Table 2 Performance assessment of the ensemble model for GSOM-based PUL approach for DDI prediction using Similarity Feature Representation1 (SFR1) and Similarity Feature Representation2 (SFR2)
From: Positive-Unlabeled Learning for inferring drug interactions based on heterogeneous attributes
| Â | Â | SFR1 | SFR2 | Ensemble model |
|---|---|---|---|---|
Cross validation (80%) | Precision | 0.960 | 0.968 | Â |
| Â | Recall | 0.841 | 0.972 | Â |
| Â | F-measure | 0.896 | 0.970 | Â |
Testing (20%) | Precision | 0.749 | 0.973 | 0.970 |
| Â | Recall | 0.648 | 0.979 | 0.975 |
| Â | F-measure | 0.692 | 0.976 | 0.973 |