Skip to main content

Table 6 Ranking of the top 40 features for the simultaneously possible and mutually exclusive classes based on their Wilcoxon ranked sum test P-values.

From: Prediction of protein interaction types based on sequence and network features

Rank

Feature name

Mean SP

Mean ME

P-value

Rank

Feature name

Mean SP

Mean ME

P-value

1

Degree

36.6

86.9

2.8e-106

21

42

0.00631

0.0108

8.2e-45

2

57

0.00207

0.00584

2.5e-95

22

16

0.0657

0.0502

1.2e-44

3

43

0.00486

0.0104

9.8e-86

23

47

0.00333

0.00622

2.7e-44

4

45

0.006

0.0113

5.2e-82

24

10

0.00372

0.00619

1.5e-43

5

50

0.00407

0.00853

3.6e-81

25

36

0.00772

0.0125

1.3e-41

6

13

0.0895

0.0552

9.5e-79

26

65

0.00099

0.00263

7.6e-38

7

3

0.0556

0.0363

1.2e-76

27

32

0.0145

0.0206

1.4e-31

8

58

0.00211

0.00563

1.4e-76

28

66

0.00116

0.00263

5.9e-29

9

15

0.0871

0.0558

3.8e-76

29

34

0.00912

0.0136

1.7e-26

10

64

0.00076

0.00315

3.9e-74

30

38

0.00576

0.00866

3.4e-26

11

33

0.00999

0.0166

2.1e-66

31

55

0.00267

0.00481

2.3e-23

12

48

0.00309

0.00716

3.7e-66

32

23

0.0152

0.0197

1.1e-22

13

54

0.0033

0.00707

3.7e-65

33

61

0.00211

0.00397

6e-22

14

22

0.0491

0.0344

2.8e-63

34

40

0.00921

0.0133

9e-21

15

60

0.00176

0.00444

9.9e-61

35

59

0.00186

0.003

9.8e-21

16

56

0.00187

0.0048

7.1e-58

36

7

0.0117

0.0144

5.6e-20

17

6

0.00608

0.00917

9e-53

37

62

0.00172

0.0029

2.1e-19

18

44

0.00651

0.0107

2.4e-50

38

67

0.00076

0.00156

1.1e-17

19

1

0.0265

0.0199

3.4e-48

39

14

0.0474

0.039

2.4e-17

20

53

0.0044

0.00793

2.3e-46

40

46

0.00712

0.00968

2.2e-16

  1. The numbers in the name column refer to EGDV values for orbits (see Table 4). For the number of disordered binding regions, fraction of disordered amino acids, and ELM both values for protein A and B are combined into one distribution which has two values for each interaction. The Wilcoxon P-value is then calculated for this distribution.