Skip to main content

Table 2 Performance of esRF models in an independent testing dataset

From: Prediction of unconventional protein secretion by exosomes

 

Dataset translation

PCP

AA

PCP + AA

DP

PCP + AA + DP

ACC (%)

68.99

71.49

71.41

75.73

75.54

AUC

0.765

0.793

0.795

0.840

0.839

MCC

0.378

0.424

0.422

0.505

0.503

  1. Table reports the accuracy (ACC %), area under the curve (AUC) and Matthews correlation coefficient (MCC) reached in the independent dataset by the top performing esRF model obtained by training in sequence features consisting of physico-chemical properties (PCP), amino acid composition (AA), combination of global properties and amino acid composition (PCP + AA), dipeptide composition (DP) and all of them (PCP + AA + DP)
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us