Skip to main content

Table 6 The five datasets used to evaluate the rules parsed from the InterPro database.

From: Association algorithm to mine the rules that govern enzyme definition and to classify protein sequences

 

the parsed rules#

 

precision

Confidence

coverage*

A testing data

52%

48%

23%

B testing data

51%

50%

24%

C testing data

56%

52%

26%

D testing data

47%

41%

20%

E testing data

64%

62%

47%

  1. A: actinobacteria B: bacillales C: fungi D: nematode + arthropoda E: viridiplantae
  2. *: coverage = the hit ratio of testing data
  3. #: The dataset was parsed from the entry xref table of the InterPro database. The IPR Acc's were corresponding to ENZYME.