Biomarker detection using corrected degree of domesticity in hybrid social network feature selection for improving classifier performance

Table 1 Classification performances of SNFS in the leukemia test set

FS	CD	CN	Acc.	Sens.	Spe.	AUC	FN
SVM SQRT-RFE+IG	Louvain	3	0.9706	1.0000	0.9286	0.9857	9
SVM SQRT-RFE+CS		3	0.9118	1.0000	0.7857	1.0000	9
SVM SQRT-RFE+RF		3	0.8824	0.8500	0.9286	0.9393	8
IG+CS		3	0.9118	1.0000	0.7857	0.9893	8
IG+RF		3	0.9412	1.0000	0.8571	0.9536	8
CS+RF		3	0.8824	1.0000	0.7143	0.9750	9
SVM SQRT-RFE+IG	Walktrap	4	0.9706	1.0000	0.9286	0.9821	10
SVM SQRT-RFE+CS		3	0.9118	1.0000	0.7857	1.0000	9
SVM SQRT-RFE+RF		3	0.8824	0.8500	0.9286	0.9393	8
IG+CS		3	0.9118	1.0000	0.7857	0.9893	8
IG+RF		3	0.9412	1.0000	0.8571	0.9536	8
CS+RF		3	0.8824	1.0000	0.7143	0.9750	9
SVM SQRT-RFE+IG \(^1\)	Infomap	2	0.9412	1.0000	0.8571	0.9929	8
SVM SQRT-RFE+CS		3	0.9118	1.0000	0.7857	1.0000	9
SVM SQRT-RFE+RF		3	0.8824	0.8500	0.9286	0.9393	8
IG+CS		3	0.9118	1.0000	0.7857	0.9893	8
IG+RF		3	0.9412	1.0000	0.8571	0.9536	8
CS+RF		3	0.8824	1.0000	0.7143	0.9750	9

FS: feature selection method used in the first step of the algorithm; CD: community detection method used in the third step of the algorithm; CN: number of communities detected by the community detection algorithm; Acc.: accuracy; Sens.: sensitivity; Spe.: specificity; AUC: area under the ROC curve; FN: number of selected features
\(^{1}\) Selected combination

ISSN: 1471-2105