Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design (2403.07902v1)

Published 26 Feb 2024 in q-bio.BM and cs.LG

Abstract: Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design and can be less efficient for exploring the large drug-like molecule space. In this paper, inspired by the convention in pharmaceutical practice, we decompose the ligand molecule into two parts, namely arms and scaffold, and propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. In order to facilitate the decomposed generation and improve the properties of the generated molecules, we incorporate both bond diffusion in the model and additional validity guidance in the sampling phase. Extensive experiments on CrossDocked2020 show that our approach achieves state-of-the-art performance in generating high-affinity molecules while maintaining proper molecular properties and conformational stability, with up to -8.39 Avg. Vina Dock score and 24.5 Success Rate. The code is provided at https://github.com/bytedance/DecompDiff

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Equivariant shape-conditioned generation of 3d molecules for ligand-based drug design. arXiv preprint arXiv:2210.04893, 2022.
  2. Anderson, A. C. The process of structure-based drug design. Chemistry & biology, 10(9):787–797, 2003.
  3. Smiles-based deep generative scaffold decorator for de-novo drug design. Journal of cheminformatics, 12(1):1–18, 2020.
  4. The protein data bank. Nucleic acids research, 28(1):235–242, 2000.
  5. Quantifying the chemical beauty of drugs. Nature chemistry, 4(2):90–98, 2012.
  6. On the art of compiling and using’drug-like’chemical fragment spaces. ChemMedChem: Chemistry Enabling Drug Discovery, 3(10):1503–1507, 2008.
  7. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34:8780–8794, 2021.
  8. Autodock vina 1.2. 0: New docking methods, expanded force field, and python bindings. Journal of Chemical Information and Modeling, 61(8):3891–3898, 2021.
  9. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. Journal of cheminformatics, 1(1):1–11, 2009.
  10. Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design. Journal of Chemical Information and Modeling, 60(9):4200–4215, 2020.
  11. Se (3)-transformers: 3d roto-translation equivariant attention networks. Advances in Neural Information Processing Systems, 33:1970–1981, 2020.
  12. Independent se (3)-equivariant models for end-to-end rigid protein docking. arXiv preprint arXiv:2111.07786, 2021.
  13. Directional message passing for molecular graphs. arXiv preprint arXiv:2003.03123, 2020.
  14. Energy-inspired molecular conformation optimization. In International Conference on Learning Representations, 2022.
  15. 3d equivariant diffusion for target-aware molecule generation and affinity prediction. arXiv preprint arXiv:2303.03543, 2023.
  16. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022.
  17. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  18. Argmax flows and multinomial diffusion: Learning categorical distributions. Advances in Neural Information Processing Systems, 34:12454–12465, 2021.
  19. Equivariant diffusion for molecule generation in 3d. In International Conference on Machine Learning, pp.  8867–8887. PMLR, 2022.
  20. 3dlinker: An e (3) equivariant variational autoencoder for molecular linker design. arXiv preprint arXiv:2205.07309, 2022.
  21. Equivariant 3d-conditional diffusion models for molecular linker design. arXiv preprint arXiv:2210.05274, 2022.
  22. Deep generative models for 3d linker design. Journal of chemical information and modeling, 60(4):1983–1995, 2020.
  23. Deep generative design with 3d pharmacophoric constraints. Chemical science, 12(43):14577–14589, 2021.
  24. Multi-objective molecule generation using interpretable substructures. In International conference on machine learning, pp.  4849–4859. PMLR, 2020.
  25. Alphaspace 2.0: Representing concave biomolecular surfaces using β𝛽\betaitalic_β-clusters. Journal of chemical information and modeling, 60(3):1494–1508, 2020.
  26. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  27. Diffwave: A versatile diffusion model for audio synthesis. In International Conference on Learning Representations, 2021.
  28. Priorgrad: Improving conditional denoising diffusion models with data-driven adaptive prior. arXiv preprint arXiv:2106.06406, 2021.
  29. Diffusion-lm improves controllable text generation. arXiv preprint arXiv:2205.14217, 2022.
  30. Deepscaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning. Journal of chemical information and modeling, 60(1):77–91, 2019.
  31. Structure-based de novo drug design using 3d deep generative models. Chemical science, 12(41):13664–13675, 2021.
  32. Scaffold-based molecular design with a graph generative model. Chemical science, 11(4):1153–1164, 2020.
  33. Diffbp: Generative diffusion of 3d molecules for target protein binding. arXiv preprint arXiv:2211.11214, 2022.
  34. Generating 3d molecules for target protein binding. arXiv preprint arXiv:2204.09410, 2022a.
  35. Generating 3d molecules for target protein binding. In International Conference on Machine Learning, 2022b.
  36. Zero-shot 3d drug design by sketching and generating. arXiv preprint arXiv:2209.13865, 2022.
  37. A 3d generative model for structure-based drug design. Advances in Neural Information Processing Systems, 34:6229–6239, 2021.
  38. An autoregressive flow model for 3d molecular geometry generation from scratch. In International Conference on Learning Representations, 2021.
  39. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741, 2021.
  40. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning, pp.  8162–8171. PMLR, 2021.
  41. Open babel: An open chemical toolbox. Journal of cheminformatics, 3(1):1–14, 2011.
  42. Pocket2mol: Efficient molecular sampling based on 3d protein pockets. arXiv preprint arXiv:2205.07249, 2022.
  43. Generating 3D molecules conditional on receptor binding sites with deep generative models. Chem Sci, 13:2701–2713, Feb 2022a. doi: 10.1039/D1SC05976A.
  44. Generating 3d molecules conditional on receptor binding sites with deep generative models. Chemical science, 13(9):2701–2713, 2022b.
  45. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  46. Alphaspace: fragment-centric topographical mapping to target protein–protein interaction interfaces. Journal of chemical information and modeling, 55(8):1585–1599, 2015.
  47. E (n) equivariant graph neural networks. In International Conference on Machine Learning. PMLR, 2021.
  48. “scaffold-hopping” by topological pharmacophore search: a contribution to virtual screening. Angewandte Chemie International Edition, 38(19):2894–2896, 1999.
  49. Structure-based drug design with equivariant diffusion models. arXiv preprint arXiv:2210.13695, 2022.
  50. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning, pp.  2256–2265. PMLR, 2015.
  51. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems, 32, 2019.
  52. Fast end-to-end learning on protein surfaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  15272–15281, 2021.
  53. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  54. Drugcentral: online drug compendium. Nucleic acids research, pp.  gkw993, 2016.
  55. Digress: Discrete denoising diffusion for graph generation. arXiv preprint arXiv:2209.14734, 2022.
  56. Stochastic voyages into uncharted chemical space produce a representative library of all possible drug-like compounds. Journal of the American Chemical Society, 135(19):7296–7303, 2013.
  57. Wermuth, C. G. The practice of medicinal chemistry. Academic Press, 2011.
  58. Mars: Markov molecular sampling for multi-objective drug discovery. arXiv preprint arXiv:2103.10432, 2021.
  59. Geodiff: A geometric diffusion model for molecular conformation generation. arXiv preprint arXiv:2203.02923, 2022.
  60. Analyzing learned molecular representations for property prediction. Journal of chemical information and modeling, 59(8):3370–3388, 2019.
  61. Syntalinker: automatic fragment linking with deep conditional transformer neural networks. Chemical science, 11(31):8312–8322, 2020.
  62. Knowledge guided geometric editing for unsupervised drug design. 2021. URL https://openreview.net/forum?id=91muTwt1_t5.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Jiaqi Guan (24 papers)
  2. Xiangxin Zhou (22 papers)
  3. Yuwei Yang (11 papers)
  4. Yu Bao (36 papers)
  5. Jian Peng (101 papers)
  6. Jianzhu Ma (48 papers)
  7. Qiang Liu (405 papers)
  8. Liang Wang (512 papers)
  9. Quanquan Gu (198 papers)
Citations (43)
View on Semantic Scholar

Summary

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

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

Tweets