Skip to main content

Table 10 Comparison of the proposed system with existing nine prediction systems in terms of Threonine site prediction in the Independent dataset.

From: Machine learning approach to predict protein phosphorylation sites by incorporating evolutionary information

Systems

Category

Performance parameters of the systems

  

Ac(%)

Sn(%)

Sp(%)

Mcc

FPR(%)

KinasePhos [11]

 

95.06

5.88

95.77

0.01

4.23

NetPhosK [10]

Kinase Specific

86.39

16.47

86.94

0.01

13.06

PPSP [6]

 

82.80

16.47

83.32

-0.00

16.68

GPS [15]

 

82.85

16.47

83.38

-0.00

16.62

AutoMotif Server AMS [14]

 

40.35

62.35

40.17

0.00

59.83

DISPHOS [8]

 

93.92

7.06

94.61

0.01

5.39

NetPhos [13]

 

82.19

22.35

82.66

0.01

17.34

PHOSIDA [5]

Kinase Independent

97.15

1.18

97.91

-0.01

2.09

Scansite [12]

 

98.93

0.00

99.71

-0.00

0.29

PPRED (Proposed system)

 

69.87

67.06

69.90

0.07

30.10