Research map / Probabilistic and scientific modeling / Molecules and proteins
CORE: Automatic Molecule Optimization Using Copy & Refine Strategy
Tianfan Fu, Cao Xiao, Jimeng Sun
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 Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · QED test set | SR2: 24.34% -> 27.23% | Improved |
| Use Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · DRD2 test set | SR2: 15.31% -> 17.31% | Improved |
| Use Copy & Refine instead of GCPN | molecule optimization · LogP04 test set | SR2: 27.01% -> 27.88% | Improved |
| Use Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · LogP06 test set | SR2: 25.30% -> 26.58% | Improved |
| Use Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · QED infrequent-substructure test subset | SR2: 20.82% -> 25.32% | Improved |
| Use Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · DRD2 infrequent-substructure test subset | SR2: 12.88% -> 15.26% | Improved |
| Use Copy & Refine instead of GCPN | molecule optimization · LogP04 infrequent-substructure test subset | SR2: 23.81% -> 25.62% | Improved |
| Use Copy & Refine instead of Graph-to-Graph substructure generation | molecule optimization · LogP06 infrequent-substructure test subset | SR2: 23.82% -> 25.91% | Improved |
Closest papers by meaning
- DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization (ICLR 2024 · similarity 0.86)
- Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization (ICML 2025 · similarity 0.86)
- Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark (NeurIPS 2026 · similarity 0.85)
- Unified all-atom molecule generation with neural fields (NeurIPS 2025 · similarity 0.85)
- Amortized Molecular Optimization via Group Relative Policy Optimization (NeurIPS 2026 · similarity 0.85)
- Aligning Transformers with Continuous Feedback via Energy Rank Alignment (NeurIPS 2025 · similarity 0.85)
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.
