mlsanityData to 14 Oct 2026

Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models

arXiv 2308.11890 ↗First posted 23 Aug 2023cs.LG q-bio.BMcited by 8

Not on the map. Why?

Abstract (arXiv)

Ligand-based drug design aims to identify novel drug candidates of similar shapes with known active molecules. In this paper, we formulated an in silico shape-conditioned molecule generation problem to generate 3D molecule structures conditioned on the shape of a given molecule. To address this problem, we developed a translation- and rotation-equivariant shape-guided generative model ShapeMol. ShapeMol consists of an equivariant shape encoder that maps molecular surface shapes into latent embeddings, and an equivariant diffusion model that generates 3D molecules based on these embeddings. Experimental results show that ShapeMol can generate novel, diverse, drug-like molecules that retain 3D molecular shapes similar to the given shape condition. These results demonstrate the potential of ShapeMol in designing drug candidates of desired 3D shapes binding to protein target pockets.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 23 Aug 2023.

Builds on

23 of 35 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  7. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  8. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  9. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  10. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  11. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  12. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
11 more
  1. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  2. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 275
  3. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  4. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  5. 2021E(n) Equivariant Normalizing Flowscited by 165
  6. 2022A 3D Generative Model for Structure-Based Drug Designcited by 149
  7. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  8. 2020A Deep Generative Model for Molecule Optimization via One Fragment Modificationcited by 37
  9. 2022Zero-Shot 3D Drug Design by Sketching and Generatingcited by 24
  10. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  11. 20223D Equivariant Graph Implicit Functionscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 3.

8 papers.

  1. 2024Diffusion Models in textitDe Novo Drug Designcited by 26
  2. 2025Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidancecited by 10
  3. 2025Unified Guidance for Geometry-Conditioned Molecular Generationcited by 9
  4. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generationcited by 3
  5. 2024nach0-pc: Multi-task Language Model with Molecular Point Cloud Encodercited by 2
  6. 2026Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectracited by 0
  7. 2026Ensemble-Conditioned Molecular Designcited by 0
  8. 2026OctMole: Multiscale 3D Molecular Generation with Hierarchical Spatial Flowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
  2. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
  3. 2025Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models
  4. 2024Physics-informed generative model for drug-like molecule conformers
  5. 2024ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design
  6. 2024BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
  7. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
  8. 2022Structure-based Drug Design with Equivariant Diffusion Models