Skip to main content

Table 3 10-fold cross validation results from NU-ResNet and NUMO-ResNet

From: Predicting RNA sequence-structure likelihood via structure-aware deep learning

Metric

NU-ResNet

NUMO-ResNet

 

\(\varvec{\vartheta }^{*}_{a}\)

\(\varvec{\vartheta }^{*}_{\ell }\)

\(\varvec{\vartheta }^{*}_{a}\)

\(\varvec{\vartheta }^{*}_{\ell }\)

Accuracy

98.13 %

97.19%

95.47%

93.44%

AUCROC

0.9939

0.9948

0.9749

0.9768

MCC

0.9629

0.9444

0.9111

0.8702

Precision

98.16%

97.54%

96.91%

93.48%

Recall

98.13%

96.88%

94.06%

93.75%

Specificity

98.13%

97.5%

96.88%

93.13%

  1. Models with parameters that optimize the validation accuracy are referred to as \(\varvec{\vartheta }^{*}_{a}\), while models with parameters that optimize validation loss are referred to as \(\varvec{\vartheta }^{*}_{\ell }\)
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us