Research map / 3D vision / Face and shape
Conformation-Guided Molecular Representation with Hamiltonian Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 HamNet fingerprints instead of the strongest listed baseline | HamNet · QM9 | Multi-MAE: 1.292 -> 1.194 | Helped |
| Use HamNet fingerprints instead of the strongest listed baseline | HamNet · Tox21 | Multi-ROC: 0.857 -> 0.875 | Helped |
| Use HamNet fingerprints instead of the strongest listed baseline | HamNet · Lipop | RMSE: 0.566 -> 0.557 | Helped |
| Use HamNet fingerprints instead of the strongest listed baseline | HamNet · FreeSolv | RMSE: 0.736 -> 0.731 | Helped |
| Use HamNet fingerprints instead of the strongest listed baseline | HamNet · ESOL | RMSE: 0.505 -> 0.504 | Helped |
| Add conformation-related components to the Fingerprint Generator (ablation) | HamNet · QM9 | Multi-MAE: 1.237±0.030 -> 1.194±0.038 | Helped |
| Add conformation-related components to the Fingerprint Generator (ablation) | HamNet · Tox21 | Multi-ROC: 0.868±0.012 -> 0.875± 0.006 | Helped |
| Add conformation-related components to the Fingerprint Generator (ablation) | HamNet · Lipop | RMSE: 0.572±0.011 -> 0.557±0.014 | Helped |
| Add conformation-related components to the Fingerprint Generator (ablation) | HamNet · FreeSolv | RMSE: 0.840±0.023 -> 0.731±0.024 | Helped |
| Add conformation-related components to the Fingerprint Generator (ablation) | HamNet · ESOL | RMSE: 0.547±0.015 -> 0.504±0.016 | Helped |
| Replace real conformations with Hamiltonian Engine-generated conformations (ablation) | HamNet · QM9 | Multi-MAE: 1.199±0.017 -> 1.194±0.038 | Helped |
| Replace real conformations with Hamiltonian Engine-generated conformations (ablation) | HamNet · Tox21 | Multi-ROC: 0.864±0.006 -> 0.875± 0.006 | Helped |
Closest papers by meaning
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.88)
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks (ICML 2024 · similarity 0.87)
- A Plug-and-Play Quaternion Message-Passing Module for Molecular Conformation Representation (AAAI 2024 · similarity 0.87)
- Enhancing Molecular Representation Learning Through the Combination of 3D and 2D Graph Machine Learning (Student Abstract) (AAAI 2025 · similarity 0.86)
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation (ICML 2024 · similarity 0.86)
- HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning (AAAI 2024 · 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.