TABLE 3.
Performance comparison on GPCR dataset over leave-one-out cross-validation.
| Method | Sn(%) | Sp(%) | ACC(%) | Str (%) | MCC |
|---|---|---|---|---|---|
| IGPCR-Drug Xiao et al. (2013) | 78.3 | 91.4 | 86.9 | 84.9 | 0.71 |
| OET-KNN Hu et al. (2016) | 77.8 | 88.7 | 85.0 | 83.3 | 0.67 |
| QuickRBF Hu et al. (2016) | 74.8 | 92.4 | 86.4 | 83.6 | 0.69 |
| SVM Hu et al. (2016) | 74.2 | 92.7 | 86.4 | 83.6 | 0.69 |
| RF Hu et al. (2016) | 76.5 | 92.9 | 87.3 | 84.7 | 0.71 |
| RF + PP Hu et al. (2016) | 79.7 | 92.8 | 88.3 | 86.3 | 0.73 |
| DWKNN(Ensemble) Wang et al. (2020) | 81.1 | 87.1 | 85.1 | 84.1 | 0.67 |
| BOW-GBDT Qiu et al. (2021) | 79.8 | 93.1 | 88.5 | 86.3 | 0.74 |
| Our method | 92.2 | 92.0 | 91.9 | 90.1 | 0.84 |
The best results for each metric are in bold.