Table 1 Performance assessment of the proposed GSOM-based PUL approach, Baseline and OCSVM using Similarity Feature Representation1 (SFR1) and Similarity Feature Representation2 (SFR2)
From: Positive-Unlabeled Learning for inferring drug interactions based on heterogeneous attributes
| Â | Â | Â | Baseline | OCSVM | GSOM-based PUL |
|---|---|---|---|---|---|
Cross validation | SFR1 | Precision | 0.628 | 0.584 | 0.951 |
| Â | Â | Recall | 0.448 | 0.499 | 0.861 |
| Â | Â | F1-score | 0.523 | 0.537 | 0.904 |
| Â | SFR2 | Precision | 0.823 | 0.622 | 0.974 |
| Â | Â | Recall | 0.850 | 0.436 | 0.975 |
| Â | Â | F1-score | 0.836 | 0.511 | 0.974 |