AlphaFold, the artificial intelligence tool developed by Google DeepMind to predict protein structure, marked a watershed moment in protein modeling and drug discovery. AlphaFold 2 is able to predict the three-dimensional structure of proteins with very high accuracy — close to that obtained experimentally, which takes months to years. The latest iteration, AlphaFold 3 (released in May), goes a step further, achieving greater accuracy than its predecessor, along with expanded functionality. AlphaFold 3 can predict the structure of not only proteins but also complexes that contain proteins and other structures, such as nucleic acids and small molecules. Indeed, the authors expect that modeling capabilities will continue to improve, due to advances in both deep learning and experimental approaches. In recognition of the importance of these advances, half of the Nobel Prize for chemistry has been awarded to John Jumper and Demis Hassabis, who led the development of AlphaFold (with the other half awarded to David Baker, University of Washington, for achievements in computational protein design).

Original references: Nature 630, 493–500 (2024); NobelPrize.org https://go.nature.com/4evrnLN (13 November 2024)