Table 1

Classifier performance measures for prediction of morbid and druggable genes

Prediction of morbid genes


Performance measure

Median [min,max] 1

Median [min,max] 1

N

W

Wc (two-tailed p = 0.05)2


Normal

Shuffled


Precision

0.658 [0.648,0.679]

0.495 [0.473,0.522]

10

0

8 *

Recall

0.648 [0.632,0.657]

0.502 [0.471,0.521]

10

0

8 *

AUC

0.716 [0.706,0.729]

0.498 [0.462,0.526]

10

0

8 *


Prediction of druggable genes


Performance measure

Median [min,max] 1

Median [min,max] 1

N

W

Wc (two-tailed p = 0.05)2


Normal

Shuffled


Precision

0.748 [0.72,0.763]

0.5 [0.451,0.556]

10

0

8 *

Recall

0.782 [0.732,0.809]

0.492 [0.447,0.564]

10

0

8 *

AUC

0.820 [0.801,0.835]

0.500 [0.43,0.546]

10

0

8 *


1 Of 10 datasets

2 According to table of critical values for W in [6]

* Difference statistically significant

Costa et al. BMC Genomics 2010 11(Suppl 5):S9   doi:10.1186/1471-2164-11-S5-S9

Open Data