BMC Systems Biology

Table 2 Performance results for CPD10

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

CPD10		Prediction method
Feature selection method	# of SNP	LR	SVM	RF	EN	LDA
LR	100	0.7973	0.8128	0.7715	0.8145	0.8078
	400	0.8017	0.9289	0.8606	0.9137	0.8966
SVM	100	0.8605	0.8699	0.8295	0.873	0.87
	400	0.8474	0.9 61	0.8961	0.9405	0.9399
RF	100	0.8143	0.8326	0.7999	0.821	0.8206
	400	0.7752	0.9164	0.8709	0.8813	0.8669
EN	100^a	0.8547	0.8594	0.8273	0.8567	0.8585
	250^a	0.8621	0.9235	0.8731	0.9046	0.9022
LDA	100	0.7758	0.7801	0.7205	0.7862	0.7814
	400	0.7948	0.9283	0.8411	0.911	0.8939

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