Table 2.
Results of multiple models on Zheng’s dataset
| Strategies | Methods | AUC | AUPR | SEN | PRE | F1-score |
|---|---|---|---|---|---|---|
| Traditional | CF17 | 0.8103 | 0.4267 | – | 0.3616 | 0.3222 |
| Traditional | LPI-NRLMF24 | 0.8287 | 0.401 | – | – | – |
| Traditional | LPI-PPSN25 | 0.9098 | – | – | – | – |
| Traditional | LPI-KTASLP31 | 0.9152 | 0.7173 | – | 0.364 | 0.3488 |
| Network based | RWR23 | 0.9282 | 0.2813 | – | 0.2864 | 0.3397 |
| Network based | LPI-HN27 | 0.9315 | 0.2472 | – | 0.3913 | 0.3938 |
| Network based | LPI-BNI28 | 0.9407 | 0.3336 | – | – | – |
| Network based | LPI-MFFKL26 | 0.9669 | 0.7062 | – | – | – |
| Network based | LPI-FKLGCCN36 | 0.9639 | 0.5212 | 0.1363 | 0.2362 | – |
| Deep learning | LPI-KCGCN38 | 0.9907 | 0.9267 | 0.7377 | 0.9823 | 0.8426 |
| Deep learning | FMSRT-LPI | 0.9916 | 0.9861 | 0.9799 | 0.9609 | 0.9744 |