Research map / Probabilistic and scientific modeling / Molecules and proteins
Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation
Wengong Jin, Siranush Sarkizova, Xun Chen, Nir Hacohen, Caroline Uhler
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 |
|---|---|---|---|
| use NERE DSM objective instead of Gaussian DSM | energy-based model · PDBBind crystal | Pearson correlation: 0.638 -> 0.656 | Improved |
| use NERE DSM objective instead of Gaussian DSM | energy-based model · PDBBind docked | Pearson correlation: 0.632 -> 0.651 | Improved |
| use NERE DSM objective instead of contrastive learning | energy-based model · PDBBind crystal | Pearson correlation: 0.625 -> 0.656 | Improved |
| use NERE DSM instead of Gaussian DSM | energy-based model · SAbDab crystal | Pearson correlation: 0.335 -> 0.361 | Improved |
| use NERE DSM instead of contrastive learning | energy-based model · SAbDab crystal | Pearson correlation: 0.308 -> 0.361 | Improved |
| use NERE DSM instead of contrastive learning | energy-based model · SAbDab docked | Pearson correlation: 0.304 -> 0.360 | Improved |
| evaluate on docked instead of crystal structures | NERE DSM · PDBBind | Pearson correlation: 0.656 -> 0.651 | No clear effect |
| evaluate on docked instead of crystal structures | NERE DSM · SAbDab | Pearson correlation: 0.361 -> 0.360 | No clear effect |
| unsupervised NERE versus supervised FANN_transfer | NERE DSM · SAbDab crystal | Pearson correlation: 0.350 -> 0.361 | Improved |
| unsupervised NERE versus supervised IGN | NERE DSM · PDBBind crystal | Pearson correlation: 0.837 -> 0.656 | Hurt |
| replace SE(3)-invariant encoder with non-invariant encoder (ablation) | NERE DSM · PDBBind/SAbDab | Pearson correlation | Hurt |
| remove rotation DSM term (ablation) | NERE DSM · PDBBind/SAbDab | Pearson correlation | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- TankBind — TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction (NeurIPS 2022) · better on 0 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
- Physics Aware Neural Networks for Unsupervised Binding Energy Prediction (ICML 2025 · similarity 0.93)
- Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset (NeurIPS 2025 · similarity 0.86)
- DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction (NeurIPS 2025 · similarity 0.86)
- Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge (ICML 2024 · similarity 0.85)
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.85)
- UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection (NeurIPS 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.
