Research map / Probabilistic and scientific modeling / Molecules and proteins
Full-Atom Protein Pocket Design via Iterative Refinement
ZAIXI ZHANG, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu
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 |
|---|---|---|---|
| add residue-level hierarchical encoder (ablation) | FAIR · CrossDocked | AAR: 25.30 -> 40.17 | Improved |
| add residue-level hierarchical encoder (ablation) | FAIR · Binding MOAD | AAR: 29.21 -> 43.75 | Improved |
| add masked residue type update (consistency) (ablation) | FAIR · CrossDocked | AAR: 36.75 -> 40.17 | Improved |
| add masked residue type update (consistency) (ablation) | FAIR · CrossDocked | Vina score: -6.937 -> -7.022 | Improved |
| add full-atom refinement (ablation) | FAIR · CrossDocked | Vina score: -6.412 -> -7.022 | Improved |
| add full-atom refinement (ablation) | FAIR · CrossDocked | RMSD: 1.62 -> 1.42 | Improved |
| add ligand molecule context (ablation) | FAIR · CrossDocked | Vina score: -6.353 -> -7.022 | Improved |
| add ligand molecule context (ablation) | FAIR · Binding MOAD | AAR: 34.54 -> 43.75 | Improved |
| replace autoregressive decoding with iterative full-shot refinement (ablation) | FAIR · CrossDocked | AAR: 31.04 -> 40.17 | Improved |
| replace autoregressive decoding with iterative full-shot refinement (ablation) | FAIR · Binding MOAD | Vina score: -7.765 -> -7.978 | Improved |
| FAIR versus strongest baseline MEAN (ablation) | FAIR · CrossDocked | AAR: 35.46 -> 40.17 | Improved |
| FAIR versus strongest baseline MEAN (ablation) | FAIR · Binding MOAD | RMSD: 1.52 -> 1.35 | Improved |
Closest papers by meaning
- Generalized Protein Pocket Generation with Prior-Informed Flow Matching (NeurIPS 2024 · similarity 0.87)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.87)
- Full-Atom Peptide Design based on Multi-modal Flow Matching (ICML 2024 · similarity 0.86)
- Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN (ICML 2025 · similarity 0.86)
- Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design (ICML 2024 · similarity 0.86)
- Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment (ICLR 2024 · similarity 0.86)
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.
