mlsanityData to 7 Oct 2026

Evaluating representation learning on the protein structure universe

arXiv 2406.13864 ↗First posted 19 Jun 2024cs.LG q-bio.BMcited by 16

Not on the map. Why?

Abstract (arXiv)

We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 39 of its 91 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

39 of 91 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  4. 2018Datasheets for Datasetscited by 1,371
  5. 2021E(n) Equivariant Graph Neural Networkscited by 951
  6. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  7. 2020Benchmarking Graph Neural Networkscited by 672
  8. 2020Directional Message Passing for Molecular Graphscited by 556
  9. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  10. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  11. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  12. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
27 more
  1. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  2. 2019Evaluating Protein Transfer Learning with TAPEcited by 229
  3. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 213
  4. 2020Design Space for Graph Neural Networkscited by 182
  5. 2022e3nn: Euclidean Neural Networkscited by 171
  6. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 161
  7. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  8. 2023On the Expressive Power of Geometric Graph Neural Networkscited by 89
  9. 2021Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designcited by 82
  10. 2022PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understandingcited by 77
  11. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 73
  12. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  13. 2023A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systemscited by 65
  14. 2022Learning Hierarchical Protein Representations via Complete 3D Graph Networkscited by 54
  15. 2022Multi-Scale Representation Learning on Proteinscited by 52
  16. 2017DeepSF: deep convolutional neural network for mapping protein sequences to foldscited by 46
  17. 2022TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discoverycited by 45
  18. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  19. 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materialscited by 22
  20. 2021Geometric Transformers for Protein Interface Contact Predictioncited by 18
  21. 2023gRNAde: Geometric Deep Learning for 3D RNA inverse designcited by 18
  22. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 15
  23. 2021DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Predictioncited by 10
  24. 2023Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoycited by 10
  25. 2023Towards Joint Sequence-Structure Generation of Nucleic Acid and Protein Complexes with SE(3)-Discrete Diffusioncited by 9
  26. 2020Protein model quality assessment using rotation-equivariant, hierarchical neural networkscited by 8
  27. 2023Modeling Molecular Structures with Intrinsic Diffusion Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 5.

16 papers.

Sort:

By area:

  1. 2025Protein Structure Tokenization: Benchmarking and New Recipecited by 13
  2. 2024Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamicscited by 5
  3. 2025Multi-state Protein Design with DynamicMPNNcited by 3
  4. 2025Topotein: Topological Deep Learning for Protein Representation Learningcited by 2
  5. 2025A Comprehensive Benchmark for RNA 3D Structure-Function Modelingcited by 1
  6. 2025Fast and Interpretable Protein Substructure Alignment via Optimal Transportcited by 1
  7. 2025Hierarchical geometric deep learning enables scalable analysis of molecular dynamicscited by 1
  8. 2024Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphscited by 0
  9. 2025General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applicationscited by 0
  10. 2025Demystify Protein Generation with Hierarchical Conditional Diffusion Modelscited by 0
  11. 2025Multi-Scale Protein Structure Modelling with Geometric Graph U-Netscited by 0
  12. 2026MMPG: MoE-based Adaptive Multi-Perspective Graph Fusion for Protein Representation Learningcited by 0
4 more
  1. 2026PUFFIN: Protein Unit Discovery with Functional Supervisioncited by 0
  2. 2026PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchiescited by 0
  3. 2026Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modelingcited by 0
  4. 2026Predicting Transmembrane Protein Topology from 3D Structurecited by 0