A visual analytics approach for models of heterogeneous cell populations

EURASIP Journal on Bioinformatics and Systems Biology

Table 1 Area under the ROC curve for different marker combinations

	C8a(0)	k _-8	k _-9	k _-10	k _-12
C8a(0)	0.569	0.747	0.626	0.808	0.690
k _-8	0.747	0.736	0.760	0.898	0.800
k _-9	0.626	0.760	0.603	0.822	0.709
k _-10	0.808	0.898	0.822	0.795	0.858
k _-12	0.690	0.800	0.709	0.858	0.676

A common performance measure for classifiers is the area under the ROC curve. The worst and best achievable performance is 0.5 and 1, respectively. The evaluation of the area under the ROC curve verifies that if only one marker can be used, k_-10 (area = 0.795) and k_-8 (area = 0.736) are the best choice (on-diagonal bold numbers). In case of two markers, the combination of k_-8 - k_-10 allows for the best classification (area = 0.898) (off-diagonal bold numbers). For the three markers k_-8, k_-10, and k_-12, the area under the ROC curve is 0.966.