Data integration by fuzzy similarity-based hierarchical clustering

BMC Bioinformatics

Table 1 Datasets description: Three omics are provided for each dataset, respectively DNA gene expression, miRNA and Methylation

	#Cases	DNA			miRNA			Methy			Multi-Omics
Dataset	-	ORI	LN	RF	ORI	LN	RF	ORI	LN	RF	ORI	LN	RF
AML	170	20531	2000	1997	5000	2000	1999	705	558	553	26236	4558	4529
BIC	621	20531	2000	2000	5000	2000	2000	1046	891	854	26577	4891	4854
COAD	220	20531	2000	2000	5000	2000	2000	705	613	591	26236	4613	4590
GBM	274	12042	2000	2000	5000	2000	2000	534	534	534	17576	4534	4534
KIRC	183	20531	2000	1999	5000	2000	1999	1046	796	754	26577	4796	4752
LIHC	367	20531	2000	2000	5000	2000	2000	1046	852	826	26577	4852	4366
LUSC	341	20531	2000	2000	5000	2000	2000	1046	878	850	26577	4878	4850
SKCM	448	20531	2000	2000	5000	2000	2000	1046	901	874	26577	4901	4874
OV	287	20531	2000	2000	5000	2000	2000	705	616	600	26236	4616	4600
SARC	257	20531	2000	2000	5000	2000	2000	1046	838	805	26577	4838	4805

The number of features at each variable selection method is shown. ORI: Original variable dimension, LN: Logarithm and normalisation and, RF: Random Forest based on Mean Decrease Gini index

ISSN: 1471-2105