Research map / Probabilistic and scientific modeling / Molecules and proteins
Hierarchical Multi-Scale Molecular Conformer Generation with Structural Awareness
Jiapeng Hu, Weizhi Gao, Zhichao Hou, Xiaorui Liu
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 ground-truth heavy-atom geometric guidance | GeoDiff · GEOM-Drugs preliminary | COV-R mean: 64.12 -> 99.58 | Improved |
| add ground-truth heavy-atom geometric guidance | GeoDiff · GEOM-Drugs preliminary | MAT-R mean: 1.1444 -> 0.5035 | Improved |
| add MSGEN two-stage generation | GeoDiff · GEOM-Drugs | COV-P mean: 60.17 -> 66.26 | Improved |
| add MSGEN two-stage generation | GeoDiff · GEOM-Drugs | MAT-R mean: 0.8686 -> 0.8424 | Improved |
| add MSGEN | GeoDiff · GEOM-QM9 ensemble energy | MAE average energy (eV): 0.2597 -> 0.1795 | Improved |
| add MSGEN under domain transfer (Drugs to QM9) | GeoDiff · GEOM-QM9 | COV-R mean: 74.94 -> 83.73 | Improved |
| add third stage (Murcko scaffold) to MSGEN (ablation) | ET-Flow · GEOM-Drugs | COV-R mean: 80.50 -> 81.91 | Improved |
| add third stage (Murcko scaffold) to MSGEN (ablation) | GeoDiff · GEOM-Drugs | COV-R mean: 90.41 -> 91.05 | Improved |
| add MSGEN 2-stage to ConfGF | ConfGF · GEOM-Drugs | COV-R mean: 62.15 -> 65.51 | Improved |
| add MSGEN 2-stage to EBD | EBD · GEOM-Drugs | COV-R mean: 92.10 -> 91.92 | No clear effect |
| add second stage (hierarchical design) after Stage 1 (ablation) | GeoDiff+MSGEN · GEOM-Drugs coarse atoms | COV-R: 87.86 -> 89.17 -> 90.41 | Improved |
| use molecular upsampling instead of random or centroid sampling (ablation) | MSGEN · GEOM-Drugs | COV/MAT | 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.
- GeoDiff — GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022) · better on 9 of 9 shared results
- ET-Flow — ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation (NeurIPS 2024) · better on 1 of 1 shared result
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
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation (ICML 2024 · similarity 0.91)
- Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow (ICML 2025 · similarity 0.90)
- Enhancing Generalizability in Molecular Conformation Generation with METRIZATION-Informed Geometric Diffusion Pretraining (AAAI 2025 · similarity 0.89)
- DiSCO: Diffusion Schrödinger Bridge for Molecular Conformer Optimization (AAAI 2024 · similarity 0.89)
- Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation (NeurIPS 2024 · similarity 0.89)
- Energy-Based Flow Matching for Generating 3D Molecular Structure (ICML 2025 · 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.
