Table 3.
Performance of the time-invariant, consensus, and published biomarkers using Random Forest.
| Signature | Dataset (Exposure Style) | Performance (Median AUC from LOOCV) | Variance (All Exposure) | |||
|---|---|---|---|---|---|---|
| Short-Term 3 | All Exposure 4 | IQR | C.V.d | C.V.e | ||
| Consensus biomarkers (1-day) | Multiple datasets 1 (1 day) | 0.739 | 0.733 | 0.049 * | 4.89% | 4.02% |
| Time-invariant biomarkers /Consensus biomarkers (3-day) |
Multiple datasets 1 (3 days) | 0.817 | 0.824 | 0.036 * | 4.34% | 4.72% |
| Consensus biomarker (1-week) | Multiple datasets 1 (5 or 7 days 2) | 0.780 | 0.810 | 0.111 | 7.41% | 7.25% |
| E5 | TG-GATEs (14 days) | 0.656 | 0.656 | 0.097 | 9.04% | 9.47% |
| F19 | DrugMatrix (5 days) | 0.796 | 0.809 | 0.085 | 6.47% | 3.88% |
| U9 | TG-GATEs (28 days) | 0.703 | 0.713 | 0.057 | 8.25% | 7.09% |
Note: 1 DrugMatrix, GSE8858, and TG-GATEs; 2 five days exposure in DrugMatrix and GSE8858, and seven days exposure in TG-GATEs; 3 1-day, 3- day, and 1-week high-dose exposures; 4 common short-term merged 14 days and 28 days high-dose exposures in TG-GATEs.* Significant difference (p < 0.05). A model with IQR, C.V.d, and C.V.e values less than 0.05 is considered as with a stable performance.