Skip to main content

Table 2 Average Precision for different data sets.

From: Application of kernel functions for accurate similarity search in large chemical databases

dataset

G-hash

WA

C-tree

Fingerprint

gIndex

PDE5

95.48

83.16

31.20

53.02

96.00*

CDK2

79.87

73.81

51.82

57.23

87.81*

COX2

92.40*

75.88

54.85

51.62

82.00

FXa

96.93*

95.78

29.36

52.80

93.23

AIA

96

98.93

36

64.61

99.00*

AChE

77

66.46

62.63

27.80

79.62*

ALF

77.38

72.14

32.59

55.61

82.88*

EGF-R

88.62

72.75

55.41

52.42

96.40*

HIV-P

83.64

56.9

40.81

46.99

95.22*

HSP90

85.66

58.19

48.72

76.57

93.00*

MAPK

84.01

66.31

53.25

44.40

95.79*

HIV-RT

80.93

69.38

54.11

54.20

84.61*

  1. Asterisk (*) denotes the best precision for the data sets among G-hash, WA, C-tree, Daylight fingerprint and gIndex methods.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us