Table 5 Results yielded by SVM on Cdataset using tenfold cross validation
From: Predicting drug−disease associations via sigmoid kernel-based convolutional neural networks
| Test set | Acc. (%) | Pre. (%) | Recall. (%) | F1-score. (%) |
|---|---|---|---|---|
| 1 | 86.61 | 88.43 | 84.25 | 86.29 |
| 2 | 89.17 | 90.95 | 87.01 | 88.93 |
| 3 | 84.39 | 87.50 | 80.24 | 83.71 |
| 4 | 90.51 | 92.18 | 88.54 | 90.32 |
| 5 | 85.77 | 89.52 | 81.03 | 85.06 |
| 6 | 86.17 | 89.96 | 81.42 | 85.48 |
| 7 | 87.15 | 89.50 | 84.19 | 86.76 |
| 8 | 87.35 | 89.54 | 84.58 | 86.99 |
| 9 | 85.97 | 89.57 | 81.42 | 85.30 |
| 10 | 87.35 | 88.57 | 85.77 | 87.15 |
| Average | 87.04 ± 1.66 | 89.57 ± 1.24 | 83.85 ± 2.63 | 86.60 ± 1.83 |
| SKCNN | 91.38 ± 1.39 | 92.69 ± 1.58 | 89.89 ± 2.21 | 91.25 ± 1.45 |