Skip to main content

Table 1 Accuracies of predicting MOA’s in the adjusted test set, based on classifiers developed on 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 75 89,67 44,94 100,67
  SVM 58 56,59 33,73 100,44
  RF 67 89,54 22,94 100,56
  PLS+LDA 71 67,73 56,80 100,61
  PLS+RF 58 44,68 44,68 100,45
  PCA+LDA 17 0,27 0,27 67,0
  PCA+RF 33 33,33 0,53 83,16
  RPART 62 100,39 11,93 83,55
RNASeq Ensemble 67 56,74 56,74 100,56
  SVM 58 67,54 22,81 100,45
  RF 58 67,54 22,81 100,45
  PLS+LDA 67 56,74 56,74 100,56
  PLS+RF 58 67,54 22,81 100,45
  PCA+LDA 25 33,20 0,40 50,17
  PCA+RF 20 22,19 11,25 33,16
  RPART 46 22,60 33,54 100,28