Scalable emulation of protein equilibrium ensembles with generative deep learning.

Journal: Science (New York, N.Y.)
Published Date: Aug 14, 2025

Abstract

Following the sequence and structure revolutions, predicting functionally relevant protein structure changes at scale remains an outstanding challenge. We introduce BioEmu, a deep learning system that emulates protein equilibrium ensembles by generating thousands of statistically independent structures per hour on a single graphics processing unit (GPU). BioEmu integrates more than 200 milliseconds of molecular dynamics (MD) simulations, static structures, and experimental protein stabilities using new training algorithms. It captures diverse functional motions-including cryptic pocket formation, local unfolding, and domain rearrangements-and predicts relative free energies with 1 kilocalorie per mole accuracy compared with millisecond-scale MD and experimental data. BioEmu provides mechanistic insights by jointly modeling structural ensembles and thermodynamic properties. This approach amortizes the cost of MD and experimental data generation, demonstrating a scalable path toward understanding and designing protein function.

Authors

  • Sarah Lewis
    Discipline of Medical Imaging Science, Faculty of Medicine and Health, University of Sydney, Sydney, NSW, Australia. sarah.lewis@sydney.edu.au.
  • Tim Hempel
    Freie Universität Berlin, Department of Mathematics and Computer Science, Berlin, Germany.
  • José Jiménez-Luna
    Computational Science Laboratory , Parc de Recerca Biomèdica de Barcelona , Universitat Pompeu Fabra , C Dr Aiguader 88 , Barcelona , 08003 , Spain . Email: gianni.defabritiis@upf.edu.
  • Michael Gastegger
    Institute of Theoretical Chemistry, University of Vienna , Währinger Str. 17, 1090 Vienna, Austria.
  • Yu Xie
    Department of Sociology, Princeton University, Princeton, New Jersey, USA.
  • Andrew Y K Foong
    AI for Science, Microsoft Research.
  • Victor García Satorras
    AI for Science, Microsoft Research.
  • Osama Abdin
    Department of Molecular Genetics, University of Toronto, Toronto, Ontario, Canada.
  • Bastiaan S Veeling
    Machine Learning lab, University of Amsterdam, 1090 GH Amsterdam and, Philips Research, Eindhoven, 5656 AE, The Netherlands.
  • Iryna Zaporozhets
    AI for Science, Microsoft Research.
  • Yaoyi Chen
    Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany. Electronic address: https://twitter.com/hello_yaoyi.
  • Soojung Yang
    AITRICS, Hyoryoung-ro 77-gil, Seocho-gu, Seoul, Republic of Korea.
  • Adam E Foster
    AI for Science, Microsoft Research.
  • Arne Schneuing
    École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland; Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland.
  • Jigyasa Nigam
    Laboratory of Computational Science and Modeling, IMX, École Polytechnique Fédérale de Lausanne 1015 Lausanne Switzerland michele.ceriotti@epfl.ch.
  • Federico Barbero
    AI for Science, Microsoft Research.
  • Vincent Stimper
    AI for Science, Microsoft Research.
  • Andrew Campbell
    Cancer Research UK Beatson Institute, Garscube Estate, Switchback Road, Glasgow G61 1BD, U.K.
  • Jason Yim
    DeepMind, London, UK.
  • Marten Lienen
    AI for Science, Microsoft Research.
  • Yu Shi
    NIH BD2K Program Centers of Excellence for Big Data Computing-KnowEng Center, Department of Computer Science, University of Illinois at Urbana-Champaign , Champaign, Illinois.
  • Shuxin Zheng
    School of Economics and Business, Changzhou Vocational Institute of Textile and Garment, Changzhou, China.
  • Hannes Schulz
    Autonomous Intelligent Systems, Computer Science Institute VI, University of Bonn, Germany. Electronic address: schulz@ais.uni-bonn.de.
  • Usman Munir
    Microsoft Health Futures, Microsoft Research, Cambridge, United Kingdom.
  • Roberto Sordillo
    AI for Science, Microsoft Research.
  • Ryota Tomioka
    AI for Science, Microsoft Research.
  • Cecilia Clementi
    Center for Theoretical Biological Physics, and Department of Chemistry, Rice University, 6100 Main Street, Houston, TX 77005, United States. Electronic address: cecilia@rice.edu.
  • Frank Noé
    Department of Mathematics and Computer Science , Freie Universität Berlin , Berlin , Germany.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals