Research map / Probabilistic and scientific modeling / Molecules and proteins
PoseX: AI Defeats Physics-based Methods on Protein Ligand Cross-Docking
Yize Jiang, Xinze Li, Yuanyuan Zhang, Jin Han, Youjun Xu, Ayush Pandit, ZAIXI ZHANG, Mengdi Wang, Mengyang Wang, Chong Liu, Guang Yang, Yejin Choi and 5 more
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 |
|---|---|---|---|
| use AI docking SurfDock instead of physics-based Glide | docking method · PoseX-SD pocket-given | success rate: 47.9% -> 78.0% | Improved |
| use AI docking SurfDock instead of physics-based Glide | docking method · PoseX-CD pocket-given | success rate: 38.4% -> 77.0% | Improved |
| add pocket specification (DiffDock-Pocket vs DiffDock-L) (ablation) | DiffDock · PoseX-SD | success rate: 47.1% -> 52.6% | Improved |
| add relaxation post-processing to AI approaches (ablation) | AI docking and co-folding · PoseX-SD/CD | PB-Valid pass rate | Improved |
| add relaxation post-processing to UMD V2 (ablation) | UMD V2 · PoseX | PB-Valid success rate | No clear effect |
| add physics-inspired steering potentials (Boltz-1x vs Boltz-1) (ablation) | Boltz-1 · PoseX-CD blind docking | chirality validity / success rate: 64.4% | Improved |
| move from similar to dissimilar pockets | TankBind · PoseX-CD | ligand RMSD: 4.79 -> 7.31 | Hurt |
| move from similar to dissimilar pockets | Chai-1 · PoseX-CD | ligand RMSD: 2.36 -> 5.72 | Hurt |
| move from similar to dissimilar pockets | Protenix · PoseX-CD | ligand RMSD: 2.53 -> 6.30 | Hurt |
| move from similar to dissimilar pockets | SurfDock · PoseX-CD | ligand RMSD: 1.56 -> 2.39 | Hurt |
| move from self-docking to cross-docking | Protenix · pocket similarity vs RMSD correlation | Pearson r: -0.390 -> -0.553 | Hurt |
| move from self-docking to cross-docking | Glide · pocket similarity vs RMSD correlation | Pearson r: 0.010 -> 0.015 | No clear effect |
Closest papers by meaning
- Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge (ICML 2024 · similarity 0.88)
- DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking (NeurIPS 2024 · similarity 0.87)
- Fast and Accurate Blind Flexible Docking (ICLR 2025 · similarity 0.86)
- Deep Confident Steps to New Pockets: Strategies for Docking Generalization (ICLR 2024 · similarity 0.85)
- Group Ligands Docking to Protein Pockets (ICLR 2025 · similarity 0.85)
- Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms (ICLR 2024 · similarity 0.85)
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.
