Skip to main content

Table 1 The performances of CapsNet-SSP and other methods on the training set

From: CapsNet-SSP: multilane capsule network for predicting human saliva-secretory proteins

Methods Accuracy Sensitivity Specificity Precision F-score MCC AUC
KNN 0.835 0.763 0.907 0.891 0.822 0.677 0.878
Decision Tree 0.820 0.789 0.852 0.842 0.815 0.642 0.800
Random Forest 0.810 0.752 0.867 0.850 0.798 0.623 0.879
AdaBoost 0.830 0.754 0.905 0.889 0.836 0.667 0.905
SVM 0.830 0.760 0.899 0.883 0.822 0.666 0.877
CapsNet-SSP 0.905 0.880 0.929 0.924 0.902 0.810 0.930
  1. The threshold is set where the MCC reaches the maximum value