Research map / 3D vision / Face and shape
DSR: Dynamical Surface Representation as Implicit Neural Networks for Protein
Daiwen Sun, He Huang, Yao Li, Xinqi Gong, Qiwei Ye
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 |
|---|---|---|---|
| extend prediction horizon from next 10 to frames 11-20 | DSR · DIMS future prediction | IoU: 0.8467 -> 0.6835 | Hurt |
| extend prediction horizon from next 10 to frames 11-20 | DSR · I-FABP future prediction | IoU: 0.8878 -> 0.8444 | Hurt |
| extend prediction horizon from next 10 to frames 11-20 | DSR · FRODA future prediction | IoU: 0.7660 -> 0.6043 | Hurt |
| extend prediction horizon from next 10 to frames 11-20 | DSR · DIMS future prediction | Chamfer distance: 0.0010 -> 0.0055 | Hurt |
| trajectories with smaller RMSD (less noise) | DSR · reconstruction across 21 proteins | IoU/Chamfer/NC: IoU 0.9316 (DIMS) vs 0.4219 (T0771) | Improved |
| use DSR instead of linear interpolation for temporal interpolation | DSR · interpolation across 20 proteins | IoU/Chamfer/NC | Improved |
| evaluate interpolation instead of reconstruction | DSR · interpolation across proteins | IoU/Chamfer/NC | No clear effect |
| train a shared model with per-protein latent vectors and increasing frame intervals | DSR · GPCRmd 4 proteins | reconstruction quality | Improved |
| increase noise level of MD trajectory (jitter) | DSR · reconstruction | fit | Hurt |
Closest papers by meaning
- Generalized Implicit Neural Representations for Dynamic Molecular Surface Modeling (AAAI 2025 · similarity 0.92)
- AtomSurf: Surface Representation for Learning on Protein Structures (ICLR 2025 · similarity 0.86)
- 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance (AAAI 2025 · similarity 0.86)
- Predicting directional flexibility in proteins (NeurIPS 2026 · similarity 0.86)
- Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression (NeurIPS 2025 · similarity 0.85)
- Boosting Protein Graph Representations through Static-Dynamic Fusion (ICML 2025 · similarity 0.85)
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.
