mlsanityData to 14 Oct 2026

Equivariant Graph Neural Networks for 3D Macromolecular Structure

arXiv 2106.03843 ↗First posted 7 Jun 2021cs.LG q-bio.BMcited by 53

Not on the map. Why?

Abstract (arXiv)

Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on three out of eight tasks in the ATOM3D benchmark, is tied for first on two others, and is competitive with equivariant networks using higher-order representations and spherical harmonic convolutions. In addition, we demonstrate that transfer learning can further improve performance on certain downstream tasks. Code is available at https://github.com/drorlab/gvp-pytorch.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 10 of its 19 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

10 of 19 references.

References · 10

  1. 2021E(n) Equivariant Graph Neural Networkscited by 965
  2. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  3. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  4. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  5. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  6. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  7. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 74
  8. 2018N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentialscited by 42
  9. 2020Protein model quality assessment using rotation-equivariant, hierarchical neural networkscited by 8
  10. 2021Protein sequence-to-structure learning: Is this the end(-to-end revolution)?cited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 17; 2024: 10; 2025: 10; 2026: 7.

53 papers.

Sort:

By area:

  1. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  2. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  3. 2022Learning Hierarchical Protein Representations via Complete 3D Graph Networkscited by 55
  4. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 54
  5. 2023Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaborationcited by 30
  6. 2023Learning Subpocket Prototypes for Generalizable Structure-based Drug Designcited by 25
  7. 2023Over-Squashing in Graph Neural Networks: A Comprehensive surveycited by 23
  8. 2023Uncovering Neural Scaling Laws in Molecular Representation Learningcited by 23
  9. 2025FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generationcited by 21
  10. 2022Equivariant Graph Attention Networks for Molecular Property Predictioncited by 20
  11. 2023Generalist Equivariant Transformer Towards 3D Molecular Interaction Learningcited by 19
  12. 2023FABind: Fast and Accurate Protein-Ligand Bindingcited by 17
38 more
  1. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 16
  2. 2023Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Actioncited by 15
  3. 2025Multi-domain Distribution Learning for De Novo Drug Designcited by 15
  4. 2022Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networkscited by 14
  5. 2023Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Predictioncited by 13
  6. 2023Generation of 3D Molecules in Pockets via Language Modelcited by 13
  7. 2024RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matchingcited by 12
  8. 2023Equivariant Neural Operator Learning with Graphon Convolutioncited by 11
  9. 2024Exploring Discrete Flow Matching for 3D De Novo Molecule Generationcited by 11
  10. 2022SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representationcited by 10
  11. 2025UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomoleculescited by 7
  12. 2025BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimationcited by 7
  13. 2024SE(3)-Hyena Operator for Scalable Equivariant Learningcited by 6
  14. 2023AtomSurf : Surface Representation for Learning on Protein Structurescited by 5
  15. 2024An Equivariant Pretrained Transformer for Unified 3D Molecular Representation Learningcited by 5
  16. 2024Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimizationcited by 5
  17. 2023Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structurecited by 4
  18. 2024Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Predictioncited by 4
  19. 2025Geometric Hyena Networks for Large-scale Equivariant Learningcited by 4
  20. 20216DCNN with roto-translational convolution filters for volumetric data processingcited by 2
  21. 2023Geometric Deep Learning for Structure-Based Drug Design: A Surveycited by 2
  22. 2021An In-depth Summary of Recent Artificial Intelligence Applications in Drug Designcited by 1
  23. 2023Graph Representation Learning for Interactive Biomolecule Systemscited by 1
  24. 2023Inverse Protein Folding Using Deep Bayesian Optimizationcited by 1
  25. 2023Predicting protein variants with equivariant graph neural networkscited by 1
  26. 2024Conditional Shift-Robust Conformal Prediction for Graph Neural Networkcited by 1
  27. 2024Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structurecited by 1
  28. 2025A Comprehensive Benchmark for RNA 3D Structure-Function Modelingcited by 1
  29. 2023Target-aware Variational Auto-encoders for Ligand Generation with Multimodal Protein Representation Learningcited by 0
  30. 2024RoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classificationcited by 0
  31. 2025Demystify Protein Generation with Hierarchical Conditional Diffusion Modelscited by 0
  32. 2025Flow-Based Fragment Identification via Binding Site-Specific Latent Representationscited by 0
  33. 2025Machine learning approaches for interpretable antibody property prediction using structural datacited by 0
  34. 2025OMTRA: A Multi-Task Generative Model for Structure-Based Drug Designcited by 0
  35. 2026Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifscited by 0
  36. 2026h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Networkcited by 0
  37. 2026Scalable Inference-Time Annealing with Surrogate Likelihood Estimatorscited by 0
  38. 2026SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggabilitycited by 0

50 most cited of 53 All 53 (JSON)