Skip to main content

Table 1 Comparison of gene expression prediction performance across models

From: DeepMethyGene: a deep-learning model to predict gene expression using DNA methylations

Method

Mean

Median

Std

Max

Min

P-value

SVM

0.327

0.317

0.132

0.767

 − 0.357

< 0.0001

RandomForest

0.374

0.365

0.139

0.936

 − 0.108

< 0.0001

geneEXPLORE

0.449

0.452

0.141

0.938

0.005

< 0.0001

NoConvLayer

0.360

0.358

0.205

0.932

0.001

< 0.0001

DeepMethyGene

0.640

0.641

0.133

0.957

0.165

 
  1. The table presents the predictive performance of DeepMethyGene compared to DeepMethyGene (NoConvLayer), geneEXPLORE, SVM, and Random Forest. The P-value indicates the significance level of the performance difference between each model and DeepMethyGene, calculated using Wilcoxon signed-rank test
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us