AI Paper Atlas

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

AAAI 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein interface and docking prediction · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add global attention over virtual atoms (Hierarchical Encoder) (ablation)SculptDrug · CrossDockedVina ScoreImproved
add Boundary Awareness Block (protein surface) (ablation)SculptDrug · CrossDockedsteric clashesImproved
add Boundary Awareness Block (protein surface) (ablation)SculptDrug · CrossDockedJSD All 12AImproved
add multi-type distance-aware edges instead of KNN (ablation)SculptDrug · CrossDockedoverall metricsImproved
SculptDrug vs MolCRAFT on Vina Min IMP%SculptDrug vs MolCRAFT · CrossDockedVina Min IMP%: 61.02 -> 60.70No clear effect
SculptDrug vs MolCRAFT on Vina Score EvinaSculptDrug vs MolCRAFT · CrossDockedVina Score Evina: -6.59 -> -6.94Improved
SculptDrug vs MolCRAFT on Vina Dock EvinaSculptDrug vs MolCRAFT · CrossDockedVina Dock Evina: -7.83 -> -8.06Improved
SculptDrug vs MolCRAFT on QEDSculptDrug vs MolCRAFT · CrossDockedQED: 0.50 -> 0.54Improved
SculptDrug vs MolCRAFT on SASculptDrug vs MolCRAFT · CrossDockedSA: 0.67 -> 0.67No clear effect
SculptDrug vs MolCRAFT on JSD BLSculptDrug vs MolCRAFT · CrossDockedJSD BL: 0.2251 -> 0.1522Improved
SculptDrug vs MolCRAFT on steric clashesSculptDrug vs MolCRAFT · CrossDockedsteric clashes: 7.03 -> 6.41Improved
SculptDrug vs MolCRAFT on strain energy 50th percentileSculptDrug vs MolCRAFT · CrossDockedstrain energy: 197.10 -> 170.17Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy