Skip to main content

Table 3 General results from the assessment on the balanced dataset of monomeric proteins

From: Performance of Web tools for predicting changes in protein stability caused by mutations

 

PoPMuSiC

DynaMut

DUET

INPS-MD

MAESTROweb

Values calculated for mutations causing a ΔΔG>|0.5|kcal/mol

True negative

94

52

89

95

86

False positive

8

50

13

7

16

True positive

44

80

64

49

62

False negative

58

22

38

53

40

Accuracy

0.68

0.65

0.75

0.71

0.73

True negative rate (specificity)

0.92

0.51

0.87

0.93

0.84

True positive rate (sensitivity)

0.43

0.78

0.63

0.48

0.61

Positive predictive value (precision)

0.85

0.62

0.83

0.88

0.79

Negative predictive value

0.62

0.70

0.70

0.64

0.68

MCC

0.40

0.31

0.52

0.46

0.46

Values calculated for mutations causing a ΔΔG≤|0.5|kcal/mol

True negative

65

35

57

64

47

False positive

15

45

23

16

33

True positive

27

50

33

25

43

False negative

52

29

46

54

36

Accuracy

0.58

0.53

0.57

0.56

0.57

True negative rate (specificity)

0.81

0.44

0.71

0.80

0.59

True positive rate (sensitivity)

0.34

0.63

0.42

0.32

0.54

Positive predictive value (precision)

0.64

0.53

0.59

0.61

0.57

Negative predictive value

0.56

0.55

0.55

0.54

0.57

MCC

0.17

0.07

0.14

0.13

0.13

  1. True negative and true positive values have been considered as those predictions that correctly predicted a negative and a positive sign for destabilizing and stabilizing mutations, respectively