BMC Systems Biology

Table 4 Performance results for SC

From: Phenotype prediction from genome-wide association studies: application to smoking behaviors

SC		Prediction method
Feature selection method	# of SNP	LR	SVM	RF	EN	LDA
LR	100	0.7290	0.7187	0.6919	0.7372	0.7308
	500	0.8245	0.8644	0.7856	0.8587	0.8591
SVM	100	0.7417	0.7299	0.6975	0.7413	0.7414
	500	0.8643	0.8934	0.8032	0.8780	0.8791
RF	100	0.7007	0.7053	0.7013	0.6992	0.7008
	500	0.7728	0.8085	0.7598	0.7676	0.7714
EN	100^a	0.7682	0.7606	0.7233	0.7691	0. 76 9 1
	176^a	0.7935	0.7964	0.7485	0.7967	0.7955
LDA	100	0.7015	0.6946	0.6585	0.7004	0.7019
	500	0.8205	0.8466	0.7426	0.8275	0.8291

In each column, the best results are shown as underlined. In each row, the best results are boldfaced. a. # of SNPs with non-zero coefficient.

Back to article page

ISSN: 1752-0509

Contact us

General enquiries: ORSupport@springernature.com