Skip to main content

Table 3 Average recovery rates

From: Statistical-based database fingerprint: chemical space dependent representation of compound databases

Dataset

MACCS keys (166-bit)

ECFP4 (2048-bit)

1-NN

DFP

SB-DFP

1-NN

DFP

SB-DFP

BRD2

43.7 (5.0)

29.9 (13.7)

13.8 (12.8)

75.4 (5.2)

28.4 (24.2)

68.0 (7.1)

BRD3

43.5 (4.8)

32.0 (12.3)

10.6 (11.3)

74.4 (5.7)

31.9 (23.8)

68.7 (7.1)

BRD4

30.0 (5.4)

7.6 (7.7)

4.5 (4.3)

54.1 (6.2)

2.7 (4.7)

52.6 (8.1)

CREBBP

52.7 (4.7)

45.5 (7.8)

16.5 (16.2)

79.0 (5.4)

55.6 (25.0)

73.7 (4.2)

DNMT1

9.9 (5.2)

0.5 (1.5)

3.8 (3.9)

12.9 (5.7)

0.0 (0.0)

17.7 (7.1)

EHMT2

66.3 (7.1)

40.9 (12.6)

28.1 (17.8)

80.1 (8.0)

40.2 (23.5)

78.4 (8.3)

EP300

34.6 (7.5)

5.5 (5.8)

1.4 (2.7)

50.2 (7.7)

0.7 (2.8)

37.0 (10.8)

HDAC10

37.1 (8.6)

34.2 (15.1)

52.2 (11.1)

36.5 (8.0)

15.4 (12.3)

51.1 (9.5)

HDAC11

34.7 (8.3)

22.5 (12.4)

43.7 (12.1)

39.6 (8.8)

6.6 (6.4)

49.3 (11.3)

HDAC1

18.2 (6.1)

15.8 (13.5)

53.7 (6.3)

30.9 (6.7)

6.3 (5.1)

51.1 (9.0)

HDAC2

20.9 (7.0)

20.1 (16.1)

54.8 (6.9)

31.3 (6.5)

9.1 (6.0)

44.7 (10.6)

HDAC3

27.5 (8.7)

27.3 (13.1)

60.2 (8.1)

32.0 (6.2)

10.4 (6.6)

45.4 (9.6)

HDAC4

19.2 (4.7)

9.1 (7.3)

29.6 (11.0)

44.9 (6.2)

7.9 (11.2)

45.8 (7.0)

HDAC5

20.7 (9.6)

30.2 (12.1)

67.6 (4.4)

23.1 (6.4)

10.0 (4.3)

32.0 (12.1)

HDAC6

22.8 (6.7)

32.0 (15.1)

64.5 (4.3)

25.7 (5.8)

9.3 (9.1)

44.6 (9.0)

HDAC7

25.6 (8.4)

36.6 (11.7)

77.6 (4.5)

28.4 (6.7)

11.0 (4.9)

38.6 (10.4)

HDAC8

27.4 (7.0)

33.9 (11.9)

71.5 (9.5)

29.6 (6.9)

9.5 (3.9)

46.2 (9.8)

HDAC9

25.4 (9.0)

34.9 (11.9)

73.9 (9.7)

27.7 (7.5)

9.6 (8.7)

38.4 (13.0)

KAT2B

55.3 (12.7)

41.0 (8.7)

37.6 (13.5)

61.8 (10.8)

35.3 (14.1)

60.4 (9.4)

KDM1A

24.6 (5.1)

13.3 (8.0)

6.8 (5.6)

53.3 (8.4)

18.3 (15.1)

58.4 (10.0)

KDM4C

12.2 (5.1)

0.4 (1.0)

11.5 (8.7)

18.9 (6.4)

0.1 (0.3)

17.1 (5.8)

L3MBTL1

62.2 (8.5)

68.8 (4.6)

66.0 (11.1)

91.1 (4.6)

94.5 (1.8)

95.5 (2.3)

L3MBTL3

59.5 (8.5)

49.7 (4.2)

37.4 (11.2)

82.8 (6.6)

71.1 (4.5)

81.1 (6.8)

MAP3K7

41.2 (6.0)

19.8 (14.3)

2.2 (3.1)

56.6 (5.2)

31.1 (23.8)

58.0 (4.0)

MGEA5

58.5 (25.6)

84.8 (4.9)

84.6 (1.7)

86.3 (3.5)

86.4 (2.0)

87.6 (2.2)

NCOA1

2.7 (2.1)

0.0 (0.2)

5.7 (5.1)

5.5 (3.3)

0.1 (0.3)

5.5 (3.4)

NCOA3

1.1 (0.9)

0.1 (0.2)

4.9 (4.5)

2.6 (1.4)

0.1 (0.3)

4.1 (2.5)

PRMT1

48.8 (8.7)

2.8 (5.7)

2.7 (4.3)

52.8 (10.5)

1.0 (3.8)

55.3 (12.1)

Average

33.1 (19.6)

26.4 (22.8)

35.3 (29.1)

46.0 (25.9)

21.5 (28.4)

50.2 (23.8)

  1. The best performing methods for each dataset are shown in bold. If there were no significative difference between two or more methods, all of them are marked. Standard deviations are shown in parentheses