A machine learning heuristic to identify biologically relevant and minimal biomarker panels from omics data

BMC Genomics

Table 3 TPR and TNR achieved by BioHEL compared to the other best methods for the five transcriptomics datasets, using leave-one-out cross validation

	NaiveBayes		SVM		IBk		Jrip		J48		RandomForest		BioHEL		RGIFE+ BioHEL
	TPR	TNR	TPR	TNR	TPR	TNR	TPR	TNR	TPR	TNR	TPR	TNR	TPR	TNR	TPR	TNR
GSE36700	0.24	0.67	0.28	0.72	0.84	0.97	0.48	0.66	0.24	0.62	0.44	0.83	0.76	0.91	0.96	0.98
GSE3698	0.58	0.73	0.39	0.60	0.67	0.79	0.67	0.78	0.75	0.84	0.54	0.72	0.73	0.83	1.00	1.00
E-GEOD-12021	0.84	0.91	0.39	0.61	0.71	0.83	0.58	0.73	0.58	0.74	0.77	0.87	0.87	0.93	0.97	0.98
E-GEOD-29746	0.48	0.63	0.48	0.68	0.65	0.79	0.61	0.76	0.42	0.59	0.55	0.71	0.77	0.87	0.84	0.90
E-GEOD-27390	1.00	1.00	1.00	1.00	0.95	0.95	0.90	0.89	0.90	0.91	0.84	0.86	1.00	1.00	1.00	1.00

ISSN: 1471-2164