Skip to main content

Table 6 Prediction performance (AUC) of MS-SPCA

From: Phenotype prediction based on genome-wide DNA methylation data

 

Normal

Normal HPV+

Normal HPV-

CIN2+(a)

CIN2+(b)

Cancer

Normal

   

0.93/0.66(0.87)

0.81/0.55(0.69)

1/0.81(0.94)

Normal HPV+

  

0.52/0.45

0.93/0.77

0.84/0.65

1/0.75

Normal HPV-

 

0.61/0.55

 

0.92/0.68

0.64/0.46

1/0.71

CIN2+(a)

0.60/0.57

0.63/0.60

0.53/0.54

 

0.83/0.71

1/0.72

CIN2+(b)

0.58/0.56

0.62/0.60

0.53/0.46

0.87/0.82(0.87)

 

0.98/0.85(1)

  1. Rows correspond to training data and columns to test data. The first number shows the performance of MS-SPCA, the second the performance of EVORA (mean value of 8 runs). Numbers in brackets show the five EVORA results as presented in [10]. Bold numbers show best predictions.