Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Artificial intelligence models have shown great potential in structure-based drug design, generating ligands with high binding affinities. However, existing models have often overlooked a crucial physical constraint: atoms must maintain a minimum pairwise distance to avoid separation violation, a phenomenon governed by the balance of attractive and repulsive forces. To mitigate such separation violations, we propose NucleusDiff. It models the interactions between atomic nuclei and their surrounding electron clouds by enforcing the distance constraint between the nuclei and manifolds. We quantitatively evaluate NucleusDiff using the CrossDocked2020 dataset and a COVID-19 therapeutic target, demonstrating that NucleusDiff reduces violation rate by up to 100.00% and enhances binding affinity by up to 22.16%, surpassing state-of-the-art models for structure-based drug design. We also provide qualitative analysis through manifold sampling, visually confirming the effectiveness of NucleusDiff in reducing separation violations and improving binding affinities.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 20 of its 42 references that are in the map. First posted on arXiv 16 Sep 2024.
Builds on
20 of 42 references.
References · 20
- 2017Attention Is All You Needcited by 60,361
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
- 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
- 2022A 3D Generative Model for Structure-Based Drug Designcited by 149
- 2022Generating 3D Molecules for Target Protein Bindingcited by 104
- 2021Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Modelscited by 73
- 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 68
8 more
- 2021Learning to design drug-like molecules in three-dimensional space using deep generative modelscited by 37
- 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretrainingcited by 32
- 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materialscited by 22
- 2022Target-aware Molecular Graph Generationcited by 18
- 2023Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusioncited by 10
- 2023Learning Harmonic Molecular Representations on Riemannian Manifoldcited by 8
- 2023AtomSurf : Surface Representation for Learning on Protein Structurescited by 5
- 2023GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flowcited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
- 2024AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design
- 2024Diffusion Models in textitDe Novo Drug Design
- 2025BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation
- 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
- 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
- 2022DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations
- 2022Structure-based Drug Design with Equivariant Diffusion Models