Table 5. Evaluation of four feature selection methods for defining a condensed biomarker signature for classification of two groups, using a 3-fold cross validation scheme repeated twice.

The length of the biomarker signature was set to 25. A linear SVM classifier was used to assess the performance in all cases, except for RF (RF), where random forest was used both for the ranking and the final AUC calculation. AUC values are given together with standard deviations. The biomarker overlap was defined as the number of common biomarkers between two signatures.

Method	Sample cohort 2				Sample cohort 3
		Biomarker overlap				Biomarker overlap
		BE-SVM	SVMc	RF		BE-SVM	SVMc	RF
	ROC AUC				ROC AUC
p-value	90.1 (2.3)	3	4	15	90.6 (1.3)	8	7	20
BE-SVM	95.9 (3.2)		17	6	93.5 (1.1)		15	9
SVMc	96.7 (2.1)			7	92.1 (0.5)			9
RF (SVM)	94.5 (1.3)				91.7 (0.8)
RF (RF)	95.1 (2.1)				90.9 (0.8)