Skip to main content

Table 5 Performance of the predictive models (M3 through M16), each with an individual or a combination of the newly added categories of features being excluded.

From: CpGIMethPred: computational model for predicting methylation status of CpG islands in human genome

 

Features

SP

SE

ACC

CC

Histone Methylation Retained

All retained

0.9405

0.9257

0.9313

0.8302

 

Acetylation ( M 3 )

0.9012

0.8965

0.9046

0.7852

 

Functional role ( M 4 )

0.9302

0.9265

0.9210

0.8038

 

Nucleosome ( M 5 )

0.9270

0.9250

0.9205

0.8024

 

Acetylation+Functional ( M 6 )

0.8791

0.8903

0.8897

0.7632

 

Acetylation+Nucleosome ( M 7 )

0.8698

0.8835

0.8826

0.7625

 

Functional+Nucleosome ( M 8 )

0.9186

0.9116

0.9186

0.8012

 

All three ( M 9 )

0.8685

0.8822

0.8786

0.7558

Histone Methylation Excluded

All but histone methylation

0.9318

0.5932

0.8575

0.6404

 

Acetylation ( M 10 )

0.9670

0.2247

0.8001

0.3302

 

Functional ( M 11 )

0.9092

0.5670

0.8312

0.6124

 

Nucleosome ( M 12 )

0.9078

0.5660

0.8296

0.6076

 

Acetylation+Functional ( M 13 )

0.9320

0.2279

0.7862

0.3236

 

Acetylation+Nucleosome ( M 14 )

0.9266

0.2304

0.7641

0.3264

 

Functional+Nucleosome ( M 15 )

0.8990

0.5519

0.8232

0.5924

 

All three ( M 16 )

0.8972

0.2338

0.7352

0.3013

  1. Specificity (SP), sensitivity (SE) and accuracy (ACC) are evaluated for binary classification, and correlation coefficient (CC) for regression models.