Skip to main content

Table 4 Performance comparison of deep learning architectures

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

Architectures Accuracy Sensitivity Specificity Precision F-score MCC AUC
DeepSig 0.792 (0.011) 0.745 (0.030) 0.838 (0.009) 0.820 (0.016) 0.781 (7.8e-04) 0.586 (0.011) 0.867 (5.8e-07)
DanQ 0.802 (1.4e-05) 0.745 1.8e-05) 0.859 (3.5e-05) 0.839 (3.3e-05) 0.789 (2.2e-05) 0.608 (1.8e-05) 0.886 (6.3e-06)
DeepLoc 0.843 (0.013) 0.755 (0.029) 0.929 (0.037) 0.914 (0.038) 0.827 (0.016) 0.695 (0.013) 0.891 (0.015)
CapsNet-SSP 0.888
(N/A)
0.847
(N/A)
0.929
(N/A)
0.922
(N/A)
0.884
(N/A)
0.779
(N/A)
0.948
(N/A)
  1. The threshold is set where the MCC reaches the maximum value, and the values in brackets are p-values