Research map / Probabilistic and scientific modeling / Molecules and proteins
DeCoDe: Decoupling Binding Position and Molecular Conformation in 3D Ligand Diffusion for Structure-Based Drug Design
Julong Yang, Wen Huang, Junhui Chen, Jian Peng
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 decoupled diffusion of binding position and conformation | TargetDiff · CrossDocked2020 | all-atom distance JSD: 0.089 -> 0.060 | Improved |
| add decoupled diffusion of binding position and conformation | IRDiff · CrossDocked2020 | carbon-carbon bond distance JSD: 0.266 -> 0.137 | Improved |
| add decoupled diffusion to TargetDiff, binding affinity | TargetDiff · CrossDocked2020 | High Affinity: 58.1% -> 56.9% | No clear effect |
| add decoupled diffusion to IRDiff, binding affinity | IRDiff · CrossDocked2020 | Vina Score avg: -6.03 -> -6.69 | Improved |
| decouple diffusion only, without parameterization decoupling (ablation) | TargetDiff · CrossDocked2020 | carbon-carbon JSD: 0.225 -> 0.292 | Hurt |
| add parameterization decoupling (protein translates rigidly) (ablation) | TargetDe · CrossDocked2020 | carbon-carbon JSD: 0.292 -> 0.214 | Improved |
| add time-dependent asynchronous noise scheduling (ablation) | TargetDeDe · CrossDocked2020 | carbon-carbon JSD: 0.214 -> 0.164 | Improved |
| use asynchronous schedule instead of synchronous schedule (ablation) | DeCoDe · CrossDocked2020 | Vina Score avg: -5.92 -> -6.19 | Improved |
| swap schedules (destroy position faster than structure) (ablation) | DeCoDe · CrossDocked2020 | Vina Score avg: -6.19 -> -5.51 | Hurt |
| apply soft-DPO fine-tuning to IRDeCo | IRDeCo · CrossDocked2020 | Vina Dock avg: -8.58 -> -8.88 | Improved |
Closest papers by meaning
- DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization (ICLR 2024 · similarity 0.90)
- Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation (NeurIPS 2024 · similarity 0.89)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.89)
- Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows (ICLR 2025 · similarity 0.89)
- Binding-Adaptive Diffusion Models for Structure-Based Drug Design (AAAI 2024 · similarity 0.89)
- DiSCO: Diffusion Schrödinger Bridge for Molecular Conformer Optimization (AAAI 2024 · similarity 0.88)
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.
