mlsanityData to 7 Oct 2026

CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation

arXiv 2306.14852 ↗First posted 26 Jun 2023cs.LG physics.chem-ph q-bio.BMcited by 7

Not on the map. Why?

Abstract (arXiv)

Molecular conformer generation (MCG) is an important task in cheminformatics and drug discovery. The ability to efficiently generate low-energy 3D structures can avoid expensive quantum mechanical simulations, leading to accelerated virtual screenings and enhanced structural exploration. Several generative models have been developed for MCG, but many struggle to consistently produce high-quality conformers. To address these issues, we introduce CoarsenConf, which coarse-grains molecular graphs based on torsional angles and integrates them into an SE(3)-equivariant hierarchical variational autoencoder. Through equivariant coarse-graining, we aggregate the fine-grained atomic coordinates of subgraphs connected via rotatable bonds, creating a variable-length coarse-grained latent representation. Our model uses a novel aggregated attention mechanism to restore fine-grained coordinates from the coarse-grained latent representation, enabling efficient generation of accurate conformers. Furthermore, we evaluate the chemical and biochemical quality of our generated conformers on multiple downstream applications, including property prediction and oracle-based protein docking. Overall, CoarsenConf generates more accurate conformer ensembles compared to prior generative models.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 26 Jun 2023.

Builds on

31 of 55 references.

References · 31

  1. 2021E(n) Equivariant Graph Neural Networkscited by 951
  2. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  3. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  4. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  5. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  6. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  7. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  8. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  9. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  10. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  11. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  12. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
19 more
  1. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  2. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 162
  3. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 143
  4. 2021GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensemblescited by 106
  5. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  6. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
  7. 2019A Generative Model for Molecular Distance Geometrycited by 73
  8. 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamicscited by 72
  9. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  10. 2020Coarse Graining Molecular Dynamics with Graph Neural Networkscited by 56
  11. 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 55
  12. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  13. 2022Direct Molecular Conformation Generationcited by 30
  14. 2022Generative Coarse-Graining of Molecular Conformationscited by 21
  15. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  16. 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteinscited by 14
  17. 2022Improving Small Molecule Generation using Mutual Information Machinecited by 10
  18. 2023Do Deep Learning Methods Really Perform Better in Molecular Conformation Generation?cited by 8
  19. 2021Fragment-based Sequential Translation for Molecular Optimizationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 1.

7 papers.

  1. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  2. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  3. 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functionalcited by 18
  4. 2024General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug Designcited by 5
  5. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generationcited by 2
  6. 2023Investigating the Behavior of Diffusion Models for Accelerating Electronic Structure Calculationscited by 1
  7. 2024DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Dockingcited by 0