Skip to main content

Table 2 Accuracies of predicting MOA’s in the originally given test set, based on classifiers developed on common gene expression sets profiled from microarray and RNASeq platforms

From: Inter-platform concordance of gene expression data for the prediction of chemical mode of action

Platform Classifier Overall Acc. % Sensitivity, Specificity    
    PPARA CAR/PXR Control OTHER
Microarray Ensemble 50 44,52 44,52 100,42 39,58
  SVM 55 0,70 0,70 83,50 100,21
  RF 57 0,73 0,73 100,50 100,25
  PLS+LDA 40 67,33 56,36 67,36 6,67
  PLS+RF 55 11,67 11,67 100,48 83,34
  PCA+LDA 12 0,15 0,15 83,0 0,21
  PCA+RF 40 0,51 0,51 94,31 0,70
  RPART 45 100,30 0,57 83,39 28,58
RNASeq Ensemble 50 33,55 33,55 100,42 50,50
  SVM 60 0,76 11,73 100,53 100,30
  RF 55 0,70 0,70 100,48 94,26
  PLS+LDA 38 56,33 56,33 100,28 0,66
  PLS+RF 55 11,67 22,64 100,48 78,38
  PCA+LDA 14 0,18 0,18 100,0 0,24
  PCA+RF 43 0,55 0,55 83,36 72,21
  RPART 43 33,46 33,46 33,45 56,33