Skip to main content

Table 3 The performance on the Gram-positive datasets

From: SigUNet: signal peptide recognition based on semantic segmentation

MethodMCC (%)FPRTM (%)Precision (%)Recall (%)F1 measure (%)
The SignalP dataset
 Phobius67.720.560.087.571.2
 PrediSi40.954.735.075.047.7
 SignalP3.0-HMM55.843.644.389.659.3
 SignalP3.0-NN47.256.434.991.750.6
 PolyPhobius71.116.266.185.474.5
 Philius69.615.464.185.473.2
 SPOCTOPUS73.915.467.289.676.8
 SignalP 4.085.12.6
 TOPCONS281.66.880.887.584.0
 DeepSig73.96.881.472.976.9
 SigUNet76.15.185.472.978.7
The SPDS17 dataset
 Phobius35.013.617.977.829.2
 PrediSi14.364.05.077.89.5
 SignalP3.0-HMM27.327.011.977.820.6
 SignalP3.0-NN16.145.55.777.810.7
 PolyPhobius34.513.217.577.828.6
 Philius30.379.016.266.726.1
 SPOCTOPUS30.313.816.266.726.1
 SignalP 4.050.30.040.066.750.0
 TOPCONS238.14.224.066.735.3
 DeepSig54.50.146.266.754.4
 SigUNet40.92.140.044.442.1
  1. The best performance is highlighted in bold