Table 5. Results for PBT Index of Chemicals (Model Dataset 5) with Best Weighting (0.5–0–0.5) Combination as Obtained from the Retrospective Study.
model | division method | R2 | Q2 | MAE95%Train | QExt-F12 | MAE95%Test | correct prediction in % | training set range | number of compounds outside ADa |
---|---|---|---|---|---|---|---|---|---|
1 | sorted responseb | 0.88 | 0.87 | 0.36 | 0.92 | 0.37 | 91.67 | 8.1 | 1 (189) |
2 | 0.90 | 0.89 | 0.33 | 0.95 | 0.27 | 100 | 2 (41, 189) | ||
3 | 0.89 | 0.88 | 0.35 | 0.94 | 0.30 | 100 | 2 (14, 189) | ||
4 | 0.89 | 0.88 | 0.34 | 0.93 | 0.34 | 91.67 | 1 (14) | ||
5 | 0.89 | 0.88 | 0.34 | 0.94 | 0.32 | 88.89 | 4 (14, 41, 189, 206) | ||
6 | Kennard–Stonec | 0.91 | 0.90 | 0.35 | 0.87 | 0.34 | 95.56 | 8.1 | 2 (211, 212) |
7 | 0.90 | 0.89 | 0.34 | 0.88 | 0.29 | 95.56 | 0 | ||
8 | 0.91 | 0.90 | 0.34 | 0.88 | 0.34 | 95.56 | 0 | ||
9 | 0.91 | 0.90 | 0.34 | 0.88 | 0.31 | 95.56 | 0 | ||
10 | 0.92 | 0.91 | 0.33 | 0.88 | 0.31 | 95.56 | 0 | ||
11 | modified-k-medoidsd | 0.91 | 0.90 | 0.32 | 0.84 | 0.45 | 88.64 | 7.24 | 3 (11, 25, 189) |
12 | 0.90 | 0.89 | 0.32 | 0.87 | 0.40 | 86.36 | 2 (11, 25) | ||
13 | 0.92 | 0.91 | 0.31 | 0.86 | 0.43 | 93.18 | 2 (11, 25) | ||
14 | 0.90 | 0.89 | 0.32 | 0.88 | 0.39 | 93.18 | 0 | ||
15 | 0.92 | 0.91 | 0.31 | 0.86 | 0.43 | 93.18 | 2 (11, 25) |
AD using standardization technique is used and compound ID mentioned under parenthesis.
NTraining = 144, NTest = 36.
NTraining = 135, NTest = 45.
NTraining = 136, NTest = 44.