mlsanityData to 7 Oct 2026

Learning Hierarchical Protein Representations via Complete 3D Graph Networks

arXiv 2207.12600 ↗First posted 26 Jul 2022cs.LG q-bio.QMcited by 54

Not on the map. Why?

Abstract (arXiv)

We consider representation learning for proteins with 3D structures. We build 3D graphs based on protein structures and develop graph networks to learn their representations. Depending on the levels of details that we wish to capture, protein representations can be computed at different levels, e.g., the amino acid, backbone, or all-atom levels. Importantly, there exist hierarchical relations among different levels. In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations. Our ProNet is very flexible and can be used to compute protein representations at different levels of granularity. By treating each amino acid as a node in graph modeling as well as harnessing the inherent hierarchies, our ProNet is more effective and efficient than existing methods. We also show that, given a base 3D graph network that is complete, our ProNet representations are also complete at all levels. Experimental results show that ProNet outperforms recent methods on most datasets. In addition, results indicate that different downstream tasks may require representations at different levels. Our code is publicly available as part of the DIG library (urlhttps://github.com/divelab/DIG).

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 39 of its 79 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

39 of 79 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  7. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  8. 2020Directional Message Passing for Molecular Graphscited by 556
  9. 2019Graph U-Netscited by 489
  10. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  11. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  12. 2019Evaluating Protein Transfer Learning with TAPEcited by 229
27 more
  1. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  2. 2018DeepDTA: Deep Drug-Target Binding Affinity Predictioncited by 171
  3. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  4. 2020ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computingcited by 162
  5. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 161
  6. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 143
  7. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  8. 2021Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Dockingcited by 81
  9. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  10. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 73
  11. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  12. 2021Equivariant Graph Neural Networks for 3D Macromolecular Structurecited by 53
  13. 2022Multi-Scale Representation Learning on Proteinscited by 52
  14. 2019Learning protein sequence embeddings using information from structurecited by 50
  15. 2017DeepSF: deep convolutional neural network for mapping protein sequences to foldscited by 46
  16. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  17. 2020Topology-Aware Graph Pooling Networkscited by 44
  18. 2021Protein sequence design with deep generative modelscited by 35
  19. 2018End-to-End Learning on 3D Protein Structure for Interface Predictioncited by 32
  20. 2022GraphFM: Improving Large-Scale GNN Training via Feature Momentumcited by 31
  21. 2022Contrastive Representation Learning for 3D Protein Structurescited by 30
  22. 2021Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Designcited by 23
  23. 2020Deep Learning of High-Order Interactions for Protein Interface Predictioncited by 22
  24. 2022Task-Agnostic Graph Explanationscited by 20
  25. 2021Geometric Transformers for Protein Interface Contact Predictioncited by 18
  26. 2022Orientation-Aware Graph Neural Networks for Protein Structure Representation Learningcited by 8
  27. 2022EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structurescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 20; 2025: 12; 2026: 11.

54 papers.

Sort:

By area:

  1. 2023On the Expressive Power of Geometric Graph Neural Networkscited by 89
  2. 2023A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systemscited by 65
  3. 2023A new perspective on building efficient and expressive 3D equivariant graph neural networkscited by 46
  4. 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
  5. 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
  6. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  7. 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materialscited by 22
  8. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  9. 2024Evaluating representation learning on the protein structure universecited by 16
  10. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 15
  11. 2023De novo protein design using geometric vector field networkscited by 14
  12. 2024Pre-training with Fractional Denoising to Enhance Molecular Property Predictioncited by 14
38 more
  1. 2023ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignmentcited by 12
  2. 2023Protein-ligand binding representation learning from fine-grained interactionscited by 12
  3. 2023Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimationcited by 7
  4. 2024Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chainscited by 6
  5. 2024Clustering for Protein Representation Learningcited by 6
  6. 2023AtomSurf : Surface Representation for Learning on Protein Structurescited by 5
  7. 2024An Equivariant Pretrained Transformer for Unified 3D Molecular Representation Learningcited by 5
  8. 2024Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamicscited by 5
  9. 2024Binding Affinity Prediction: From Conventional to Machine Learning-Based Approachescited by 3
  10. 2024Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfercited by 3
  11. 2024MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Predictioncited by 3
  12. 2025Advances in Protein Representation Learning: Methods, Applications, and Future Directionscited by 3
  13. 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanationcited by 3
  14. 2026Self-Conditioned Denoising for Atomistic Representation Learningcited by 3
  15. 2024GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learningcited by 2
  16. 2024OneProt: Towards Multi-Modal Protein Foundation Modelscited by 2
  17. 2025Multi-Modality Representation Learning for Antibody-Antigen Interactions Predictioncited by 2
  18. 2024PepGB: Facilitating peptide drug discovery via graph neural networkscited by 1
  19. 2024Deep Manifold Transformation for Protein Representation Learningcited by 1
  20. 2025Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Modelcited by 1
  21. 2025A Comprehensive Benchmark for RNA 3D Structure-Function Modelingcited by 1
  22. 2025Bidirectional Hierarchical Protein Multi-Modal Representation Learningcited by 1
  23. 2025GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generationcited by 1
  24. 2025Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discoverycited by 1
  25. 2024NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networkscited by 0
  26. 2024HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learningcited by 0
  27. 2024Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphscited by 0
  28. 2024DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Dockingcited by 0
  29. 2025Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-trainingcited by 0
  30. 2025AlphaFold Database Debiasing for Robust Inverse Foldingcited by 0
  31. 2025Demystify Protein Generation with Hierarchical Conditional Diffusion Modelscited by 0
  32. 2025Tokenizing Loops of Antibodiescited by 0
  33. 2026MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learningcited by 0
  34. 2026Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifscited by 0
  35. 2026Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensemblescited by 0
  36. 2026h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Networkcited by 0
  37. 2026Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioningcited by 0
  38. 2026Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generationcited by 0

50 most cited of 54 All 54 (JSON)