Group sparse canonical correlation analysis for genomic data integration

BMC Bioinformatics

Table 1 Correlations and the number of features from three pairs of loading vectors

Data set	Model	dim1			dim2			dim3			p(dim1)
Data set	Model	corr.	No.(u)	No.(v)	corr.	No.	No.	corr.	No.	No.	p(dim1)
Glioma	CCA-group	0.3036	103	113	0.3675	153	93	0.3501	110	104	0.0005
	CCA-l1	0.5362	72	78	0.6884	83	76	0.5743	78	82	<0.0001
	CCA-sparse group	0.5903	53	47	0.7023	41	61	0.5728	67	60	<0.0001
NCI60	CCA-group	0.8425	189	184	0.8943	100	125	0.8310	125	115	<0.0001
NCI60	CCA-l1	0.9645	100	171	0.9527	67	120	0.9495	131	88	<0.0001
	CCA-sparse group	0.9649	45	71	0.9633	66	109	0.9355	97	108	<0.0001

ISSN: 1471-2105