Skip to main content

Table 2 Attributes of the PPIs used in the SVM-based method. a

From: Assessing the druggability of protein-protein interactions by a supervised machine-learning method

No.

Attribute

 

Structural information

1

   Pocket volume

2

   Accessible surface area of pocket

3

   Percentage of accessible surface area of pocket to that of total surface of protein

4

   Pocket compactness

5

   Pocket planarity

6

   d 1 +d 2

7

   Pocket narrowness

8

   d 4 +d 5

9

   Ratio of Ala frequency on pocket surface to that on total surface b

10

   Ratio of Cys frequency on pocket surface to that on total surface b

11

   Ratio of Asp frequency on pocket surface to that on total surface b

12

   Ratio of Glu frequency on pocket surface to that on total surface b

13

   Ratio of Phe frequency on pocket surface to that on total surface b

14

   Ratio of Gly frequency on pocket surface to that on total surface b

15

   Ratio of His frequency on pocket surface to that on total surface b

16

   Ratio of Ile frequency on pocket surface to that on total surface b

17

   Ratio of Lys frequency on pocket surface to that on total surface b

18

   Ratio of Leu frequency on pocket surface to that on total surface b

19

   Ratio of Met frequency on pocket surface to that on total surface b

20

   Ratio of Asn frequency on pocket surface to that on total surface b

21

   Ratio of Pro frequency on pocket surface to that on total surface b

22

   Ratio of Gln frequency on pocket surface to that on total surface b

23

   Ratio of Arg frequency on pocket surface to that on total surface b

24

   Ratio of Ser frequency on pocket surface to that on total surface b

25

   Ratio of Thr frequency on pocket surface to that on total surface b

26

   Ratio of Val frequency on pocket surface to that on total surface b

27

   Ratio of Trp frequency on pocket surface to that on total surface b

28

   Ratio of Tyr frequency on pocket surface to that on total surface b

 

Drug and chemical information

29

   Number of small chemical drugs (L) d

30

   Number of small chemical drugs (S) e

31

   Number of biotech drugs (L) d

32

   Number of biotech drugs (S) e

33

   Number of approved drugs (L) d

34

   Number of approved drugs (S) e

35

   Number of experimental drugs (L) d

36

   Number of experimental drugs (S) e

37

   Number of investigational drugs (L) d

38

   Number of investigational drugs (S) e

39

   Number of nutraceutical drugs (L) d

40

   Number of nutraceutical drugs (S) e

41

   Number of withdrawn drugs (L) d

42

   Number of withdrawn drugs (S) e

43

   Number of illicit drugs (L) d

44

   Number of illicit drugs (S) e

 

Functional information

45

   Both proteins are related to OMIM-registered diseases (1) or not (0)

46

   Number of interacting proteins (L) d

47

   Number of interacting proteins (S) e

48

   Number of biological pathways in which either protein is involved (L) d

49

   Number of biological pathways in which either protein is involved (S) e

50

   Number of biological pathways in which both interacting proteins are involved

51

   Identity scores of the GO terms in the Cellular Component category

52

   Identity scores of the GO terms in the Molecular Function category

53

   Identity scores of the GO terms in the Biological Process category

54

   Number of paralogs in the KEGG (L) d

55

   Number of paralogs in the KEGG (S) e

56

   Number of paralogs in the PIRSF (L) d

57

   Number of paralogs in the PIRSF (S) e

58

   Number of gene-expressing health states (L) d

59

   Number of gene-expressing health states (S) e

60

   Number of health states in which both genes are expressed

61

   Number of gene-expressing body sites (L) d

62

   Number of gene-expressing body sites (S) e

63

   Number of body sites in which both genes are expressed

64

   Number of gene-expressing developmental stages (L) d

65

   Number of gene-expressing developmental stages (S) e

66

   Number of developmental stages in which both genes are expressed

67

   Similarity scores of gene expression profiles in the Health State category

68

   Similarity scores of gene expression profiles in the Body Sites category

69

   Similarity scores of gene expression profiles in the Developmental Stage category

  1. aFor details of the definitions and calculation methods, see Additional file 4: Supplementary Methods.
  2. bAbbreviations: Ala, alanine; Cys, cysteine; Asp, aspartic acid; Glu, glutamic acid; Phe, phenylalanine; Gly, glycine; His, histidine; Ile, isoleucine; Lys, lysine; Leu, leucine; Met, methionine; Asn, asparagine; Pro, proline; Gln, glutamine; Arg, arginine; Ser, serine; Thr, threonine; Val, valine; Trp, tryptophan; Tyr, tyrosine.
  3. dDefined as the larger one of the two numbers for the two interacting proteins in a PPI.
  4. eDefined as the smaller one of the two numbers for the two interacting proteins in a PPI.