Combining DNA methylation and RNA sequencing data of cancer for supervised knowledge extraction

Table 6 Example of combined matrix on the breast cancer data

Combined	GDA_dMeth	SCN3A_dMeth	...	GDA_rna	SCN3A_rna	Class
TCGA-A1-A0SD-01A	?	?	...	0.6	28.4	Normal
TCGA-GI-A2C9-01A	1.9	2.7	...	?	?	Tumoral
..	..	..	..	..	..	..
TCGA-A7-A4SD-01A	1.6	2.3	...	0.0	6.4	Tumoral

In the combined matrix, rows are identified by the TCGA Barcode (excluding the part that identifies the type of experiment carried out on a sample). In this way it is possible to recognize the sequenced sample with both NGS techniques (RNA sequencing and DNA methylation). In this case the matrix has as many rows as the total samples (union of RNA sequencing samples and DNA methylation samples), counting only one time those samples in common, on which both experiments were preformed

ISSN: 1756-0381