|
a |
|
b/man/get_tcga_exp.Rd |
|
|
1 |
% Generated by roxygen2: do not edit by hand |
|
|
2 |
% Please edit documentation in R/GetTcgaExp.R |
|
|
3 |
\name{get_tcga_exp} |
|
|
4 |
\alias{get_tcga_exp} |
|
|
5 |
\title{TCGA Expression Data Processing} |
|
|
6 |
\usage{ |
|
|
7 |
get_tcga_exp( |
|
|
8 |
counts_file_path, |
|
|
9 |
gene_probes_file_path, |
|
|
10 |
phenotype_file_path, |
|
|
11 |
output_file_path |
|
|
12 |
) |
|
|
13 |
} |
|
|
14 |
\arguments{ |
|
|
15 |
\item{counts_file_path}{File path to the counts data (usually in the form of a large matrix with gene expression data).} |
|
|
16 |
|
|
|
17 |
\item{gene_probes_file_path}{File path containing the gene probes data.} |
|
|
18 |
|
|
|
19 |
\item{phenotype_file_path}{File path to the phenotype data, which includes various sample attributes.} |
|
|
20 |
|
|
|
21 |
\item{output_file_path}{Path where the output files, distinguished between tumor and normal, will be saved.} |
|
|
22 |
} |
|
|
23 |
\value{ |
|
|
24 |
A list containing matrices for tumor and normal expression data. |
|
|
25 |
} |
|
|
26 |
\description{ |
|
|
27 |
This function processes expression data and phenotype information, separates tumor and normal samples, |
|
|
28 |
and saves the results into different files. It's specifically designed for data obtained from TCGA. |
|
|
29 |
} |
|
|
30 |
\note{ |
|
|
31 |
IMPORTANT: This function assumes that the input files follow a specific format and structure, typically found in TCGA data releases. |
|
|
32 |
Users should verify their data's compatibility. Additionally, the function does not perform error checking on the data's content, |
|
|
33 |
which users should handle through proper preprocessing. |
|
|
34 |
|
|
|
35 |
CRITICAL: The 'output_file_path' parameter must end with '.rds' to be properly recognized by the function. It is also highly recommended |
|
|
36 |
that the path includes specific identifiers related to the target samples, as the function will create further subdivisions in the specified |
|
|
37 |
path for tumor or normal tissues. Please structure the 'output_file_path' following this pattern: './your_directory/your_sample_type.exp.rds'. |
|
|
38 |
} |
|
|
39 |
\examples{ |
|
|
40 |
counts_file <- system.file("extdata", "TCGA-SKCM.htseq_counts_test.tsv", package = "TransProR") |
|
|
41 |
gene_probes_file <- system.file("extdata", |
|
|
42 |
"TCGA_gencode.v22.annotation.gene.probeMap_test", |
|
|
43 |
package = "TransProR") |
|
|
44 |
phenotype_file <- system.file("extdata", "TCGA-SKCM.GDC_phenotype_test.tsv", package = "TransProR") |
|
|
45 |
ouput_file <- file.path(tempdir(), "SKCM_Skin_TCGA_exp_test.rds") |
|
|
46 |
|
|
|
47 |
SKCM_exp <- get_tcga_exp( |
|
|
48 |
counts_file_path = counts_file, |
|
|
49 |
gene_probes_file_path = gene_probes_file, |
|
|
50 |
phenotype_file_path = phenotype_file, |
|
|
51 |
output_file_path = ouput_file |
|
|
52 |
) |
|
|
53 |
head(SKCM_exp[["tumor_tcga_data"]])[1:5, 1:5] |
|
|
54 |
head(SKCM_exp[["normal_tcga_data"]], n = 10) # Because there is only one column. |
|
|
55 |
} |
|
|
56 |
\author{ |
|
|
57 |
Dongyue Yu |
|
|
58 |
} |