Skip to main content

Table 3 Performance of the selected models in fitting, CV, and on the test sets

From: OPERA models for predicting physicochemical properties and environmental fate endpoints

Property No. of descriptors Fivefold CV (75%) Training (75%) Test (25%)
Q2 RMSE Dataset R2 RMSE Dataset R2 RMSEP
AOH 13 0.85 1.14 516 0.85 1.12 176 0.83 1.23
BCF 10 0.84 0.55 469 0.85 0.53 157 0.83 0.64
BioHL 6 0.89 0.25 112 0.88 0.26 38 0.75 0.38
BP 13 0.93 22.46 4077 0.93 22.06 1358 0.93 22.08
HL 9 0.84 1.96 441 0.84 1.91 150 0.85 1.82
KM 12 0.83 0.49 405 0.82 0.5 136 0.73 0.62
KOA 2 0.95 0.69 202 0.95 0.65 68 0.96 0.68
KOC 12 0.81 0.55 545 0.81 0.54 184 0.71 0.61
LogP 9 0.86 0.69 10,537 0.86 0.67 3513 0.86 0.78
MP 16 0.74 50.20 6486 0.75 49.12 2167 0.74 52.27
VP 12 0.91 1.08 2034 0.91 1.08 679 0.92 1
WS 11 0.87 0.81 3158 0.87 0.82 1066 0.86 0.86
Property Descriptor BA Sn–Sp Dataset BA Sn–Sp Dataset BA Sn–Sp
RB 10 0.8 0.82–0.78 1197 0.8 0.82–0.79 411 0.79 0.81–0.77