Skip to main content

Table 3 Classification results for the score matrices with SLiMs obtained from CM using 3-fold cross validation

From: The predictive performance of short-linear motif features in the prediction of calmodulin-binding proteins

Dataset for classification # features Classifier Accuracy (%) MCC ROC Area
S score matrix   SVM-Polynomial (c=1,g=0) 72.6 0.45 0.73
  100 RF 74.7 0.49 0.74
   k-NN (k=1) 78.3 0.57 0.78
T score matrix   SVM-Polynomial (c=1,g=0) 57.6 0.21 0.58
  100 RF 69.3 0.40 0.77
   k-NN (k=1) 58.1 0.26 0.58