Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 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

Binding-Adaptive Diffusion Models for Structure-Based Drug Design (2402.18583v1)

Published 15 Jan 2024 in q-bio.BM and cs.LG

Abstract: Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-Adaptive Diffusion Models (BindDM). In BindDM, we adaptively extract subcomplex, the essential part of binding sites responsible for protein-ligand interactions. Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information. We iterate this hierarchical complex-subcomplex process with cross-hierarchy interaction node for adequately fusing global binding context between the complex and its corresponding subcomplex. Empirical studies on the CrossDocked2020 dataset show BindDM can generate molecules with more realistic 3D structures and higher binding affinities towards the protein targets, with up to -5.92 Avg. Vina Score, while maintaining proper molecular properties. Our code is available at https://github.com/YangLing0818/BindDM

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Anderson, A. C. 2003. The process of structure-based drug design. Chemistry & biology, 10(9): 787–797.
  2. Geometric deep learning on molecular representations. Nature Machine Intelligence, 3(12): 1023–1032.
  3. Exploring protein hotspots by optimized fragment pharmacophores. Nature Communications, 12(1): 3201.
  4. An enumerative algorithm for de novo design of proteins with diverse pocket structures. Proceedings of the National Academy of Sciences, 117(36): 22135–22145.
  5. A structure-based drug discovery paradigm. International journal of molecular sciences, 20(11): 2783.
  6. Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges. arXiv:2104.13478.
  7. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv:1412.3555.
  8. MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design. arXiv:2203.14500.
  9. AutoDock Vina 1.2. 0: New docking methods, expanded force field, and python bindings. Journal of Chemical Information and Modeling, 61(8): 3891–3898.
  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.
  11. Utilizing graph machine learning within drug discovery and development. Briefings in bioinformatics, 22(6): bbab159.
  12. 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction. In International Conference on Learning Representations.
  13. DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design. In Krause, A.; Brunskill, E.; Cho, K.; Engelhardt, B.; Sabato, S.; and Scarlett, J., eds., Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, 11827–11846. PMLR.
  14. Hawkins, P. C. 2017. Conformation generation: the state of the art. Journal of Chemical Information and Modeling, 57(8): 1747–1756.
  15. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33: 6840–6851.
  16. Equivariant diffusion for molecule generation in 3d. In International conference on machine learning, 8867–8887. PMLR.
  17. A machine learning-based method to improve docking scoring functions and its application to drug repurposing. Journal of chemical information and modeling, 51(2): 408–419.
  18. Ligand deconstruction: Why some fragment binding positions are conserved and others are not. Proceedings of the National Academy of Sciences, 112(20): E2585–E2594.
  19. Structure-based de novo drug design using 3D deep generative models. Chemical science, 12(41): 13664–13675.
  20. DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding. arXiv:2211.11214.
  21. Generating 3D Molecules for Target Protein Binding. In International Conference on Machine Learning.
  22. Generating 3D Molecules for Target Protein Binding. arXiv:2204.09410.
  23. A 3D generative model for structure-based drug design. Advances in Neural Information Processing Systems, 34: 6229–6239.
  24. An autoregressive flow model for 3d molecular geometry generation from scratch. In International Conference on Learning Representations.
  25. Pocket2mol: Efficient molecular sampling based on 3d protein pockets. In International Conference on Machine Learning, 17644–17655. PMLR.
  26. Fragment-based ligand generation guided by geometric deep learning on protein-ligand structure. bioRxiv, 2022–03.
  27. Generating 3D molecules conditional on receptor binding sites with deep generative models. Chem Sci, 13: 2701–2713.
  28. Generating 3D molecules conditional on receptor binding sites with deep generative models. Chemical science, 13(9): 2701–2713.
  29. E (n) equivariant graph neural networks. In International conference on machine learning, 9323–9332. PMLR.
  30. “Scaffold-hopping” by topological pharmacophore search: a contribution to virtual screening. Angewandte Chemie International Edition, 38(19): 2894–2896.
  31. Structure-based Drug Design with Equivariant Diffusion Models. arXiv:2210.13695.
  32. Shape-based generative modeling for de novo drug design. Journal of chemical information and modeling, 59(3): 1205–1214.
  33. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning, 2256–2265. PMLR.
  34. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems, 32.
  35. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations.
  36. Surface-based protein binding pocket similarity. Proteins: Structure, Function, and Bioinformatics, 79(9): 2746–2763.
  37. Target-aware molecular graph generation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 410–427. Springer.
  38. De novo molecule design through the molecular generative model conditioned by 3D information of protein binding sites. Journal of Chemical Information and Modeling, 61(7): 3240–3254.
  39. Omni-granular ego-semantic propagation for self-supervised graph representation learning. In International Conference on Machine Learning, 25022–25037. PMLR.
  40. Diffusion-based scene graph to image generation with masked contrastive pre-training. arXiv preprint arXiv:2211.11138.
  41. Dpgn: Distribution propagation graph network for few-shot learning. In IEEE Conference on Computer Vision and Pattern Recognition, 13390–13399.
  42. Improving Diffusion-Based Image Synthesis with Context Prediction. In Thirty-seventh Conference on Neural Information Processing Systems.
  43. VQGraph: Graph Vector-Quantization for Bridging GNNs and MLPs. arXiv preprint arXiv:2308.02117.
  44. Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys, 56(4): 1–39.
  45. Knowledge Guided Geometric Editing for Unsupervised Drug Design.
  46. Learning Subpocket Prototypes for Generalizable Structure-based Drug Design. In International Conference on Machine Learning.
  47. Molecule generation for target protein binding with structural motifs. In The Eleventh International Conference on Learning Representations.
  48. A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design. arXiv:2306.11768.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Zhilin Huang (9 papers)
  2. Ling Yang (88 papers)
  3. Zaixi Zhang (34 papers)
  4. Xiangxin Zhou (22 papers)
  5. Yu Bao (36 papers)
  6. Xiawu Zheng (63 papers)
  7. Yuwei Yang (11 papers)
  8. Yu Wang (939 papers)
  9. Wenming Yang (71 papers)
Citations (6)
View on Semantic Scholar

Summary

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

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