Skip to main content

Table 2 Statistics about the comparative performance of the base k-NN classifiers and their label similarity-incorporated versions, measured in terms of the number of classes for which AUC scores are improved by the latter over the former, and the average and maximum improvement in AUC scores over all classes.

From: Incorporating functional inter-relationships into protein function prediction algorithms

Dataset

Total # classes

# Classes improved

Average improvement over all classes

Maximum improvement

Mnaimneh

137

74

0.0219 (3.57%)

0.1882 (39.92%)

Rosetta

137

47

0.0083 (1.33%)

0.2091 (38.66%)

Krogan

108

30

0.0045 (0.63%)

0.1982 (31.82%)

Combined

136

59

0.0079 (1.02%)

0.1129 (20.39%)