Research map / Probabilistic and scientific modeling / Molecules and proteins
SigmaDock: Untwisting Molecular Docking with Fragment-Based SE(3) Diffusion
Alvaro Prat, Leo Zhang, Charlotte Deane, Yee Whye Teh, Garrett M Morris
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 triangulation conditioning (ablation) | SigmaDock · PoseBusters | Top-1 RMSD<2: 71.9 -> 80.5 | Improved |
| add triangulation conditioning (ablation) | SigmaDock · PoseBusters | Top-1 PB-valid: 67.1 -> 79.9 | Improved |
| add protein-ligand interactions in graph (ablation) | SigmaDock · PoseBusters | Top-1 PB-valid: 76.3 -> 79.9 | Improved |
| add fragment merging (ablation) | SigmaDock · PoseBusters | Top-1 PB-valid: 73.7 -> 79.9 | Improved |
| add energy scoring to ranking heuristic (ablation) | SigmaDock · PoseBusters | Top-1 RMSD<2: 67.2 -> 80.5 | Improved |
| add PB-check scoring to ranking heuristic (ablation) | SigmaDock · PoseBusters | Top-1 RMSD<2 vs PB-valid: RMSD 82.1 -> 80.5; PB-valid 70.8 -> 79.9 | Mixed |
| sample fragments from bound manifold M_b instead of M_c (ablation) | SigmaDock · PoseBusters | Top-1 PB-valid: 79.9 -> 85.4 | Improved |
| increase N_seeds from 10 to 40 (ablation) | SigmaDock · PoseBusters | Top-1 PB-valid: 72.2 -> 79.9 | Improved |
| increase pocket cutoff d0 from 5A to 7A | SigmaDock · PoseBusters | RMSD<2: 81.5 -> 69.8 | Hurt |
| complexes with co-factors versus none (natural ligands) | SigmaDock · PoseBusters | Top-1 RMSD<2: 84.2 -> 58.8 | Hurt |
| reduce Vina pocket size (autobox+5A) | Vina · PoseBusters | Top-1: 57.2 vs 56.0 | No clear effect |
Closest papers by meaning
- DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (ICLR 2023 · similarity 0.92)
- Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge (ICML 2024 · similarity 0.92)
- DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking (NeurIPS 2024 · similarity 0.91)
- Deep Confident Steps to New Pockets: Strategies for Docking Generalization (ICLR 2024 · similarity 0.87)
- Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms (ICLR 2024 · similarity 0.87)
- Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design (ICML 2024 · 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.
