Research map / Graph learning / Knowledge and temporal graphs
Predicting Molecular Conformation via Dynamic Graph Score Matching
Shitong Luo, Chence Shi, Minkai Xu, Jian Tang
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 dynamic graph construction with non-bonded edges (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-QM9 | COV mean (%): 88.49 -> 91.49 | Improved |
| add dynamic graph construction with non-bonded edges (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-QM9 | MAT mean (A): 0.2673 -> 0.2139 | Improved |
| add dynamic graph construction with non-bonded edges (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-Drugs | COV mean (%): 62.15 -> 78.73 | Improved |
| add dynamic graph construction with non-bonded edges (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-Drugs | MAT mean (A): 1.1629 -> 1.0154 | Improved |
| add dynamic graph construction (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-QM9 ensemble property | MAE of average energy E (eV): 2.7886 -> 1.0313 | Improved |
| add dynamic graph construction (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-QM9 ensemble property | MAE of lowest energy Emin (eV): 0.1765 -> 0.0761 | Improved |
| add dynamic graph construction (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · GEOM-QM9 ensemble property | MAE of average gap (eV): 0.4688 -> 0.1963 | Improved |
| add dynamic graph construction (DGSM vs CONFGF) | ConfGF-style score-based conformation generator · SidechainNet sidechain generation | mean RMSD (A): 3.38 -> 2.85 | Improved |
Closest papers by meaning
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks (ICML 2024 · similarity 0.90)
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.90)
- REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring (ICLR 2025 · similarity 0.89)
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation (ICML 2024 · similarity 0.88)
- Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism (NeurIPS 2024 · similarity 0.88)
- Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel (ICLR 2024 · similarity 0.87)
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.
