mlsanityData to 7 Oct 2026

Inverse design of 3d molecular structures with conditional generative neural networks

arXiv 2109.04824 ↗First posted 10 Sep 2021cs.LG physics.chem-ph physics.comp-phcited by 93

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a conditional generative neural network for 3d molecular structures with specified chemical and structural properties. This approach is agnostic to chemical bonding and enables targeted sampling of novel molecules from conditional distributions, even in domains where reference calculations are sparse. We demonstrate the utility of our method for inverse design by generating molecules with specified motifs or composition, discovering particularly stable molecules, and jointly targeting multiple electronic properties beyond the training regime.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). Builds on 24 of its 86 references that are in the map. First posted on arXiv 10 Sep 2021.

Builds on

24 of 86 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  4. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  5. 2020Directional Message Passing for Molecular Graphscited by 556
  6. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  7. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  8. 2020Machine Learning Force Fieldscited by 204
  9. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  10. 2021E(n) Equivariant Normalizing Flowscited by 165
  11. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  12. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
12 more
  1. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
  2. 2019A Generative Model for Molecular Distance Geometrycited by 73
  3. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  4. 2020Symmetry-Aware Actor-Critic for 3D Molecular Designcited by 55
  5. 2020Reinforcement Learning for Molecular Design Guided by Quantum Mechanicscited by 51
  6. 2019Deep learning for molecular design - a review of the state of the artcited by 38
  7. 2017Machine Learning Molecular Dynamics for the Simulation of Infrared Spectracited by 30
  8. 2019Generating valid Euclidean distance matricescited by 19
  9. 20203DMolNet: A Generative Network for Molecular Structurescited by 19
  10. 2020TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Searchcited by 15
  11. 2018Generating equilibrium molecules with deep neural networkscited by 10
  12. 2021Generating stable molecules using imitation and reinforcement learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 20; 2023: 20; 2024: 19; 2025: 24; 2026: 9.

93 papers.

Sort:

By area:

  1. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  3. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  4. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  5. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  6. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  7. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  8. 2024Space Group Constrained Crystal Generationcited by 71
  9. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  10. 2023Equivariant Flow Matching with Hybrid Probability Transportcited by 59
  11. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  12. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 44
38 more
  1. 2022Structure-based drug design with geometric deep learningcited by 40
  2. 2024Space Group Informed Transformer for Crystalline Materials Generationcited by 40
  3. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimizationcited by 36
  4. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  5. 2022SchNetPack 2.0: A neural network toolbox for atomistic machine learningcited by 29
  6. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  7. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  8. 2022Graph Neural Networks for Moleculescited by 21
  9. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  10. 2024Unified Generative Modeling of 3D Molecules via Bayesian Flow Networkscited by 18
  11. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17
  12. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generationcited by 17
  13. 2024MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworkscited by 15
  14. 2025A Periodic Bayesian Flow for Material Generationcited by 15
  15. 2025Periodic Materials Generation using Text-Guided Joint Diffusion Modelcited by 15
  16. 2024Geometric Representation Condition Improves Equivariant Molecule Generationcited by 13
  17. 2025Equivariant Neural Diffusion for Molecule Generationcited by 13
  18. 2023PubChemQC B3LYP/6-31G*//PM6 dataset: the Electronic Structures of 86 Million Molecules using B3LYP/6-31G* calculationscited by 12
  19. 2025Graph Neural Networks in Modern AI-aided Drug Discoverycited by 12
  20. 2023DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraintscited by 10
  21. 2023An Equivariant Generative Framework for Molecular Graph-Structure Co-Designcited by 10
  22. 2024Integrating Chemistry Knowledge in Large Language Models via Prompt Engineeringcited by 10
  23. 2022Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulationscited by 9
  24. 2024Molecular relaxation by reverse diffusion with time step predictioncited by 9
  25. 2025Siamese Foundation Models for Crystal Structure Predictioncited by 8
  26. 2025Equivariant Diffusion for Crystal Structure Predictioncited by 8
  27. 2023PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embeddingcited by 7
  28. 2023Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networkscited by 5
  29. 2024Text-guided Diffusion Model for 3D Molecule Generationcited by 5
  30. 2024Conditional Synthesis of 3D Molecules with Time Correction Samplercited by 5
  31. 2025Multilevel Generative Samplers for Investigating Critical Phenomenacited by 5
  32. 2025Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modelingcited by 5
  33. 2025Sampling 3D Molecular Conformers with Diffusion Transformerscited by 5
  34. 2022Atomic structure generation from reconstructing structural fingerprintscited by 4
  35. 2024Diffusion Twigs with Loop Guidance for Conditional Graph Generationcited by 4
  36. 2025TFG-Flow: Training-free Guidance in Multimodal Generative Flowcited by 4
  37. 2025Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusioncited by 4
  38. 2025InvDesFlow-AL: active learning-based workflow for inverse design of functional materialscited by 4

50 most cited of 93 All 93 (JSON)