Skip to main content

Table 2 The number of functional class whose F 1 = NaN for four algorithms and four functional groups

From: Predicting gene function using few positive examples and unlabeled ones

algorithms

< 60

60-100

100-300

> 300

twoclass

31

8

3

1

twoclassbal

0

0

0

0

PSoL

22

6

0

1

SPE-RNE

0

0

0

0

  1. When the number of negative examples is far more than positive examples, imbalanced problem occurs and the algorithm can not recall any true positive examples for some functional classes. As a result, P = 0 and R = 0 result in F 1 = NaN (Not a Number) in matlab. Table 2 shows the number of NaN for each functional group.