Research map / Probabilistic and scientific modeling / Molecules and proteins
Topology-Enhanced and Label Correlation-Aware Model for Protein-Protein Interaction Prediction
Bin Deng, Huifang Ma, Ruijia Zhang, Meihuizi Jia, Rui Bing
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 topology enhancement (H2 edges) (ablation) | TELC-PPI · STRING (Random split) | micro-F1: 96.24 -> 96.94 | Improved |
| add topology enhancement (H2 edges) (ablation) | TELC-PPI · SHS27k (Random split) | micro-F1: 89.09 -> 89.37 | Improved |
| add topology enhancement (H2 edges) (ablation) | TELC-PPI · average of three datasets | micro-F1: 92.54 -> 92.98 | Improved |
| add topological strength in H2 edge scoring (alpha>0) (ablation) | TELC-PPI · average of three datasets | micro-F1: 92.80 -> 92.98 | Improved |
| add node (label-distribution) similarity in H2 edge scoring (alpha<1) (ablation) | TELC-PPI · average of three datasets | micro-F1: 92.59 -> 92.98 | Improved |
| add label embedding module with co-occurrence and ML loss (ablation) | TELC-PPI · average of three datasets | micro-F1: 92.81 -> 92.98 | Improved |
| add label embedding module (ablation) | TELC-PPI · SHS27k (Random split) | micro-F1: 89.21 -> 89.37 | Improved |
| TELC-PPI versus MAPE-PPI on DFS split | MAPE-PPI · SHS27k (DFS split) | micro-F1: 71.98 -> 73.45 | Improved |
| TELC-PPI versus MAPE-PPI on BFS split | MAPE-PPI · SHS148k (BFS split) | micro-F1: 74.76 -> 73.61 | Hurt |
| TELC-PPI versus MAPE-PPI on STRING DFS split | TELC-PPI · STRING (DFS split) | micro-F1: 86.50 -> 87.98 | Improved |
| sampling ratio rho too small (0.1) or too large (0.8) (ablation) | TELC-PPI · SHS27k (Random split) | micro-F1 | Hurt |
| moderate alpha in {0.3,0.4,0.5} with rho in {0.3,0.4} (ablation) | TELC-PPI · SHS27k (Random split) | micro-F1: 0.8937 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MAPE-PPI — MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding (ICLR 2024) · better on 8 of 9 shared results
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
- PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs (NeurIPS 2025 · similarity 0.87)
- PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design (ICML 2025 · similarity 0.85)
- MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding (ICLR 2024 · similarity 0.84)
- PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction (AAAI 2024 · similarity 0.84)
- Revisiting Link Prediction: a data perspective (ICLR 2024 · similarity 0.83)
- MOTIVE: A Drug-Target Interaction Graph For Inductive Link Prediction (NeurIPS 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.
