BioMed Research International / 2011 / Article / Tab 2

Research Article

Prediction of B-cell Linear Epitopes with a Combination of Support Vector Machine Classification and Amino Acid Propensity Identification

Table 2

Comparison of the performances of LEPS, BepiPred, ABCPred, BCPred, and FBCPred systems.

SystemsSENaSPEaACCaPPVaMCCa

PC dataset

LEPS12.7888.3361.6645.123.65
BepiPred48.2359.7255.3338.197.49
A B C P r e d 0 . 8 b 65.4640.2648.8936.215.13
BCPred50.9259.3552.8336.074.43
FBCPred51.0352.5552.2035.263.17

AntiJen dataset

LEPS26.7284.4873.8128.8510.10
BepiPred51.7957.6155.5222.026.04
ABCPred0.867.3340.4044.7021.835.46
BCPred58.8454.8753.9223.348.93
FBCPred60.3151.2151.4522.336.73

HIV dataset

LEPS48.3374.8463.4571.4422.76
BepiPred50.1660.8556.7261.229.72
ABCPred0.787.9714.6556.5956.335.64
BCPred80.1854.5766.5765.5529.80
FBCPred73.2058.2067.1365.5627.81

AHP datasetc

LEPS26.9784.2272.5232.0710.36
BepiPred51.4857.9155.5725.066.32
ABCPred0.868.2839.0645.5824.515.45
BCPred59.4554.8054.5026.329.73
FBCPred60.4051.6652.3125.387.60

aSEN: sensitivity; SPE: specificity; PPV: positive prediction value; ACC: accuracy; MCC: Matthews’ correlation coefficient, unit, %.
bThe subscripts of ABCPred denote threshold values according to the highest accuracy.
cThis dataset is a merge of the other 3 datasets.

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.