Статья

Accurate structure prediction of biomolecular interactions with AlphaFold 3

Josh AbramsonCore Contributor, Google DeepMind, London, UKJonas AdlerCore Contributor, Google DeepMind, London, UKJack DungerCore Contributor, Google DeepMind, London, UKRichard EvansCore Contributor, Google DeepMind, London, UKTim GreenCore Contributor, Google DeepMind, London, UKAlexander PritzelCore Contributor, Google DeepMind, London, UKOlaf RonnebergerCore Contributor, Google DeepMind, London, UKLindsay WillmoreCore Contributor, Google DeepMind, London, UKAndrew J. BallardCore Contributor, Google DeepMind, London, UKJoshua BambrickSebastian W. BodensteinCore Contributor, Google DeepMind, London, UKDavid A. EvansCore Contributor, Google DeepMind, London, UKChia-Chun HungMichael O’NeillCore Contributor, Google DeepMind, London, UKDavid ReimanCore Contributor, Google DeepMind, London, UKKathryn TunyasuvunakoolCore Contributor, Google DeepMind, London, UKZachary WuGoogle (United Kingdom)Akvilė ŽemgulytėCore Contributor, Google DeepMind, London, UKEirini ArvanitiGoogle DeepMind, London, UKCharles BeattieGoogle DeepMind, London, UKOttavia BertolliGoogle DeepMind, London, UKAlex BridglandGoogle DeepMind, London, UKAlexey V. CherepanovMiles CongreveAlexander I. Cowen-RiversGoogle DeepMind, London, UKAndrew CowieGoogle DeepMind, London, UKMichael FigurnovGoogle DeepMind, London, UKFabian B. FuchsGoogle DeepMind, London, UKHannah GladmanGoogle DeepMind, London, UKRishub JainGoogle DeepMind, London, UKYousuf A. KhanDepartment of Molecular and Cellular Physiology, Stanford University, Stanford, CA, USACaroline M. R. LowKuba PerlinGoogle DeepMind, London, UKAnna PotapenkoGoogle DeepMind, London, UKPascal SavySukhdeep SinghGoogle DeepMind, London, UKAdrian StecułaAshok ThillaisundaramGoogle DeepMind, London, UKCatherine TongSergei YakneenEllen D. ZhongDepartment of Computer Science, Princeton University, Princeton, NJ, USAMichał ZielińskiGoogle DeepMind, London, UKAugustin ŽídekGoogle DeepMind, London, UKVictor BapstCore Contributor, Google DeepMind, London, UKPushmeet KohliCore Contributor, Google DeepMind, London, UKMax JaderbergCore Contributor, Isomorphic Labs, London, UK. [email protected]Demis HassabisCore Contributor, Google DeepMind, London, UK. [email protected]John JumperCore Contributor, Google DeepMind, London, UK. [email protected]

2024en

ABI

Аннотация

Abstract The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design 2–6 . Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3 7,8 . Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Перевод пока недоступен

Идентификаторы

DOI: 10.1038/s41586-024-07487-w

Цитирования и источники

Цитирований: 5Использованных источников: 0

Показатели — AkademScholar