Table 1 Comparison with other bioinformatics tools.

From: MatureP: prediction of secreted proteins with exclusive information from their mature regions

Bioinformatics tool

Performance (%)

Train set

Test set¹

Experimental data²

SignalP 4.07

99.61

99.27

51.64

LipoP8

99.83

99.71

61.39

Phobius46

98.78

98.72

72.08

PRED-TAT10

99.66

99.61

62.07

Classifier

 Preprotein (#P1)

97.19

95.51

97.96

 MatureP (#M22)

91.46

91.24

85.10

 Disorder (#M7)

84.73

84.18

85.86

  1. We measured the performance of four bioinformatics tools: SignalP 4.0 LipoP, Phobius and PRED-TAT on the training, testing and experimental datasets. We used the AUC as a performance metric35. AUC depicts relative trade-offs between true positive (benefits) and false positive (costs) and represents the performance of the average classifier (over different classifiers which assume different miss-classification cost ratios).
  2. ¹Randomly selected samples (20% of the total sample set; Table S1) which remained unused during the training of the classifiers.
  3. ²Experimental data manually collected from the literature (Table S4).
Back to article page