mlsanityData to 7 Oct 2026

GEOM: Energy-annotated molecular conformations for property prediction and molecular generation

arXiv 2006.05531 ↗First posted 9 Jun 2020physics.comp-ph cs.LGcited by 238

Not on the map. Why?

Cited by 72 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Machine learning (ML) outperforms traditional approaches in many molecular design tasks. ML models usually predict molecular properties from a 2D chemical graph or a single 3D structure, but neither of these representations accounts for the ensemble of 3D conformers that are accessible to a molecule. Property prediction could be improved by using conformer ensembles as input, but there is no large-scale dataset that contains graphs annotated with accurate conformers and experimental data. Here we use advanced sampling and semi-empirical density functional theory (DFT) to generate 37 million molecular conformations for over 450,000 molecules. The Geometric Ensemble Of Molecules (GEOM) dataset contains conformers for 133,000 species from QM9, and 317,000 species with experimental data related to biophysics, physiology, and physical chemistry. Ensembles of 1,511 species with BACE-1 inhibition data are also labeled with high-quality DFT free energies in an implicit water solvent, and 534 ensembles are further optimized with DFT. GEOM will assist in the development of models that predict properties from conformer ensembles, and generative models that sample 3D conformations.

Key facts. Cited by 238 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 22; 2023: 37; 2024: 51; 2025: 62; 2026: 54.

238 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. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  4. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  5. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  6. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  7. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
  8. 2024Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Datacited by 143
  9. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  10. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  11. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  12. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 96
38 more
  1. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
  2. 2023PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEscited by 84
  3. 2024Scientific Large Language Models: A Survey on Biological & Chemical Domainscited by 80
  4. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
  5. 2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 75
  6. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  7. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  8. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  9. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  10. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  11. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  12. 2023Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Modelscited by 65
  13. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  14. 2022MDM: Molecular Diffusion Model for 3D Molecule Generationcited by 58
  15. 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 55
  16. 2023Swallowing the Bitter Pill: Simplified Scalable Conformer Generationcited by 55
  17. 2023Clifford Group Equivariant Neural Networkscited by 54
  18. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 53
  19. 2023Graph Generation with Diffusion Mixturecited by 52
  20. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  21. 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Moleculescited by 49
  22. 2022Unified 2D and 3D Pre-Training of Molecular Representationscited by 45
  23. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  24. 2024ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generationcited by 41
  25. 2024SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matchingcited by 40
  26. 20233D molecule generation by denoising voxel gridscited by 38
  27. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  28. 2023Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasetscited by 37
  29. 2022State-specific protein-ligand complex structure prediction with a multi-scale deep generative modelcited by 35
  30. 2022A Systematic Survey of Chemical Pre-trained Modelscited by 34
  31. 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretrainingcited by 32
  32. 2021Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphscited by 31
  33. 2023Graph Positional and Structural Encodercited by 31
  34. 2022Direct Molecular Conformation Generationcited by 30
  35. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  36. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3Dcited by 24
  37. 2023Automated 3D Pre-Training for Molecular Property Predictioncited by 24
  38. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 23

50 most cited of 238 All 238 (JSON)