Skip to main content

Table 1 The mean values of SVM prediction performance parameters of 100 runs using various kernels

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

Kernel Category ACC SE SP MCC
Linear Training 80.7 90.4 64.8 0.581
  Test 68.8 82.1 46.6 0.312
  External 70.7 77.6 59.1 0.375
Polynomial Training 79.2 96.4 50.7 0.506
  Test 65.8 86.8 30.8 0.198
  External 66.1 81.9 39.8 0.174
RBF Training 84.5 93.8 69.1 0.665
  Test 69.7 83.3 47.2 0.332
  External 70.9 77.7 59.6 0.382
  1. 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). The external data set was only used to validate the prediction power of the models constructed, and was not used for model selection.