A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers

BMC Bioinformatics

Table 4 Overview of individual classifier performance and definition of ensembles

Classifier	Method	Features	Accuracy	Sensitivity	Specificity	AUC	Ensemble A	Ensemble B	Ensemble C	Ensemble D	Ensemble E	Ensemble F
mRNA-Classifier1	EN	182	0.9298	0.9737	0.8421	0.9737	X			X	X
mRNA-Classifier2	EN	73	0.9123	1.0000	0.7368	0.9709					X
mRNA-Classifier3	EN	36	0.8947	0.9737	0.7368	0.9501			X		X
mRNA-Classifier4	LDA	2	0.9298	0.9211	0.9474	0.9640					X
mRNA-Classifier5	RF	500	0.8947	0.9737	0.7368	0.9418					X
mRNA-Classifier6	SVM	500	0.9298	0.9474	0.8947	0.9640					X
mRNA-Classifier7	EN	43	0.9123	0.9474	0.8421	0.9598						X
mRNA-Classifier8	EN	25	0.9298	0.9737	0.8421	0.9612						X
mRNA-Classifier9	EN	17	0.9298	0.9737	0.8421	0.9695						X
mRNA-Classifier10	LDA	2	0.9298	0.9211	0.9474	0.9640				X		X
mRNA-Classifier11	RF	50	0.9298	0.9474	0.8947	0.9584			X			X
mRNA-Classifier12	SVM	50	0.8947	0.9211	0.8421	0.9557		X		X		X
miRNA-Classifier1	EN	66	0.8947	0.9211	0.8421	0.9626	X				X
miRNA-Classifier2	EN	21	0.9474	0.9737	0.8947	0.9709			X		X
miRNA-Classifier3	EN	8	0.9649	0.9737	0.9474	0.9723				X	X
miRNA-Classifier4	LDA	4	0.9298	0.9211	0.9474	0.9626				X	X
miRNA-Classifier5	RF	152	0.8947	0.8947	0.8947	0.9765					X
miRNA-Classifier6	SVM	152	0.9123	0.9474	0.8421	0.9626					X
miRNA-Classifier7	EN	36	0.9298	0.9474	0.8947	0.9709						X
miRNA-Classifier8	EN	16	0.9298	0.9474	0.8947	0.9848						X
miRNA-Classifier9	EN	12	0.9474	0.9737	0.8947	0.9806						X
miRNA-Classifier10	LDA	4	0.9298	0.9211	0.9474	0.9626						X
miRNA-Classifier11	RF	50	0.9123	0.9211	0.8947	0.9778				X		X
miRNA-Classifier12	SVM	50	0.8947	0.9211	0.8421	0.9612		X	X			X

Shown is a list of 12 mRNA- and 12 miRNA classifiers, their individual classification performance and their inclusion into 6 ensembles that are explored for classification of tumour vs normal samples. Abbreviations are the same as in Table 1.

ISSN: 1471-2105