MVDA: a multi-view genomic data integration methodology

BMC Bioinformatics

Table 1 Datasets: Description of the datasets used in this study

Dataset	Response	N(0)	N(1)	N(2)	N(3)	Gene	RNASeq	microRNA	miRNASeq	Protein	Copy	Clinical
						expression		expression		expression	number	data
Breast Cancer from The Cancer genome Atlas, N = 151
TCGA.BRC	Pam50 (Her2,Basal,LumA,LumB)	24	13	55	59		x		x
Breast Cancer from The Gene Expression Omnibus, N = 201
OXF.BRC.1	Pam50 (Her2,Basal,LumA,LumB)	26	6	117	52	x		x
OXF.BRC.2	Clinical (Level1, Level2, Level3, Level4)	73	54	42	32	x		x
Prostate Cancer from Memorial Sloan-Kettering Cancer Center, N = 88
MSKCC.PRCA	Tumor stages T1 vs. T2, T3, T4	53	35			x		x			x	x
Ovarian Cancer from The Cancer Genome Atlas, N = 398
TCGA.OVG	Tumor stage I,II, Tumor stage III, Tumor stage IV	33	315	50		x		x		x
Glioblastoma Multiforme from The Cancer genome Atlas, N = 167
from TCGA.GBM	(Classical, Mesechymal, Neural, Proneural)	37	54	24	52	x		x

“N” is the number of subjects for each dataset. Ni is the number of samples in the i-th class. An x denotes if that view (column) is available for a specific dataset (row)

ISSN: 1471-2105