Skip to main content

Table 1 Effectivenss of clustering of high diverse MDDR dataset: ALOGP Fingerprint.

From: Using graph-based consensus clustering for combining K-means clustering of heterogeneous chemical structures

Clustering Method

No. of clusters

   

500

600

700

800

900

1000

Consensus (HGPA)

 

N = 5

48.06

52.87

55.80

57.97

60.71

62.70

  

N = 10

49.78

54.29

58.22

59.15

61.46

64.09

  

N = 15

50.59

55.20

58.17

59.86

61.73

63.52

  

N = 20

50.73

54.35

57.85

60.05

61.85

63.97

  

N = 25

50.58

54.43

57.20

59.65

61.81

64.16

  

N = 30

51.67

54.09

59.26

59.53

60.81

63.82

  

N = 35

51.89

54.99

57.82

60.80

63.14

64.01

  

N = 40

51.66

54.71

57.69

60.39

61.68

62.87

  

N = 45

51.57

54.86

57.85

60.12

62.03

63.98

  

N = 50

52.44

54.52

57.48

60.44

62.71

63.50

Individual

Wards' Method

 

39.01

41.83

44.49

46.03

47.89

49.45