Skip to main content

Table 3 Accuracies of predicting MOA’s in the adjusted test set, based on classifiers developed on complete 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
Microarray Ensemble 62 56,66 44,73 100,49
  SVM 50 33,60 44,54 83,39
  RF 67 89,54 22,94 100,56
  PLS+LDA 67 67,67 44,81 100,56
  PLS+RF 54 44,60 33,67 100,39
  PCA+LDA 12 33,0 0,20 0,17
  PCA+RF 8 22,0 0,13 0,11
  RPART 62 100,39 11,93 83,55
RNASeq Ensemble 62 56,66 44,73 100,49
  SVM 54 44,60 33,67 100,39
  RF 62 78,52 22,86 100,49
  PLS+LDA 58 44,66 44,66 100,44
  PLS+RF 50 44,54 22,67 100,33
  PCA+LDA 33 33,33 0,53 83,16
  PCA+RF 25 22,27 0,40 67,11
  RPART 42 44,41 22,54 67,34