Skip to main content

Table 7 Subcellular localization performance achieved by different classifiers. The second column specifies the cleavage site predictors that were used for determining the positions at which the amino sequences were truncated. Notice that TargetP can perform both cleavage site prediction and subcellular localization. For Rows 4 and 5, TargetP was used as a cleavage site predictor, where “TargetP(P)” and “TargetP(N)” mean selecting plant or non-plant option in TargetP, respectively. For Rows 6–8 “CRF” means that conditional random fields were used for cleavage site prediction.

From: Fast subcellular localization by cascaded fusion of signal-based and homology-based methods

Row

Cleavage Site Predictor

Localization Predictor

Classification Accuracy (%)

Matthew’s correlation coefficient (MCC)

   

Ext

Mit

Chl

Cyt/Nuc

Overall

Ext

Mit

Chl

Cyt/Nuc

Overall

1

SubLoc [7]

51.44

55.83

77.86

66.79

2

TargetP (P)

79.08

88.02

89.19

69.57

73.93

0.79

0.49

0.79

0.64

0.65

3

TargetP (N)

97.40

89.22

0.00

87.82

87.97

0.93

0.58

0.00

0.81

0.84

4

TargetP(N)

SVM

97.26

67.07

36.49

95.86

92.63

0.93

0.70

0.53

0.86

0.90

5

TargetP(N)

PDA

97.55

61.68

6.76

95.61

91.34

0.91

0.68

0.26

0.84

0.88

6

TargetP(N)

PDAproj+SVM

97.26

65.27

37.84

93.57

91.10

0.93

0.64

0.50

0.83

0.88

7

CRF

SVM

94.52

63.47

28.38

95.86

91.45

0.90

0.68

0.45

0.84

0.89

8

CRF

PDA

94.81

59.28

1.35

95.55

90.24

0.88

0.67

0.11

0.82

0.81

9

CRF

PDAproj+SVM

94.66

63.47

25.68

93.63

89.97

0.90

0.60

0.41

0.82

0.87