Figure 5

1-D input importance computed for some models. Bar plots with the 1-D input importance computed for some of the RNA-seq based transcriptome profiles. We measured the importance of each feature in each supervised model that we trained/validated, using a sensitivity analysis (SA), which is a simple method that measures the effects on the output of a given model when the inputs are varied through their range of values. The red vertical bar indicates the highest sensitive score reached by features.