Table 2.
Predictive accuracies using gene expression thresholds.
| Training Set | Test Set | Unit | TP | TN | FP | FN | Sensitivity | Specificity | PPV | NPV | Balanced accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|
| TG-Training | TG-Test | Chemical | 9 | 23 | 6 | 0 | 1.000 | 0.793 | 0.600 | 1.000 | 0.897 |
| TG-All | DM-All | Chemical | 37 | 16 | 26 | 1 | 0.974 | 0.381 | 0.587 | 0.941 | 0.677 |
| DM-All | TG-All | Chemical | 17 | 56 | 6 | 1 | 0.944 | 0.903 | 0.739 | 0.982 | 0.924 |
| DM-All | TG-4d | Chemical | 15 | 61 | 1 | 3 | 0.833 | 0.984 | 0.938 | 0.953 | 0.909 |
| DM-All | TG-8d | Chemical | 16 | 61 | 1 | 2 | 0.889 | 0.984 | 0.941 | 0.968 | 0.936 |
| DM-All | TG-15d | Chemical | 16 | 59 | 3 | 2 | 0.889 | 0.952 | 0.842 | 0.967 | 0.920 |
| DM-All | TG-29d | Chemical | 17 | 58 | 4 | 1 | 0.944 | 0.935 | 0.810 | 0.983 | 0.940 |
DM, DrugMatrix; TG, TG-GATES; TP, true positive; TN, true negative; FP, false positive; FN, false negative; PPV, positive predictive value; NPV, negative predictive value.