Table 3

Accuracy of different cleavage prediction models developed on cattle neuropeptides

Cleavage Prediction Model

AA1

AA-Prop2

Model Accuracy Statistic

LR3

ANT4

LR

ANT


True Negative

669

691

667

690

True Positive

44

43

50

46

False Negative

41

42

35

39

False Positive

77

55

79

56

Correct Classification Rate (%)

86

88

86

89

Sensitivity (%)

52

51

59

54

Specificity (%)

90

93

89

92

Area under receiver operating characteristic curve (%)

76

76

82

78


1AA = Models developed using only amino acids

2 AA-Prop = Models developed using amino acids plus amino acid physiochemical properties

3LR = Models developed using logistic regression

4 ANT = Models developed using artificial neural networks

Southey et al. BMC Genomics 2009 10:228   doi:10.1186/1471-2164-10-228

Open Data