Skip to main content

Table 3 Prediction power of the selected SVM model

From: Predicting substrates of the human breast cancer resistance protein using a support vector machine method

  TP FN TN FP ACC SE SP MCC
Training set 89 15 38 25 76.0 85.6 60.3 0.478
Test set 31 4 11 10 75.0 88.6 52.4 0.448
External set 19 6 10 5 72.5 76.0 66.7 0.422
  1. TP, true positive; TN, true negative; FP, false positive; FN, false negative; ACC, accuracy (overall prediction accuracy); SP, specificity (prediction accuracy for the non-substrates); SE, sensitivity (prediction accuracy for the substrates); MCC, the Matthews correlation coefficient (a more balanced prediction parameter than ACC).