Research map / Probabilistic and scientific modeling / Molecules and proteins
Efficiently incorporating quintuple interactions into geometric deep learning force fields
Zun Wang, Guoqing Liu, Yichi Zhou, Tong Wang, Bin Shao
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 explicit five-body interactions up to part II (ablation) | QuinNet · Chignolin | energy and force MAE | Improved |
| add five-body interactions up to part I (ablation) | QuinNet · Chignolin | energy MAE | Mixed |
| remove four-body improper terms when five-body part I is used (ablation) | QuinNet · Chignolin | energy and force MAE: 1.2906 ± 0.0267 energy, 0.2974 ± 0.002417 force | Improved |
| compare QuinNet with nine other models | QuinNet · MD17 | energy and force MAE: 57.14% | Improved |
| compare QuinNet with ViSNet and other models | QuinNet · Revised MD17 | energy and force MAE | No clear effect |
| compare QuinNet with ViSNet-LSRM and MACE on forces | QuinNet · MD22 | force MAE: 0.0942 -> 0.0681 on Ac-Ala3-NHMe | Improved |
| compare QuinNet energy with ViSNet-LSRM and long-range or large-cutoff models | QuinNet · MD22 | energy MAE | Hurt |
Closest papers by meaning
- Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians (ICLR 2025 · similarity 0.87)
- EDBench: Large-Scale Electron Density Data for Molecular Modeling (NeurIPS 2025 · similarity 0.86)
- Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation (ICLR 2024 · similarity 0.85)
- Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs (NeurIPS 2024 · similarity 0.85)
- Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions (ICML 2025 · similarity 0.85)
- The dark side of the forces: assessing non-conservative force models for atomistic machine learning (ICML 2025 · similarity 0.84)
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.
