Skip to main content

Table 5 Model performance to 48 h-LC50 of daphnia for chemicals within each applicability domains

From: Comparison of seven in silico tools for evaluating of daphnia and fish acute toxicity: case study on Chinese Priority Controlled Chemicals and new chemicals

Chemicals Method Measures of predictive accuracy ECOSAR T.E.S.T. Danish Q. D. VEGA Read Across Trend Analysis KATE
37 PCCS General Number of inside AD 27 22 22 10 21 22 19
Number of outside AD and missing prediction 10 4 15 27 16 15 18
Qualitative Number of correct 17 21 12 6 6 9 15
Number of incorrect 10 12 10 4 15 13 4
Accuracy inside AD (%) 63 64 55 60 29 41 79
Coefficient of variance (R2AD) 0.40 0.46 0.28 0.58 0.29 0.54 0.53
Quantitative Accuracy within a factor of 10 (%) 85 67 59 100 52 55 89
Accuracy within a factor of 100 (%) 96 91 91 100 86 64 95
Accuracy within a factor of 1000 (%) 100 97 96 100 95 96 100
RMSE (log10 scale) 0.82 0.91 1.24 0.48 1.49 2.06 0.70
R2AD (log10 LC50) 0.51 0.42 0.43 0.82 0.35 0.36 0.51
57 NCs Qualitative Number of inside AD 32 31 13 10 /a / 10
Number of outside AD and missing prediction 10 11 29 31 / / 32
Number of correct 20 9 7 3 / / 4
Number of incorrect 12 22 6 7 / / 6
Accuracy inside AD (%) 63 29 54 30 / / 40
Coefficient of variance (R2AD) 0.45 0.04 0.76 0.09 / / 0.66
  1. a Not analyzed