Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DockGame: Cooperative Games for Multimeric Rigid Protein Docking (2310.06177v1)

Published 9 Oct 2023 in cs.LG

Abstract: Protein interactions and assembly formation are fundamental to most biological processes. Predicting the assembly structure from constituent proteins -- referred to as the protein docking task -- is thus a crucial step in protein design applications. Most traditional and deep learning methods for docking have focused mainly on binary docking, following either a search-based, regression-based, or generative modeling paradigm. In this paper, we focus on the less-studied multimeric (i.e., two or more proteins) docking problem. We introduce DockGame, a novel game-theoretic framework for docking -- we view protein docking as a cooperative game between proteins, where the final assembly structure(s) constitute stable equilibria w.r.t. the underlying game potential. Since we do not have access to the true potential, we consider two approaches - i) learning a surrogate game potential guided by physics-based energy functions and computing equilibria by simultaneous gradient updates, and ii) sampling from the Gibbs distribution of the true potential by learning a diffusion generative model over the action spaces (rotations and translations) of all proteins. Empirically, on the Docking Benchmark 5.5 (DB5.5) dataset, DockGame has much faster runtimes than traditional docking methods, can generate multiple plausible assembly structures, and achieves comparable performance to existing binary docking baselines, despite solving the harder task of coordinating multiple protein chains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. The mechanics of n-player differentiable games. In International Conference on Machine Learning, pp. 354–363, 2018.
  2. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324–345, 1952.
  3. Predicting the structure of large protein complexes using alphafold and monte carlo tree search. Nature communications, 13(1):6028, 2022.
  4. Pyrosetta: a script-based interface for implementing molecular modeling algorithms using rosetta. Bioinformatics, 26(5):689–691, 2010.
  5. Zdock: an initial-stage protein-docking algorithm. Proteins: Structure, Function, and Bioinformatics, 52(1):80–87, 2003.
  6. Large-scale multi-agent deep fbsdes. In International Conference on Machine Learning, pp. 1740–1748. PMLR, 2021.
  7. Diffdock: Diffusion steps, twists, and turns for molecular docking. International Conference on Learning Representations (ICLR), 2023.
  8. Riemannian score-based generative modelling. Advances in Neural Information Processing Systems, 35:2406–2422, 2022.
  9. A web interface for easy flexible protein-protein docking with attract. Biophysical journal, 108(3):462–465, 2015.
  10. Multi-lzerd: multiple protein docking for asymmetric complexes. Proteins: Structure, Function, and Bioinformatics, 80(7):1818–1833, 2012.
  11. Protein complex prediction with alphafold-multimer. biorxiv, pp.  2021–10, 2021.
  12. Independent SE(3)-equivariant models for end-to-end rigid protein docking. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=GQjaI9mLet.
  13. e3nn: Euclidean neural networks. arXiv preprint arXiv:2207.09453, 2022.
  14. Path integral stochastic optimal control for sampling transition paths. arXiv preprint arXiv:2207.02149, 2022.
  15. Syndock: N rigid protein docking via learnable group synchronization, 2023.
  16. Unsupervised protein-ligand binding energy prediction via neural euler’s rotation equation. arXiv preprint arXiv:2301.10814, 2023.
  17. Torsional diffusion for molecular conformer generation. Advances in Neural Information Processing Systems, 35:24240–24253, 2022.
  18. Eigenfold: Generative protein structure prediction with diffusion models. arXiv preprint arXiv:2304.02198, 2023.
  19. Diffdock-pp: Rigid protein-protein docking with diffusion models. arXiv preprint arXiv:2304.03889, 2023.
  20. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  21. The cluspro web server for protein–protein docking. Nature protocols, 12(2):255–278, 2017.
  22. Denoising diffusion probabilistic models on so (3) for rotational alignment. In ICLR 2022 Workshop on Geometrical and Topological Representation Learning, 2022.
  23. Deep generalized schrödinger bridge. Advances in Neural Information Processing Systems, 35:9374–9388, 2022.
  24. An integrated suite of fast docking algorithms. Proteins: Structure, Function, and Bioinformatics, 78(15):3197–3204, 2010.
  25. Potential games. Games and economic behavior, 14(1):124–143, 1996.
  26. Normal distribution on the rotation group so (3). Texture, Stress, and Microstructure, 29:201–233, 1997.
  27. Dynamic-backbone protein-ligand structure prediction with multiscale generative diffusion models. arXiv preprint arXiv:2209.15171, 2022.
  28. Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290, 2023.
  29. Functional maps representation on product manifolds. In Computer Graphics Forum, volume 38, pp.  678–689. Wiley Online Library, 2019.
  30. Aligned diffusion Schrödinger bridges. In Robin J. Evans and Ilya Shpitser (eds.), Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, volume 216 of Proceedings of Machine Learning Research, pp.  1985–1995. PMLR, 31 Jul–04 Aug 2023.
  31. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
  32. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
  33. End-to-end learning on 3d protein structure for interface prediction. Advances in Neural Information Processing Systems, 32, 2019.
  34. Updates to the integrated protein–protein interaction benchmarks: docking benchmark version 5 and affinity benchmark version 2. Journal of molecular biology, 427(19):3031–3041, 2015.
  35. Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models. BioRxiv, pp.  2022–12, 2022.
  36. Geodiff: A geometric diffusion model for molecular conformation generation. arXiv preprint arXiv:2203.02923, 2022.
  37. The hdock server for integrated protein–protein docking. Nature protocols, 15(5):1829–1852, 2020.
  38. Se (3) diffusion model with application to protein backbone generation. arXiv preprint arXiv:2302.02277, 2023.
  39. Tm-align: a protein structure alignment algorithm based on the tm-score. Nucleic acids research, 33(7):2302–2309, 2005.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - vsomnath/dockgame: DockGame: Cooperative Games for Multimeric Rigid Protein Docking (11 stars)