Skip to main content

Table 2 The performance on the Eukaryotes datasets

From: SigUNet: signal peptide recognition based on semantic segmentation

MethodMCC (%)FPRTM (%)Precision (%)Recall (%)F1 measure (%)
The SignalP dataset
 Phobius81.115.377.695.285.5
 PrediSi56.152.652.091.366.3
 SignalP3.0-HMM75.923.569.597.481.1
 SignalP3.0-NN56.264.148.498.865.0
 PolyPhobius80.612.579.591.985.2
 Philius80.413.477.893.785.0
 SPOCTOPUS80.114.079.091.784.9
 SignalP 4.087.46.1
 TOPCONS284.69.683.693.688.3
 DeepSig87.24.292.587.890.1
 SigUNet90.24.093.092.192.5
The SPDS17 dataset
 Phobius65.89.647.895.763.8
 PrediSi38.543.320.789.133.6
 SignalP3.0-HMM51.622.331.295.747.1
 SignalP3.0-NN36.059.117.595.729.5
 PolyPhobius72.08.056.495.771.0
 Philius62.36.544.393.560.1
 SPOCTOPUS54.016.437.984.852.3
 SignalP 4.081.94.075.091.382.3
 TOPCONS273.95.660.693.573.5
 DeepSig86.12.582.491.386.6
 SigUNet89.61.291.189.190.1
  1. The performances of Phoibus, PrediSi and SignalP 3.0 are obtained from their online services (Phobius: http://phobius.sbc.su.se/; PrediSi: http://www.predisi.de/predisi/; SignalP 3.0: http://www.cbs.dtu.dk/services/SignalP-3.0/) [11, 23, 24]. The performances of PolyPhobius, Philius, SPOCTOPUS and TOPCONS2 are obtained from the TOPCONS2 software (https://github.com/ElofssonLab/TOPCONS2) [25,26,27,28]. The performance of SignalP 4.0 on the SignalP dataset is obtained from the original paper [12] and the performance on the SPDS17 dataset is obtained from its online service (http://www.cbs.dtu.dk/services/SignalP-4.0/). The performance of DeepSig on the SignalP dataset is obtained by reproducing the algorithm and the performance on the SPDS17 dataset is obtained using the source code (https://github.com/BolognaBiocomp/deepsig). For each dataset, the best performance is highlighted in bold.