【已完结，后续更新分析流程】如何批量下载TCGA公开的转录组、miRNA转录组，蛋白表达谱、SNV、甲基化以及CNV数据

conda create -n R4 -c conda-forge -y r-essentials r-base r-devtools
conda activate R4
R

install.packages("BiocManager")
BiocManager::install("BioinformaticsFMRP/TCGAbiolinksGUI.data")
BiocManager::install("BioinformaticsFMRP/TCGAbiolinks") ## 致敬开发者

library(TCGAbiolinks)
projects <- getGDCprojects()
projects <- projects$project_id
TCGA_dowload<-function(x,dirpath){
#转录组数据
query.exp <-GDCquery(
  project = x, 
  data.category = "Transcriptome Profiling",
  data.type = "Gene Expression Quantification", 
  workflow.type = "STAR - Counts""
)
GDCdownload(query.exp)
Exp <- GDCprepare(query = query.exp)
#SNV数据
query.maf <- GDCquery(
  project = x, 
  data.category = "Simple Nucleotide Variation", 
  access = "open"
)
Maf <- GDCprepare(query = query.maf)
saveRDS(Maf,file = paste0(dirpath,x,"_maf.rds"))
#甲基化数据
for (i in c("450","27")) {
    query_met.hg38 <- GDCquery(
      project = x, 
      data.category = "DNA Methylation",
      platform = paste0("Illumina Human Methylation ",i),
      data.type = "Methylation Beta Value"
    )
    Met <- GDCprepare(query = query_met.hg38)
    saveRDS(Met,file = paste0(dirpath,x,"_met_Ill",i,".rds"))
  }
#miRNA数据
query.mirna <- GDCquery(
    project = x, 
    experimental.strategy = "miRNA-Seq",
    data.category = "Transcriptome Profiling", 
    data.type = "miRNA Expression Quantification"
  )
GDCdownload(query.mirna)
Mirna <- GDCprepare(query = query.mirna)
saveRDS(Mirna,file = paste0(dirpath,x,"_miRNA.rds"))
#蛋白表达量
query.rppa <- GDCquery(
    project = x, 
    data.category = "Proteome Profiling",
    data.type = "Protein Expression Quantification"
  )
GDCdownload(query.rppa) 
Proteins <- GDCprepare(query.rppa)
saveRDS(Proteins,file = paste0(dirpath,x,"_protein.rds"))
#CNV数据
CNV.type<-c("Allele-specific Copy Number Segment", 
            "Gene Level Copy Number",
            "Masked Copy Number Segment")
for (ii in CNV.type) {
    query.CNV <- GDCquery(
      project = project,
      data.category = "Copy Number Variation",
      data.type = ii
    )
    GDCdownload(query.CNV)
    CNV <- GDCprepare(query = query.CNV)
    saveRDS(CNV,file = paste0(dirpath,project,"_CNV_",
                              stringr::str_replace_all(i," ","_"),
                              ".rds"))
  }
}

## 批量下载数据
for (j in projects) {
  print(j)
  try(TCGA_dowload(j,dirpath = "./TCGAbiolinks_data/"),silent = T)
}

TCGA_ACC_Exp<-readRDA("TCGA-ACC_exp.rds") ##注意文件路径要正确

TCGA_ACC_Exp_unstrand<-SummarizedExperiment::assay(TCGA_ACC_Exp,1)

TCGA_ACC_clinData<-SummarizedExperiment::colData(TCGA_ACC_Exp)