Wikinventia — Atlas of discoveries and inventions · Digital Age

AlphaFold 3 — prediction of biomolecule structure and interactions, including pathological misfolding

2024 AD · Transmission: Global
AIMethodBritish

Google DeepMind and Isomorphic Labs present in 2024 AlphaFold 3, an AI model that predicts the structure and interactions of virtually all the molecules of life — proteins, DNA, RNA, ligands, and ions — with unprecedented accuracy, broadening the scope of earlier versions (AlphaFold, 2020; AlphaFold 2, 2020) focused on predicting individual protein structure. Unlike its predecessors, AlphaFold 3 incorporates a diffusion module that also allows modeling pathological protein misfolding, the same underlying problem that decades earlier motivated Stanley Prusiner's research on prions. The model was published in a paper in Nature in June 2024, and its code and weights were released for academic use in November of that year.

InstitutionGoogle DeepMind / Isomorphic Labs
Historical regionUnited Kingdom — London
Primary sourceAbramson, J., Adler, J., Dunger, J. et al. — "Accurate structure prediction of biomolecular interactions with AlphaFold 3" (Nature, 630, 493–500, 2024). DOI: 10.1038/s41586-024-07487-w
Secondary sourceGoogle DeepMind — "AlphaFold 3 predicts the structure and interactions of all of life's molecules" (blog.google, May 2024)
Original languageEnglish
View this entry in the interactive atlas → View in graph →