Research map / Probabilistic and scientific modeling / Molecules and proteins
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
Jiahao Chen, Letian Gao, Yanhao Zhu, Wenbiao zhou, Bing Su, Zhi John Lu, Bo Huang
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 |
|---|---|---|---|
| raise diffraction resolution cutoff from d_min 3.5 A to 1.5 A (ablation) | EDMolGPT · DUD-E CalED | Bioactive molecule recovery: 41% -> 46% | Improved |
| change d_min between 3.5 A and 1.5 A (ablation) | EDMolGPT · DUD-E CalED | Glide min-in-place: -6.92 -> -6.94 | No clear effect |
| increase sampling temperature from 0.7 to 1.2 (d_min 3.5 A) (ablation) | EDMolGPT · DUD-E CalED | Div: 0.184 -> 0.176 | No clear effect |
| increase sampling temperature from 0.7 to 1.2 (d_min 1.5 A) (ablation) | EDMolGPT · DUD-E CalED | Bioactive molecule recovery: 46% -> 44% | Hurt |
| increase sampling temperature from 0.7 to 1.2 (d_min 1.5 A) (ablation) | EDMolGPT · DUD-E CalED | Min-in-place better than redocking: 33% -> 36% | Improved |
| increase sampling temperature from 0.7 to 1.2 (d_min 3.5 A) (ablation) | EDMolGPT · DUD-E CalED | Bioactive molecule recovery: 41% -> 41% | No clear effect |
| condition on ligand electron density point clouds instead of rigid pockets | EDMolGPT vs MolCRAFT · DUD-E CalED | Bioactive molecule recovery: 17% -> 41% | Improved |
| condition on ligand electron density point clouds instead of rigid pockets | EDMolGPT vs Lingo3DMol · DUD-E CalED | Glide min-in-place: -6.8 -> -6.92 | Improved |
| add force-field refinement as in ED2Mol | ED2Mol vs EDMolGPT · DUD-E CalED | Strain energy median: 69 -> 24 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MolCRAFT — MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space (ICML 2024) · better on 4 of 4 shared results
- Pocket2Mol — Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets (ICML 2022) · better on 3 of 4 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
- Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows (ICLR 2025 · similarity 0.88)
- EDBench: Large-Scale Electron Density Data for Molecular Modeling (NeurIPS 2025 · similarity 0.86)
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation (ICLR 2024 · similarity 0.86)
- MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space (ICML 2024 · similarity 0.86)
- FlashMol: High-Quality Molecule Generation in as Few as Four Steps (NeurIPS 2026 · similarity 0.86)
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph (ICLR 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.
