mlsanityData to 7 Oct 2026

Learning Gradient Fields for Molecular Conformation Generation

arXiv 2105.03902 ↗First posted 9 May 2021cs.LG physics.chem-ph q-bio.BMcited by 162

Not on the map. Why?

Cited by 55 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs. Existing machine learning approaches usually first predict distances between atoms and then generate a 3D structure satisfying the distances, where noise in predicted distances may induce extra errors during 3D coordinate generation. Inspired by the traditional force field methods for molecular dynamics simulation, in this paper, we propose a novel approach called ConfGF by directly estimating the gradient fields of the log density of atomic coordinates. The estimated gradient fields allow directly generating stable conformations via Langevin dynamics. However, the problem is very challenging as the gradient fields are roto-translation equivariant. We notice that estimating the gradient fields of atomic coordinates can be translated to estimating the gradient fields of interatomic distances, and hence develop a novel algorithm based on recent score-based generative models to effectively estimate these gradients. Experimental results across multiple tasks show that ConfGF outperforms previous state-of-the-art baselines by a significant margin.

Key facts. Cited by 162 papers in the map (data through 7 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 9 May 2021.

Builds on

31 of 52 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  8. 2021E(n) Equivariant Graph Neural Networkscited by 951
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  10. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
19 more
  1. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  2. 2020Directional Message Passing for Molecular Graphscited by 556
  3. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  4. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  5. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  6. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  7. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  8. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  9. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  10. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
  11. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  12. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  13. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
  14. 2019A Generative Model for Molecular Distance Geometrycited by 73
  15. 2020Symmetry-Aware Actor-Critic for 3D Molecular Designcited by 55
  16. 2020Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Propertiescited by 51
  17. 2020TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Searchcited by 15
  18. 2020Autoregressive Score Matchingcited by 15
  19. 2021HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networkscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 41; 2023: 48; 2024: 34; 2025: 20; 2026: 10.

162 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  3. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  4. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  5. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  6. 2022Long Range Graph Benchmarkcited by 258
  7. 2022A Survey on Generative Diffusion Modelcited by 238
  8. 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptionscited by 215
  9. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  10. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  11. 2023The probability flow ODE is provably fastcited by 145
  12. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 143
38 more
  1. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  2. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  3. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  4. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  5. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  6. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  7. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  8. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  9. 2021Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designcited by 82
  10. 2023Generative Diffusion Models on Graphs: Methods and Applicationscited by 79
  11. 2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 75
  12. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
  13. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 73
  14. 2022Equivariant Graph Mechanics Networks with Constraintscited by 67
  15. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  16. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  17. 2023Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Modelscited by 65
  18. 2022MDM: Molecular Diffusion Model for 3D Molecule Generationcited by 58
  19. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  20. 2022GFPose: Learning 3D Human Pose Prior with Gradient Fieldscited by 57
  21. 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 55
  22. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generationcited by 55
  23. 2022TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discoverycited by 45
  24. 2022Unified 2D and 3D Pre-Training of Molecular Representationscited by 45
  25. 2023Stable Target Field for Reduced Variance Score Estimation in Diffusion Modelscited by 44
  26. 2021Physics-Guided Deep Learning for Dynamical Systems: A Surveycited by 43
  27. 2024ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generationcited by 41
  28. 2023Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltoniancited by 38
  29. 20233D molecule generation by denoising voxel gridscited by 38
  30. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  31. 2024Equivariant Graph Neural Operator for Modeling 3D Dynamicscited by 37
  32. 2022Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Pathscited by 36
  33. 2022E3Bind: An End-to-End Equivariant Network for Protein-Ligand Dockingcited by 35
  34. 2023A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Materialcited by 34
  35. 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretrainingcited by 32
  36. 2021Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphscited by 31
  37. 2022Protein Sequence and Structure Co-Design with Equivariant Translationcited by 31
  38. 2022Direct Molecular Conformation Generationcited by 30

50 most cited of 162 All 162 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Physics-informed generative model for drug-like molecule conformers
  2. 2026Generative Pseudo-Force Fields for Molecular Generation
  3. 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
  4. 2026VecMol: Vector-Field Representations for 3D Molecule Generation
  5. 2022Flow-matching -- efficient coarse-graining of molecular dynamics without forces
  6. 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
  7. 2024Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
  8. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D