Skip to main content

Advertisement

Springer Nature is making Coronavirus research free. View research | View latest news | Sign up for updates

Table 1 Performance of the proposed models

From: Deep neural networks for human microRNA precursor detection

Model (Data set partition)Sen.(%)Spe.(%)F1(%)MCC(%)Acc.(%)
CNN (Training/Evalu./Test)88.8388.2888.8377.1188.56
CNN (10-fold CV)89.58 ± 4.7284.90 ± 4.8487.53 ± 1.3874.72 ± 3.5287.24 ± 1.80
RNN (Training/Evalu./Test)85.7191.2888.3577.0388.43
RNN (10-fold CV)85.89 ± 3.2991.14 ± 2.7588.09 ± 2.0377.04 ± 3.6688.44 ± 1.80
  1. Note: Classification performance of different models on the testing dataset was shown as sensitivity (column 2), specificity (column 3), F1-Score (column 4), MCC (column 5) and accuracy (column 6) respectively. For the 10-fold CV, the performance was shown as mean ± standard error