mlsanityData to 14 Oct 2026

DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing

arXiv 2306.01794 ↗First posted 1 Jun 2023q-bio.QM cs.LGcited by 24

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Proteins play a critical role in carrying out biological functions, and their 3D structures are essential in determining their functions. Accurately predicting the conformation of protein side-chains given their backbones is important for applications in protein structure prediction, design and protein-protein interactions. Traditional methods are computationally intensive and have limited accuracy, while existing machine learning methods treat the problem as a regression task and overlook the restrictions imposed by the constant covalent bond lengths and angles. In this work, we present DiffPack, a torsional diffusion model that learns the joint distribution of side-chain torsional angles, the only degrees of freedom in side-chain packing, by diffusing and denoising on the torsional space. To avoid issues arising from simultaneous perturbation of all four torsional angles, we propose autoregressively generating the four torsional angles from chi1 to chi4 and training diffusion models for each torsional angle. We evaluate the method on several benchmarks for protein side-chain packing and show that our method achieves improvements of 11.9% and 13.5% in angle accuracy on CASP13 and CASP14, respectively, with a significantly smaller model size (60× fewer parameters). Additionally, we show the effectiveness of our method in enhancing side-chain predictions in the AlphaFold2 model. Code is available at https://github.com/DeepGraphLearning/DiffPack.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 34 of its 77 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

34 of 77 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023SE(3) diffusion model with application to protein backbone generation5 Feb
  2. 2022Protein structure generation via folding diffusion30 Sep
  3. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem8 Jun
  4. 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models26 May
  5. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  6. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  8. 2021E(n) Equivariant Graph Neural Networkscited by 965
  9. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  10. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  11. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  12. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
16 more
  1. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  2. 2020Directional Message Passing for Molecular Graphscited by 561
  3. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  4. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  5. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 313
  6. 2022Torsional Diffusion for Molecular Conformer Generationcited by 263
  7. 2021Autoregressive Diffusion Modelscited by 210
  8. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 162
  9. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 106
  10. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 68
  11. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 54
  12. 2022Multi-Scale Representation Learning on Proteinscited by 52
  13. 2022Contrastive Representation Learning for 3D Protein Structurescited by 30
  14. 2018Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materialscited by 21
  15. 2015Protein secondary structure prediction using deep convolutional neural fieldscited by 12
  16. 2017Prediction of amino acid side chain conformation using a deep neural networkcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 10; 2026: 2.

24 papers.

Sort:

By area:

  1. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  2. 2024Full-Atom Peptide Design based on Multi-modal Flow Matchingcited by 34
  3. 2024PPFlow: Target-aware Peptide Design with Torsional Flow Matchingcited by 26
  4. 2024Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridgecited by 16
  5. 2025An All-Atom Generative Model for Designing Protein Complexescited by 10
  6. 2025Flexible MOF Generation with Torsion-Aware Flow Matchingcited by 10
  7. 2024DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detectorcited by 9
  8. 2024Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extensioncited by 9
  9. 2025Diffusion Generative Modeling on Lie Group Representationscited by 8
  10. 2023H-Packer: Holographic Rotationally Equivariant Convolutional Neural Network for Protein Side-Chain Packingcited by 6
  11. 2024De novo antibody design with SE(3) diffusioncited by 5
  12. 2024Multi-level Interaction Modeling for Protein Mutational Effect Predictioncited by 5
12 more
  1. 2024EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamicscited by 5
  2. 2024SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learningcited by 4
  3. 2025AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusioncited by 4
  4. 2025PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Modelscited by 3
  5. 2026Surface-based Molecular Design with Multi-modal Flow Matchingcited by 3
  6. 2025Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flowscited by 2
  7. 2024Sifting through the Noise: A Survey of Diffusion Probabilistic Models and Their Applications to Biomoleculescited by 1
  8. 2025The Docking Game: Loop Self-Play for Fast, Dynamic, and Accurate Prediction of Flexible Protein-Ligand Bindingcited by 1
  9. 2025Full-Atom Peptide Design via Riemannian-Euclidean Bayesian Flow Networkscited by 1
  10. 2025THFlow: A Temporally Hierarchical Flow Matching Framework for 3D Peptide Designcited by 0
  11. 2025Joint Design of Protein Surface and Structure Using a Diffusion Bridge Modelcited by 0
  12. 2026MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Torsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement
  2. 2024AlphaFolding: 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance
  3. 2023Graph Denoising Diffusion for Inverse Protein Folding
  4. 2025Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time
  5. 2023DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models
  6. 2023Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction
  7. 2024Mask prior-guided denoising diffusion improves inverse protein folding
  8. 2024Loop-Diffusion: an equivariant diffusion model for designing and scoring protein loops