Research map / Probabilistic and scientific modeling / Molecules and proteins
SYNC: Measuring and Advancing Synthesizability in Structure-Based Drug Design
Yunfan Liu, Lirong Wu, Zhifeng Gao, Yufei Huang, Cheng Tan, Haitao Lin, Zicheng Liu, Changxi Chi, Chang Yu, Stan Z. Li
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 SYNC gradient guidance to diffusion sampling | TargetDiff · CrossDocked2020 | SYNC score: 0.1958 -> 0.3977 | Improved |
| add SYNC-based DPO fine-tuning | TargetDiff · CrossDocked2020 | SYNC score: 0.1958 -> 0.2385 | Improved |
| add SYNC guidance | DecompDiff · CrossDocked2020 | SYNC score: 0.1201 -> 0.1378 | Improved |
| add SYNC-based DPO | DecompDiff · CrossDocked2020 | GASA: 0.2104 -> 0.1762 | Hurt |
| add SYNC-based DPO | DecompDiff · CrossDocked2020 | RAScore: 0.330 -> 0.300 | Hurt |
| add SYNC guidance | TargetDiff · CrossDocked2020 | Vina Dock avg: -7.42 -> -7.75 | Improved |
| add SYNC-based DPO | TargetDiff · CrossDocked2020 | Vina Dock avg: -7.42 -> -7.58 | Improved |
| add SYNC guidance | DecompDiff · CrossDocked2020 | Vina Dock avg: -8.39 -> -8.60 | Improved |
| use 3D conformation instead of 1D fingerprints (ablation) | SYNC · Nonpher-Test | accuracy: 0.8250 -> 0.9313 | Improved |
| use 3D conformation instead of 1D SMILES (ablation) | SYNC · Nonpher-Test | accuracy: 0.7250 -> 0.9313 | Improved |
| use 3D conformation instead of 2D graphs (ablation) | SYNC · Nonpher-Test | accuracy: 0.9188 -> 0.9313 | Improved |
| add bond-type edge features (ablation) | SYNC · Enamine | accuracy: 0.9520 -> 0.9366 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DecompDiff — DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design (ICML 2023) · better on 2 of 2 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
- FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling (NeurIPS 2024 · similarity 0.90)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.88)
- Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design (NeurIPS 2026 · similarity 0.88)
- Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule (ICML 2025 · similarity 0.88)
- Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion (ICML 2024 · similarity 0.88)
- MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space (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.
