Figure legends
Figure 1 . The Decision Tree computed from the RandomTree
classifier, available in Weka, using the sorafenib dataset. The
RandomTree’s parameters were set up as follows: weka.classifiers.trees.
RandomTree -K 0 -M 1.0 -V 0.001 -S 1, the selected Test models 10-fold
cross-validation, reaching an accuracy of 69.5652%.
Figure 2. Expression of genes identified by decision tree
analysis in HCC patients treated with sorafenib. Data are expressed as
mean ± SD, and the differences between the two groups were assessed with
the Mann Whitney U test.
Figure 3. The consolidated network obtained for each seed gene
by computing the neighborhoods with a radius of one.
Figure 4 . Top 10 genes by their degree of relevance in the seed
network, computed using CytoHubba: high significance values are
represented by red, orange, and yellow, while all bluish colors
represent less significant values.