Skip to main content

Table 1 Statistics of the datasets that are used in this study

From: SigUNet: signal peptide recognition based on semantic segmentation

OrganismSignal PeptidesTransmembraneCytosolic or NuclearTotal
TrainCompTrainCompTrainComp
SignalP
 Eukaryotes1640606987939513310007760
 Gram-positive20848117117360213685
 Gram-negative4231045235239122601858
SPDS17
 Eukaryotes463236891058
 Gram-positive9189240438
 Gram-negative238999211
  1. The SignalP dataset is from the UniProtKB/Swiss-Prot in accordance with the identity list in Pertersen et al.’s study [12]; The SPDS17 dataset is from the UniProtKB/Swiss-Prot in accordance with the identity list in Savojardo et al.’s study [6].