TCGAbiolinks下载TCGA数据
2020-03-11 本文已影响0人
养猪场小老板
#以下为安装TCGAbiolinks的R包
#1)第一种
if (!requireNamespace("BiocManager", quietly=TRUE))
install.packages("BiocManager")
BiocManager::install("TCGAbiolinks")
#2)第二种
#可以先下载到本地安装比较快
#Tools > install.packages
#3) 第三种
devtools::install_github(repo = "BioinformaticsFMRP/TCGAbiolinks")
#################################
# TCGA-12-4567-01-blah-blah --> 这是Normal
# TCGA-12-4567-11-blah-blah --> 这是tumor
# 注意黑体的部分。01-09是tumor;10-19是Normal;20-29是Control
####加载程序包
library(TCGAbiolinks)
library(dplyr)
library(DT)
library(SummarizedExperiment)
#################################
#下面填入要下载的癌症种类
request_cancer=c("PRAD","BLCA","KICH","KIRC","KIRP")
for (i in request_cancer) {
cancer_type=paste("TCGA",i,sep="-")
print(cancer_type)
#下载临床数据
clinical <- GDCquery_clinic(project = cancer_type, type = "clinical")
write.csv(clinical,file = paste(cancer_type,"clinical.csv",sep = "-"))
#下载rna-seq的counts数据
query <- GDCquery(project = cancer_type,
data.category = "Transcriptome Profiling",
data.type = "Gene Expression Quantification",
workflow.type = "HTSeq - Counts")
GDCdownload(query, method = "api", files.per.chunk = 100)
expdat <- GDCprepare(query = query)
count_matrix=assay(expdat)
write.csv(count_matrix,file = paste(cancer_type,"Counts.csv",sep = "-"))
#下载miRNA数据
query <- GDCquery(project = cancer_type,
data.category = "Transcriptome Profiling",
data.type = "miRNA Expression Quantification",
workflow.type = "BCGSC miRNA Profiling")
GDCdownload(query, method = "api", files.per.chunk = 50)
expdat <- GDCprepare(query = query)
count_matrix=assay(expdat)
write.csv(count_matrix,file = paste(cancer_type,"miRNA.csv",sep = "-"))
#下载Copy Number Variation数据
query <- GDCquery(project = cancer_type,
data.category = "Copy Number Variation",
data.type = "Copy Number Segment")
GDCdownload(query, method = "api", files.per.chunk = 50)
expdat <- GDCprepare(query = query)
count_matrix=assay(expdat)
write.csv(count_matrix,file = paste(cancer_type,"Copy-Number-Variation.csv",sep = "-"))
#下载甲基化数据
query.met <- GDCquery(project =cancer_type,
legacy = TRUE,
data.category = "DNA methylation")
GDCdownload(query.met, method = "api", files.per.chunk = 300)
expdat <- GDCprepare(query = query)
count_matrix=assay(expdat)
write.csv(count_matrix,file = paste(cancer_type,"methylation.csv",sep = "-"))
}