👏🤦🏻♀️👏🤦🏻♀️👏🤦🏻♀️ 50-years of open problem closed.
Proteins are essentially correctly folded and well-functioning polypeptide chains. So theoretically, protein 3D structures are determined by the sequence of amino acids in the polypeptide chain. The Nobel Prize in Chemistry (1972) was awarded to C. Anfinsen for this finding.
amino acids make up proteins essentially like LEGOS. importantly, proteins function only when they are folded and form their structure in the right way
Since then, determining 3D protein structure has been the grand challenge for biology. Doing it experimentally is a way—bascially it’s taking photos of proteins, but using X-ray instead of natural light, and also because you have to freeze the object for a nice shot, proteins need to be crystalized—hence, ‘X-ray crystallography’. And NMR spectroscopy. Both are expensive, experimental, lengthy methods.
AI said, nah you guys are too slow:
the Nobel Prize in Chemistry 2024:
David Baker (1/2) | U. Washington, Seattle
‘for computational protein design’;
Demis Hassabis and John M. Jumper (jointly 1/2) | Google DeepMind, London, UK
‘for protein structure prediction’.
Reference: the official press release from nobelprice.org.
And some more nice pictures from the press release that explains everything:
how does AlphaFold2 work?
an AI model trained to predict protein structure from its amino acid sequence
artificial protein design:
the first artificial protein that is completely different to all known existing proteins in nature
AlphaFold2 predicting protein structure
Protein structures determined using AlphaFold2