Skip to main content

Table 1 VaxiJen models validation.

From: VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines

model validation AUCROCa threshold b accuracy%c sensitivity%d specificity%e
  LOO-CV 0.883 0.5 80 79 81
bacterial test set 0.726 0.5 70 76 64
  LOO-CV (mean)g 0.899 0.5 83 81 85
  LOO-CV 0.937 0.5 87 91 82
viral test set 0.743 0.4 70 84 56
  LOO-CV (mean)g 0.810 0.5 73 74 71
  LOO-CV 0.964 0.5 89 94 84
tumour test set 0.930 0.5 86 96 76
  LOO-CV (mean)g 0.911 0.5 82 78 86
  1. aThe area under the curve (AUC ROC ) is a quantitative measure of the predictive ability and varies from 0.5 for a random prediction to 1.0 for a perfect prediction.
  2. bThe threshold of the highest accuracy.
  3. cAccuracy = (true antigens + true non-antigens)/total.
  4. dSensitivity = true antigens/all antigens.
  5. eSpecificity = true non-antigens/all non-antigens.
  6. gMean values of five training sets.