Skip to main content
Fig. 1 | Clinical Proteomics

Fig. 1

From: Proteomic signature associated with chronic kidney disease (CKD) progression identified by data-independent acquisition mass spectrometry

Fig. 1

a ROC Curves showing the performance of the models built with the biomarkers identified by our Differential Expression Analysis and Random Forest with Boruta Feature Selection algorithm. The ROC curve for Boruta gives us the best AUC (0.81). b Overlap between the two sets of biomarkers (Differential Expression Analysis using limma and Random Forest model using Boruta Feature Selection. c Table with the 11 overlapping biomarkers coloured by significance (p value < 0.05) (Significant proteins: CCDC25, CCT4, AFM, SERPINA4, C6, TTR)

Back to article page

Clinical Proteomics

ISSN: 1559-0275