Skip to main content

Table 3 Multi-class remote fold recognition using the triple(1,3) kernel

From: Efficient use of unlabeled data for protein sequence classification: a comparative study

Method

Error

Top-5 Error

Balanced Error

Top-5 Balanced Error

F1

Top-5 F1

full sequence

50.81

17.92

71.95

27.80

28.92

73.93

region

36.81

10.91

52.58

20.07

49.69

81.26

no tails (full seq.)

48.21

19.71

70.42

33.37

30.91

73.39

max. length (full seq.)

51.63

23.13

76.96

39.21

26.85

66.99