Research map / Probabilistic and scientific modeling / Molecules and proteins
KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction
Jiayu Qin, Zhengquan Luo, Guy Tadmor, Changyou Chen, David Zeevi, zhiqiang xu
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 KGOT pseudo-labels | PairRE · KG link prediction | Hits@1: 10.0% -> 10.9% | Improved |
| add KGOT pseudo-labels | RotatE · KG link prediction | Hits@1: 48.5% -> 52.0% | Improved |
| add KGOT pseudo-labels | MuRE · KG link prediction | Hits@1: 15.9% -> 13.7% | Hurt |
| add KGOT pseudo-labels | TorusE · KG link prediction | Hits@5: 70.0% -> 74.9% | Improved |
| add KGOT pseudo-labels | ComplEx-FF · KG link prediction | Hits@1: 30.8% -> 43.6% | Improved |
| use OT loss instead of InfoNCE for score learning (ablation) | scoring model (MuRE) · KG link prediction | MRR: 0.243 -> 0.256 | Improved |
| add OT pseudo-labels vs none (ablation) | TorusE · KG link prediction | Hits@5: 68.5 -> 74.9 | Improved |
| use random pseudo-labels instead of none (ablation) | TorusE · KG link prediction | Hits@5: 68.5 -> 66.0 | Hurt |
| use OT instead of top-k pseudo-labels (ablation) | TorusE · KG link prediction | Hits@5: 72.0 -> 74.9 | Improved |
| add molecular similarity constraint to OT (ablation) | TorusE · KG link prediction | Hits@5: 73.8 -> 74.9 | Improved |
| use low entropy regularization epsilon=0.01 instead of 0.1 (ablation) | TorusE · KG link prediction | Hits@5: 73.0 -> 74.9 | Improved |
| add Gene Ontology relations to KG (ablation) | TorusE · KG link prediction | Hits@1: 36.3% -> 43.7% | Improved |
Closest papers by meaning
- PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs (NeurIPS 2025 · similarity 0.85)
- MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding (ICLR 2024 · similarity 0.85)
- PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design (ICML 2025 · similarity 0.84)
- Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision (CVPR 2024 · similarity 0.84)
- PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction (AAAI 2024 · similarity 0.83)
- Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning (ICML 2024 · similarity 0.83)
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.
