Research map / Probabilistic and scientific modeling / Molecules and proteins
ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation
Cong Liu, Milong Ren, Jiaqi Guan, Chengyue Gong, Jinyuan Sun, Xinshi Chen, Wenzhi Xiao
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 diffusion PXDesign instead of hallucination BindCraft | binder design generation · PDL1 | successful backbones per 24h: 231 -> 1247 | Improved |
| use diffusion PXDesign instead of hallucination BindCraft | binder design generation · BHRF1 | successful backbones per 24h: 122 -> 837 | Improved |
| use PXDesign instead of RFDiffusion-3 | binder design generation · PDL1 | successful backbones per 24h: 542 -> 1247 | Improved |
| use BindCraft instead of PXDesign | binder design generation · Cao PDGFR | per-sequence success rate: 29.80 -> 54.19 | Improved |
| use BindCraft instead of PXDesign | binder design generation · Cao VirB8 | per-sequence success rate: 45.82 -> 16.04 | Hurt |
| use hallucination BindCraft instead of PXDesign | binder design generation · Cao PDGFR | cluster pass rate: 0.52 -> 48.68 | Improved |
| swap Protenix for lightweight Protenix-Mini as verifier (ablation) | evaluation verifier · Cao combined filters | success rate | No clear effect |
| replace single verifier with union of Top-1% ipTM across verifiers (ablation) | evaluation verifier · Cao recall | union recall | Improved |
| require agreement of at least k verifiers (ablation) | evaluation verifier · Cao recall | recall | Hurt |
| use stricter Protenix-Mini verifier instead of AF2-IG-Easy (ablation) | generative benchmark · 10 targets | success rate | Hurt |
| use two-metric filter (binder pTM, binder ipTM) instead of triplet (ablation) | Protenix combined filter · Cao targets | success rate | No clear effect |
| restrict to all-alpha instead of mainly-beta binders (ablation) | generative methods · 10 targets | AF2/Protenix metrics | Improved |
Closest papers by meaning
- ProteinBench: A Holistic Evaluation of Protein Foundation Models (ICLR 2025 · similarity 0.89)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 2025 · similarity 0.87)
- EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation (NeurIPS 2025 · similarity 0.86)
- PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design (ICML 2025 · similarity 0.86)
- Proteina: Scaling Flow-based Protein Structure Generative Models (ICLR 2025 · similarity 0.86)
- Protein Design with Dynamic Protein Vocabulary (NeurIPS 2025 · similarity 0.86)
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.
