Skip to main content

Table 3 Performance of methylation status prediction using different classifiers

From: Predicting genome-wide DNA methylation using methylation marks, genomic position, and DNA regulatory elements

Classifier

Accuracy (%)

AUC

Specificity (%)

Sensitivity (%)

MCC

k-NN

73.2

0.80

72.6

73.7

0.46

Naive Bayes

80.8

0.91

64.4

94.2

0.62

Logistic regression

91.1

0.96

87.3

94.1

0.82

SVM

91.3

0.96

86.6

95.1

0.82

Random forest

91.8

0.96

87.9

95.1

0.84

  1. AUC, area under the receiver operating characteristic curve; k-NN, k-nearest neighbors classifier; MCC, Matthew’s correlation coefficient; SVM, support vector machine.