Fig. 2: Ranking and hierarchical clustering using the top discriminatory renally excreted urinary protein biomarkers for endometrial cancer detection.

a, b Top 20 discriminatory renally excreted proteins identified by Random Forest machine learning technique and ranked by their contribution to classification accuracy using the mean decrease accuracy (a) and mean decrease Gini index (b) based on all study samples. c Hierarchical clustering using the top discriminatory proteins. The difference in intensities of the biomarkers by cancer-control status is shown. Each coloured cell in the map represents scaled/relative concentration of the indicated protein. Proteins are clustered along the vertical axis while subjects are clustered along the horizontal axis. Hierarchical clustering was based on the Euclidean distance measure and Ward algorithm