IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v15y2024i1d10.1038_s41467-024-51801-z.html
   My bibliography  Save this article

AlphaFold predictions of fold-switched conformations are driven by structure memorization

Author

Listed:
  • Devlina Chakravarty

    (National Institutes of Health)

  • Joseph W. Schafer

    (National Institutes of Health)

  • Ethan A. Chen

    (National Institutes of Health)

  • Joseph F. Thole

    (National Institutes of Health
    National Institutes of Health)

  • Leslie A. Ronish

    (National Institutes of Health
    National Institutes of Health)

  • Myeongsang Lee

    (National Institutes of Health)

  • Lauren L. Porter

    (National Institutes of Health
    National Institutes of Health)

Abstract

Recent work suggests that AlphaFold (AF)–a deep learning-based model that can accurately infer protein structure from sequence–may discern important features of folded protein energy landscapes, defined by the diversity and frequency of different conformations in the folded state. Here, we test the limits of its predictive power on fold-switching proteins, which assume two structures with regions of distinct secondary and/or tertiary structure. We find that (1) AF is a weak predictor of fold switching and (2) some of its successes result from memorization of training-set structures rather than learned protein energetics. Combining >280,000 models from several implementations of AF2 and AF3, a 35% success rate was achieved for fold switchers likely in AF’s training sets. AF2’s confidence metrics selected against models consistent with experimentally determined fold-switching structures and failed to discriminate between low and high energy conformations. Further, AF captured only one out of seven experimentally confirmed fold switchers outside of its training sets despite extensive sampling of an additional ~280,000 models. Several observations indicate that AF2 has memorized structural information during training, and AF3 misassigns coevolutionary restraints. These limitations constrain the scope of successful predictions, highlighting the need for physically based methods that readily predict multiple protein conformations.

Suggested Citation

  • Devlina Chakravarty & Joseph W. Schafer & Ethan A. Chen & Joseph F. Thole & Leslie A. Ronish & Myeongsang Lee & Lauren L. Porter, 2024. "AlphaFold predictions of fold-switched conformations are driven by structure memorization," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
  • Handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-51801-z
    DOI: 10.1038/s41467-024-51801-z
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-024-51801-z
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-024-51801-z?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Georgios A. Pavlopoulos & Fotis A. Baltoumas & Sirui Liu & Oguz Selvitopi & Antonio Pedro Camargo & Stephen Nayfach & Ariful Azad & Simon Roux & Lee Call & Natalia N. Ivanova & I. Min Chen & David Pae, 2023. "Unraveling the functional dark matter through global metagenomics," Nature, Nature, vol. 622(7983), pages 594-602, October.
    2. Philipp Konrad Zuber & Kristian Schweimer & Paul Rösch & Irina Artsimovitch & Stefan H. Knauer, 2019. "Reversible fold-switching controls the functional cycle of the antitermination factor RfaH," Nature Communications, Nature, vol. 10(1), pages 1-13, December.
    3. Patrick Bryant & Gabriele Pozzati & Arne Elofsson, 2022. "Author Correction: Improved prediction of protein-protein interactions using AlphaFold2," Nature Communications, Nature, vol. 13(1), pages 1-1, December.
    4. Yao Xia & Rongfeng Zou & Maxime Escouboué & Liang Zhong & Chengjun Zhu & Cécile Pouzet & Xueqiang Wu & Yongjin Wang & Guohua Lv & Haibo Zhou & Pinghua Sun & Ke Ding & Laurent Deslandes & Shuguang Yuan, 2021. "Secondary-structure switch regulates the substrate binding of a YopJ family acetyltransferase," Nature Communications, Nature, vol. 12(1), pages 1-10, December.
    5. Patrick Bryant & Gabriele Pozzati & Arne Elofsson, 2022. "Improved prediction of protein-protein interactions using AlphaFold2," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    6. Josh Abramson & Jonas Adler & Jack Dunger & Richard Evans & Tim Green & Alexander Pritzel & Olaf Ronneberger & Lindsay Willmore & Andrew J. Ballard & Joshua Bambrick & Sebastian W. Bodenstein & David , 2024. "Accurate structure prediction of biomolecular interactions with AlphaFold 3," Nature, Nature, vol. 630(8016), pages 493-500, June.
    7. Gabriel Monteiro da Silva & Jennifer Y. Cui & David C. Dalgarno & George P. Lisi & Brenda M. Rubenstein, 2024. "High-throughput prediction of protein conformational distributions with subsampled AlphaFold2," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    8. Joseph W. Schafer & Lauren L. Porter, 2023. "Evolutionary selection of proteins with two folds," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    9. Lauren L. Porter & Allen K. Kim & Swechha Rimal & Loren L. Looger & Ananya Majumdar & Brett D. Mensh & Mary R. Starich & Marie-Paule Strub, 2022. "Many dissimilar NusG protein domains switch between α-helix and β-sheet folds," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    10. John Jumper & Richard Evans & Alexander Pritzel & Tim Green & Michael Figurnov & Olaf Ronneberger & Kathryn Tunyasuvunakool & Russ Bates & Augustin Žídek & Anna Potapenko & Alex Bridgland & Clemens Me, 2021. "Highly accurate protein structure prediction with AlphaFold," Nature, Nature, vol. 596(7873), pages 583-589, August.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Joseph W. Schafer & Lauren L. Porter, 2023. "Evolutionary selection of proteins with two folds," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    2. Kazutoshi Tani & Ryo Kanno & Xuan-Cheng Ji & Itsusei Satoh & Yuki Kobayashi & Malgorzata Hall & Long-Jiang Yu & Yukihiro Kimura & Akira Mizoguchi & Bruno M. Humbel & Michael T. Madigan & Zheng-Yu Wang, 2023. "Rhodobacter capsulatus forms a compact crescent-shaped LH1–RC photocomplex," Nature Communications, Nature, vol. 14(1), pages 1-9, December.
    3. Patrick Bryant & Gabriele Pozzati & Wensi Zhu & Aditi Shenoy & Petras Kundrotas & Arne Elofsson, 2022. "Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    4. Brooke M. Britton & Remy A. Yovanno & Sara F. Costa & Joshua McCausland & Albert Y. Lau & Jie Xiao & Zach Hensel, 2023. "Conformational changes in the essential E. coli septal cell wall synthesis complex suggest an activation mechanism," Nature Communications, Nature, vol. 14(1), pages 1-15, December.
    5. Patrick Bryant & Frank Noé, 2024. "Structure prediction of alternative protein conformations," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    6. Christoph Buhlheller & Theo Sagmeister & Christoph Grininger & Nina Gubensäk & Uwe B. Sleytr & Isabel Usón & Tea Pavkov-Keller, 2024. "SymProFold: Structural prediction of symmetrical biological assemblies," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    7. Hélène Bret & Jinmei Gao & Diego Javier Zea & Jessica Andreani & Raphaël Guerois, 2024. "From interaction networks to interfaces, scanning intrinsically disordered regions using AlphaFold2," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    8. Zhiye Guo & Jian Liu & Jeffrey Skolnick & Jianlin Cheng, 2022. "Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
    9. Tânia F. Custódio & Maxime Killer & Dingquan Yu & Virginia Puente & Daniel P. Teufel & Alexander Pautsch & Gisela Schnapp & Marc Grundl & Jan Kosinski & Christian Löw, 2023. "Molecular basis of TASL recruitment by the peptide/histidine transporter 1, PHT1," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    10. Mindaugas Margelevičius, 2024. "GTalign: spatial index-driven protein structure alignment, superposition, and search," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    11. Lauren L. Porter & Allen K. Kim & Swechha Rimal & Loren L. Looger & Ananya Majumdar & Brett D. Mensh & Mary R. Starich & Marie-Paule Strub, 2022. "Many dissimilar NusG protein domains switch between α-helix and β-sheet folds," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    12. Qianqian Ming & Daniel Antfolk & David A. Price & Anna Manturova & Elliot Medina & Srishti Singh & Charlotte Mason & Timothy H. Tran & Keiran S. M. Smalley & Daisy W. Leung & Vincent C. Luca, 2024. "Structural basis for mouse LAG3 interactions with the MHC class II molecule I-Ab," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    13. Marin Matic & Pasquale Miglionico & Manae Tatsumi & Asuka Inoue & Francesco Raimondi, 2023. "GPCRome-wide analysis of G-protein-coupling diversity using a computational biology approach," Nature Communications, Nature, vol. 14(1), pages 1-17, December.
    14. Genki Hibi & Taro Shiraishi & Tatsuki Umemura & Kenji Nemoto & Yusuke Ogura & Makoto Nishiyama & Tomohisa Kuzuyama, 2023. "Discovery of type II polyketide synthase-like enzymes for the biosynthesis of cispentacin," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    15. Andreas Lackner & Michael Müller & Magdalena Gamperl & Delyana Stoeva & Olivia Langmann & Henrieta Papuchova & Elisabeth Roitinger & Gerhard Dürnberger & Richard Imre & Karl Mechtler & Paulina A. Lato, 2023. "The Fgf/Erf/NCoR1/2 repressive axis controls trophoblast cell fate," Nature Communications, Nature, vol. 14(1), pages 1-20, December.
    16. Huiyu Cai & Zuobai Zhang & Mingkai Wang & Bozitao Zhong & Quanxiao Li & Yuxuan Zhong & Yanling Wu & Tianlei Ying & Jian Tang, 2024. "Pretrainable geometric graph neural network for antibody affinity maturation," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    17. Qianqiao Liu & Beth M. Stadtmueller, 2023. "SIgA structures bound to Streptococcus pyogenes M4 and human CD89 provide insights into host-pathogen interactions," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    18. Yinghui Chen & Yunxin Xu & Di Liu & Yaoguang Xing & Haipeng Gong, 2024. "An end-to-end framework for the prediction of protein structure and fitness from single sequence," Nature Communications, Nature, vol. 15(1), pages 1-17, December.
    19. Philipp K. Zuber & Nelly Said & Tarek Hilal & Bing Wang & Bernhard Loll & Jorge González-Higueras & César A. Ramírez-Sarmiento & Georgiy A. Belogurov & Irina Artsimovitch & Markus C. Wahl & Stefan H., 2024. "Concerted transformation of a hyper-paused transcription complex and its reinforcing protein," Nature Communications, Nature, vol. 15(1), pages 1-19, December.
    20. Marius Klein & Klemens Wild & Irmgard Sinning, 2024. "Multi-protein assemblies orchestrate co-translational enzymatic processing on the human ribosome," Nature Communications, Nature, vol. 15(1), pages 1-11, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-51801-z. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.