Skip to main content
Fig. 1 | Biology Direct

Fig. 1

From: Multi-omics integration for neuroblastoma clinical endpoint prediction

Fig. 1

INF workflow. Graphical representation of the INF workflow for two generic omics datasets (adapted from [9]). A first RF classifier is trained on the juxtaposed data and the feature list obtained is ranked by mean decrease in Gini impurity (ML-juxt). The two data sets are then integrated by Similarity Network Fusion, the features are ranked by rSNF and a RF model is developed on the juxtaposed dataset with the feature ranking so defined (ML-rSNF). Finally, a RF classifier is trained on the juxtaposed dataset restricted to the intersection of juxt and rSNF top discriminant feature lists. All the predictive models are developed within the DAP described in the methods

Back to article page