy of Sciences split the 2024 Nobel Prize in Chemistry. Half went to David Baker at the University of Washington “for computational protein design”. The other half went to Demis Hassabis and John Jumper of Google DeepMind “for protein structure prediction”.
Two halves of one problem
Proteins and peptides are chains of amino acids that fold into shapes, and the shape decides what they do. For 50 years, predicting the shape from the sequence was one of biology’s hardest problems. AlphaFold 2, released in 2020, largely solved it for single proteins, and its database now covers about 200 million structures.
Baker’s group works the other way round: start with the shape you want and find a sequence that folds into it. Since the early 2000s it has designed proteins that do not exist in nature, and more recently has used AI tools such as RFdiffusion to design binders, enzymes and ring peptides.
Why peptide researchers care
Both tools now sit at the start of many peptide projects. Structure prediction shows where a peptide hormone docks on its receptor. Design tools invent binders against toxins, viruses or cancer proteins, sometimes in days.
The prize recognises methods. Most designed molecules are still in labs or early trials, and the hard parts of drug development, such as safety, dosing and manufacture, are unchanged.
Source Nobel Prize in Chemistry 2024 announcement, 9 October 2024
Amino Weekly reports research. It is not medical advice and never gives doses.