Accurate structure prediction of biomolecular interactions with AlphaFold 3.

Journal: Nature
PMID: 38718835

Abstract

The introduction of AlphaFold 2 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design. 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. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Authors

  • Josh Abramson
    Core Contributor, Google DeepMind, London, UK.
  • Jonas Adler
  • Jack Dunger
    Core Contributor, Google DeepMind, London, UK.
  • Richard Evans
    DeepMind, London, UK.
  • Tim Green
    DeepMind, London, UK.
  • Alexander Pritzel
    DeepMind, London, UK.
  • Olaf Ronneberger
    DeepMind, London, EC4A 3TW, UK.
  • Lindsay Willmore
    Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA.
  • Andrew J Ballard
    DeepMind, London, UK.
  • Joshua Bambrick
    Core Contributor, Isomorphic Labs, London, UK.
  • Sebastian W Bodenstein
    Core Contributor, Google DeepMind, London, UK.
  • David A Evans
    Core Contributor, Google DeepMind, London, UK.
  • Chia-Chun Hung
    Core Contributor, Isomorphic Labs, London, UK.
  • Michael O'Neill
    Natural Computing Research and Applications Group, School of Business, University College Dublin, Ireland.
  • David Reiman
    DeepMind, London, UK.
  • Kathryn Tunyasuvunakool
    DeepMind, London, UK. ktkool@deepmind.com.
  • Zachary Wu
    Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA, USA.
  • Akvilė Žemgulytė
    Core Contributor, Google DeepMind, London, UK.
  • Eirini Arvaniti
    Institute for Molecular Systems Biology, Department of Biology, ETH Zurich, Auguste-Piccard-Hof 1, Zurich 8093, Switzerland.
  • Charles Beattie
    Google DeepMind, 5 New Street Square, London EC4A 3TW, UK.
  • Ottavia Bertolli
    Faculty, London, UK.
  • Alex Bridgland
    DeepMind, London, UK.
  • Alexey Cherepanov
    Isomorphic Labs, London, UK.
  • Miles Congreve
    Isomorphic Labs, London, UK.
  • Alexander I Cowen-Rivers
    Google DeepMind, London, UK.
  • Andrew Cowie
    DeepMind, London, UK.
  • Michael Figurnov
    DeepMind, London, UK.
  • Fabian B Fuchs
    Google DeepMind, London, UK.
  • Hannah Gladman
    Google DeepMind, London, UK.
  • Rishub Jain
    DeepMind, London, UK.
  • Yousuf A Khan
    Google DeepMind, London, UK.
  • Caroline M R Low
    Isomorphic Labs, London, UK.
  • Kuba Perlin
    Google DeepMind, London, UK.
  • Anna Potapenko
    DeepMind, London, UK.
  • Pascal Savy
    Isomorphic Labs, London, UK.
  • Sukhdeep Singh
    Department of Radiology, Mayo Clinic, Phoenix, AZ, USA.
  • Adrian Stecula
    Atomwise Inc., San Francisco, California 94103, United States.
  • Ashok Thillaisundaram
    Google DeepMind, London, UK.
  • Catherine Tong
    International Society for Disease Surveillance, Boston, MA.
  • Sergei Yakneen
    Isomorphic Labs, London, UK.
  • Ellen D Zhong
    Computational and Systems Biology, Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Michal Zielinski
    DeepMind, London, UK.
  • Augustin Žídek
    DeepMind, London, UK.
  • Victor Bapst
    Core Contributor, Google DeepMind, London, UK.
  • Pushmeet Kohli
    DeepMind, London, UK.
  • Max Jaderberg
    DeepMind, London, UK. lejlot@google.com jaderberg@google.com.
  • Demis Hassabis
    Google DeepMind, 5 New Street Square, London EC4A 3TW, UK.
  • John M Jumper
    Core Contributor, Google DeepMind, London, UK. jumper@google.com.

Keywords

External Resources

Popular Topics
Recent Journals