Research map / Probabilistic and scientific modeling / Molecules and proteins
SculptDrug: A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design
Qingsong Zhong, Haomin Yu, Yan Lin, Wangmeng Shen, Long Zeng, Jilin Hu
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 global attention over virtual atoms (Hierarchical Encoder) (ablation) | SculptDrug · CrossDocked | Vina Score | Improved |
| add Boundary Awareness Block (protein surface) (ablation) | SculptDrug · CrossDocked | steric clashes | Improved |
| add Boundary Awareness Block (protein surface) (ablation) | SculptDrug · CrossDocked | JSD All 12A | Improved |
| add multi-type distance-aware edges instead of KNN (ablation) | SculptDrug · CrossDocked | overall metrics | Improved |
| SculptDrug vs MolCRAFT on Vina Min IMP% | SculptDrug vs MolCRAFT · CrossDocked | Vina Min IMP%: 61.02 -> 60.70 | No clear effect |
| SculptDrug vs MolCRAFT on Vina Score Evina | SculptDrug vs MolCRAFT · CrossDocked | Vina Score Evina: -6.59 -> -6.94 | Improved |
| SculptDrug vs MolCRAFT on Vina Dock Evina | SculptDrug vs MolCRAFT · CrossDocked | Vina Dock Evina: -7.83 -> -8.06 | Improved |
| SculptDrug vs MolCRAFT on QED | SculptDrug vs MolCRAFT · CrossDocked | QED: 0.50 -> 0.54 | Improved |
| SculptDrug vs MolCRAFT on SA | SculptDrug vs MolCRAFT · CrossDocked | SA: 0.67 -> 0.67 | No clear effect |
| SculptDrug vs MolCRAFT on JSD BL | SculptDrug vs MolCRAFT · CrossDocked | JSD BL: 0.2251 -> 0.1522 | Improved |
| SculptDrug vs MolCRAFT on steric clashes | SculptDrug vs MolCRAFT · CrossDocked | steric clashes: 7.03 -> 6.41 | Improved |
| SculptDrug vs MolCRAFT on strain energy 50th percentile | SculptDrug vs MolCRAFT · CrossDocked | strain energy: 197.10 -> 170.17 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MolCRAFT — MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space (ICML 2024) · better on 9 of 11 shared results
- DecompDiff — DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design (ICML 2023) · better on 7 of 7 shared results
- Pocket2Mol — Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets (ICML 2022) · better on 3 of 3 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
- Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration (NeurIPS 2025 · similarity 0.90)
- Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks (ICLR 2024 · similarity 0.88)
- Structure-based drug design by denoising voxel grids (ICML 2024 · similarity 0.88)
- Energy-Based Flow Matching for Generating 3D Molecular Structure (ICML 2025 · similarity 0.87)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.87)
- Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows (ICLR 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.
