Figure 3

Display of the selected features in distinguishing the four subtypes of GBM, i.e., pro-neural (P), neural (N), classical (C), and mesenchymal (M) for the testing dataset (a) and the training dataset (b). 121 features (3 miRNA expression probes on the top and followed by 118 mRNA expression probes) were chosen from both miRNA expression and mRNA expression data. Each row represents a feature and each column represents a sample/patient. Each feature is normalized by the largest value in each row. The samples with arrows were misclassified to the subtypes as denoted by the arrow.