CoChat

Deep Learning for Flexible and Site-Specific Protein Docking and Design

Open access
McPartlon, Matt, Xu, Jinbo · 2023 · bioRxiv (Cold Spring Harbor Laboratory)
PreprintCited by 20

The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.

Abstract

Protein complexes are vital to many biological processes and their understanding can lead to the development of new drugs and therapies. Although the structure of individual protein chains can now be predicted with high accuracy, determining the three-dimensional structure of a complex remains a challenge. Protein docking, the task of computationally determining the structure of a protein complex given the unbound structures of its components (and optionally binding site information), provides a way to predict protein complex structure. Traditional docking methods rely on empirical scoring functions and rigid body simulations to predict the binding poses of two or more proteins. However, they often make unrealistic assumptions about input structures, and are not effective at accommodating conformational flexibility or binding site information. In this work, we present DockGPT (Generative Protein Transformer for Docking), an end-to-end deep learning method for flexible and site-specific protein docking that allows conformational flexibility and can effectively make use of binding site information. Tested on multiple benchmarks with unbound and predicted monomer structures as input, we significantly outperform existing methods in both accuracy and running time. Our performance is especially pronounced for antibody-antigen complexes, where we predict binding poses with high accuracy even in the absence of binding site information. Finally, we highlight our method’s generality by extending it to simultaneously dock and co-design the sequence and structure of antibody complementarity determining regions targeting a specified epitope.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2023.04.01.535079

Cites

25 of 25 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 60

  1. Michael J Lee and Michael B Yaffe . “Protein regulation in signal transduction”. en. In: Cold Spring Harb. Perspect. Biol. 8.6 (June 2016). · DOI · Paper page
  2. 2001, Scaffolding proteins organize multimolecular protein complexes for sensory signal transduction, en. In: Eur. J. Neurosci, 14, 769
  3. 1995, The synaptic vesicle cycle: a cascade of protein–protein interactions, In: Nature, 375, 645
  4. 2022, Membrane-mediated protein interactions drive membrane protein organization, In: Nature Communications, 13, 7373
  5. 2008, The integrated analysis of metabolic and protein interaction networks reveals novel molecular organizing principles, en. In: BMC Syst. Biol, 2, 100
  6. 2021, Global mapping of protein–metabolite interactions in Saccharomyces cerevisiae reveals that Ser-Leu dipeptide regulates phosphoglycerate kinase activity, In: Communications Biology, 4, 181
  7. 2021, Molecular basis for protein-protein interactions, en. In: Beilstein J. Org. Chem, 17, 1
  8. Laura Bettinetti , Matteo Magnani , and Alessandro Padova . “Drug Discovery by Targeting Protein– Protein Interactions”. In: Disruption of Protein-Protein Interfaces: In Search of New Inhibitors. Ed. by Stefano Mangani. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 1–29. · DOI
  9. 2018, PPI network analyses of human WD40 protein family systematically reveal their tendency to assemble complexes and facilitate the complex predictions, In: BMC Systems Biology, 12, 41
  10. 2010, Monoclonal antibodies: versatile platforms for cancer immunotherapy, In: Nat Rev Immunol, 10, 317
  11. 2019, Determination of ProteinâProtein Interactions in a Mixture of Two Monoclonal Antibodies, In: Molecular Pharmaceutics, 16, 4775
  12. Stefano Mangani . “Protein–Protein Interactions in the Solid State: The Troubles of Crystallizing Protein–Protein Complexes”. In: ed. by Stefano Mangani. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 113–134. · DOI
  13. 2002, Crystallization of protein–protein complexes, In: Journal of Applied Crystallography, 35, 674
  14. 2000, The Protein Data Bank, en. In: Nucleic Acids Res, 28, 235
  15. 2018, Structural prediction of protein models using distance restraints derived from cross-linking mass spectrometry data, In: Nature Protocols, 13, 478
  16. 2018, Protein-protein docking in drug design and discovery, en. In: Methods Mol. Biol, 1762, 285
  17. 2017, Recent advances and applications of molecular docking to G protein-coupled receptors, en. In: Molecules, 22, 340
  18. 2021, A practical guide to largescale docking, In: Nature Protocols, 16, 4799
  19. Pedro H. M. Torres , Ana C. R. Sodero , Paula Jofily , and Floriano P. Silva-Jr . “Key Topics in Molecular Docking for Drug Design”. In: International Journal of Molecular Sciences 20.18 (2019). · DOI · Paper page
  20. Juliette Martin , Leslie Regad , Helene Lecornet , and Anne-Claude Camproux . “Structural deformation upon protein-protein interaction: A structural alphabet approach”. en. In: Bmc 8.12 (2008). · DOI
  21. 2005, Structural changes involved in protein binding correlate with intrinsic motions of proteins in the unbound state, In: Proceedings of the National Academy of Sciences, 102, 18908
  22. 2009, Binding of Small-Molecule Ligands to Proteins: âWhat You Seeâ Is Not Always âWhat You Getâ, In: Structure, 17, 489
  23. 2009, Backbone flexibility in computational protein design, en. In: Curr. Opin. Biotechnol, 20, 420
  24. 2022, Linking protein structural and functional change to mutation using amino acid networks, In: Plos One, 17, 1
  25. 2003, Protein side-chain rearrangement in regions of point mutations, en. In: Proteins, 50, 272
  26. 2021, Targeting protein-protein interaction interfaces in COVID-19 drug discovery, In: Computational and Structural Biotechnology Journal, 19, 2246
  27. 2021, Neutralizing antibodies for the prevention and treatment of COVID-19, In: Cellular & Molecular Immunology, 18, 2293
  28. Octavian-Eugen Ganea , Xinyuan Huang , Charlotte Bunne , Yatao Bian , Regina Barzilay , et al. “Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking”. In: International Conference on Learning Representations. 2022.
  29. 2020, Macromolecular modeling and design in Rosetta: recent methods and frameworks, In: Nature Methods, 17, 665
  30. 2021, An expanded benchmark for antibody-antigen docking and affinity prediction reveals insights into antibody recognition determinants, en. In: Structure, 29, 606
  31. Fabian B. Fuchs , Daniel E. Worrall , Volker Fischer , and Max Welling . “SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks”. In: CoRR abs/2006.10503 (2020). · arXiv
  32. Victor Garcia Satorras , Emiel Hoogeboom , and Max Welling . “E(n) Equivariant Graph Neural Networks”. In: CoRR abs/2102.09844 (2021). · arXiv
  33. Chloe Hsu , Robert Verkuil , Jason Liu , Zeming Lin , Brian Hie , et al. “Learning inverse folding from millions of predicted structures”. In: bioRxiv (2022). · DOI · Paper page
  34. Matt McPartlon , Ben Lai , and Jinbo Xu . “A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding”. In: bioRxiv (2022). · DOI · Paper page
  35. Jue Wang , Sidney Lisanza , David Juergens , Doug Tischer , Ivan Anishchenko , et al. “Deep learning methods for designing proteins scaffolding functional sites”. In: bioRxiv (2021). · DOI · Paper page
  36. Wengong Jin , Jeremy Wohlwend , Regina Barzilay , and Tommi S. Jaakkola . “Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design”. In: International Conference on Learning Representations. 2022.
  37. Boqiao Lai , Matt McPartlon , and Jinbo Xu . “End- to-End deep structure generative model for protein design”. In: bioRxiv (2022).
  38. 2017, HDOCK: a web server for protein-protein and protein-DNA/RNA docking based on a hybrid strategy, en. In: Nucleic Acids Res, 45, W365
  39. 2020, The HDOCK server for integrated protein–protein docking, In: Nature Protocols, 15, 1829
  40. 2014, ZDOCK server: interactive docking prediction of protein-protein complexes and symmetric multimers, en. In: Bioinformatics, 30, 1771
  41. 2015, A web interface for easy flexible protein-protein docking with ATTRACT, en. In: Biophys. J, 108, 462
  42. 2017, The ClusPro web server for protein-protein docking, In: Nature Protocols, 12, 255
  43. 2008, The Rosetta-Dock server for local protein-protein docking, en. In: Nucleic Acids Res, 36, W233–8
  44. Computation Resources for Molecular Biology, 2016, The HADDOCK2.2 Web Server: User-Friendly Inte-grative Modeling of Biomolecular Complexes, In: Journal of Molecular Biology, 428, 720
  45. 2019, Benchmarking of different molecular docking methods for protein-peptide docking, In: BMC Bioinformatics, 19, 426
  46. 2016, Comprehensive evaluation of ten docking programs on a diverse set of proteinâligand complexes: the prediction accuracy of sampling power and scoring power, In: Phys. Chem. Chem. Phys, 18, 12964
  47. 2017, Software for molecular docking: a review, en. In: Biophys. Rev, 9, 91
  48. Isabella Guedes et al. “New machine learning and physics-based scoring functions for drug discovery”. In: Nature Scientific Reports 11 (2021). · DOI · Paper page
  49. 2015, Machine-learning scoring functions for identifying native poses of ligands docked to known and novel proteins, en. In: BMC Bioinformatics, 16, S3
  50. 2021, GNINA 1.0: molecular docking with deep learning, en. In: J. Chemin-form, 13, 43
  51. Matt McPartlon , Ben Lai, and Jinbo Xu . “A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding”. In: bioRxiv (2022). · DOI · Paper page
  52. 1989, Conformations of immunoglobulin hypervariable regions, In: Nature, 342, 877
  53. 1997, Standard conformations for the canonical structures of immunoglobulins, en. In: J. Mol. Biol, 273, 927
  54. 2016, MMseqs software suite for fast and deep clustering and searching of large protein sequence sets, en. In: Bioinformatics, 32, 1323
  55. 1976, A solution for the best rotation to relate two sets of vectors, In: Acta Crystallographica Section A, 32, 922
  56. 2018, RosettaAntibodyDesign (RAbD): A general framework for computational antibody design, en. In: PLoS Comput. Biol, 14, e1006112
  57. Ruibin Xiong et al. “On Layer Normalization in the Transformer Architecture”. In: CoRR abs/2002.04745 (2020). · arXiv
  58. Thomas Bachlechner , Bodhisattwa Prasad Majumder , Huanru Henry Mao , Garrison W. Cottrell , and Julian J. McAuley . “ReZero is All You Need: Fast Convergence at Large Depth”. In: CoRR abs/2003.04887 (2020). · arXiv
  59. Dan Hendrycks and Kevin Gimpel . “Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units”. In: CoRR abs/1606.08415 (2016). · arXiv
  60. 2022, ColabFold: making protein folding accessible to all, en. In: Nat. Methods, 19, 679

Cited by

See all 20

Metadata

Authors
McPartlon, M., & Xu, J.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2023-04-02
OpenAlex
W4362510910
Cited by
20
References
25
Type
posted content
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.