Skip to main content

Table 4 Tool performance and comparison summary statistics to 48 h-LC50 of daphnia based on entire dataset

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

Methods

Measures of predictive performance

ECOSAR

T.E.S.T.

Danish Q.D.

VEGA

Read Across

Trend Analysis

KATE

37 PCCs

Number of missing predictions

0

4

3

2

2

6

12

Qualitative

Number of correct

24

21

20

18

16

14

21

Number of incorrect

13

12

14

17

19

17

4

Total accuracy (%)a

65

64

59

51

46

45

84

Predictive power (%)b

65

57

54

49

43

38

57

R2 (toxicity class)

0.46

0.46

0.37

0.29

0.51

0.33

0.65

Quantitative

Accuracy within a factor of 10 (%)

76

67

68

63

49

45

80

Accuracy within a factor of 100 (%)

86

91

91

80

83

55

96

Accuracy within a factor of 1000 (%)

97

97

94

94

94

81

100

R2(log10 LC50)

0.40

0.42

0.38

0.13

0.42

0.40

0.68

42 NCs

Qualitative

Number of correct

22

9

13

9

/c

/

9

Number of incorrect

16

22

11

32

/

/

11

Number of missing predictions

4

11

18

1

/

/

22

Total accuracy (%)a

58

29

54

22

/

/

45

Predictive power (%)b

52

21

31

21

/

/

21

R2 (toxicity class)

0.35

0.04

0.50

0.04

/

/

0.36

  1. a Total accuracy is the fraction of chemicals assessed by each tool for which the predicted LC50 falls within the same regulatory category as the measured LC50. b Similar to total accuracy, predictive power measures the total number of correct category assignments. However, lack of prediction is treated as an incorrect assignment. c Not analyzed