Skip to main content

Table 7 The performance of data augmentation on the SPDS17 dataset

From: SigUNet: signal peptide recognition based on semantic segmentation

CompEukaryotesGram-positiveGram-negative
TrainMCC (%)FPRTM (%)MCC (%)FPRTM (%)MCC (%)FPRTM (%)
SigUNet
 As compa89.61.240.92.197.61.1
 All organismsb89.22.246.11.6100.00.0
 Bacteriac49.51.197.61.1
SigUNet-light
 As comp84.83.751.71.692.81.1
 All organisms89.12.243.31.6100.00.0
 Bacteria49.51.1100.00.0
  1. aThe model is trained using the same organism as the comparison dataset. bThe model is trained using all organisms. cThe model is trained using all of the bacteria data. The best performance is highlighted in bold