Research map / Probabilistic and scientific modeling / Molecules and proteins
DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
Yangtian Zhang, Zuobai Zhang, Bozitao Zhong, Sanchit Misra, Jian Tang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| autoregressive chi1-chi4 diffusion instead of joint diffusion (ablation) | DiffPack · CASP13/CASP14 | angle MAE (chi1,chi2): chi1 CASP13 17.14 -> 15.35; chi2 CASP14 34.51 -> 25.54 | Improved |
| autoregressive instead of random-angle diffusion (ablation) | DiffPack · CASP13 | chi2 angle MAE: 27.27 -> 19.19 | Improved |
| add multi-round sampling (ablation) | DiffPack · CASP13 | chi2 angle MAE: 23.13 -> 19.19 | Improved |
| add annealed temperature sampling (ablation) | DiffPack · CASP13 | chi2 angle MAE: 22.56 -> 19.19 | Improved |
| add confidence model ranking of samples (ablation) | DiffPack · CASP13 | chi2 angle MAE: 22.92 -> 19.19 | Improved |
| model torsion angles diffusion vs Cartesian regression (AttnPacker) | DiffPack · CASP13 | atom RMSD: 0.669 -> 0.579 | Improved |
| DiffPack refinement of AlphaFold2 backbones side chains | DiffPack · CASP13-FM | angle accuracy: 51.3 -> 55.5 | Improved |
Later papers that compared with this method
2 later accepted papers report DiffPack as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Full-Atom Peptide Design via Riemannian–Euclidean Bayesian Flow Networks (AAAI 2026 · better on 2 of 2 shared results)
- Full-Atom Peptide Design based on Multi-modal Flow Matching (ICML 2024 · better on 5 of 5 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance (AAAI 2025 · similarity 0.90)
- Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time (NeurIPS 2025 · similarity 0.88)
- Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression (NeurIPS 2025 · similarity 0.87)
- Bridge-IF: Learning Inverse Protein Folding with Markov Bridges (NeurIPS 2024 · similarity 0.87)
- SE(3)-Stochastic Flow Matching for Protein Backbone Generation (ICLR 2024 · similarity 0.87)
- Learning conformational ensembles of proteins based on backbone geometry (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
