TCGA数据下载：Downloading Dataset from TCGA via TCGAbiolinks

前言

肿瘤的多组学分析过程，我们常需要从TCGA下载相关的数据，这里我们介绍使用TCGAbiolinks包下载数据的流程。最后数据分装成SummerisedExperiment格式。更多知识分享请到 https://zouhua.top/。

代码

library(TCGAbiolinks)
library(dplyr)
library(SummarizedExperiment)

cancer_type <- "TCGA-CESC"
clinical <- GDCquery_clinic(project = cancer_type,
                            type = "clinical")
write.csv(clinical, "TCGA-CESC_clincal.csv", row.names = F)

# download omics-data 
get_OmicsData <- function(project  = cancer_type,
                          Outdir   = "mRNA"){
  if(Outdir == "mRNA"){
    query_Data <- GDCquery(project = project,
                           data.category = "Transcriptome Profiling",
                           data.type = "Gene Expression Quantification",
                           workflow.type = "HTSeq - Counts")    
  }else if(Outdir == "miRNA"){
    query_Data <- GDCquery(project = project,
                           data.category = "Transcriptome Profiling",
                           data.type = "miRNA Expression Quantification",
                           workflow.type = "BCGSC miRNA Profiling")     
  }else if(Outdir == "CNV"){
    query_Data <- GDCquery(project = project,
                           data.category = "Copy Number Variation",
                           data.type = "Copy Number Segment")     
  }else if(Outdir == "DNA_Methylation"){
    query_Data <- GDCquery(project = project,
                           data.category = "DNA methylation",
                           legacy = TRUE)     
  }
  
  GDCdownload(query = query_Data,
              method = "api",
              files.per.chunk = 60,
              directory = Outdir)
  
  expdat <- GDCprepare(query = query_Data,
                       directory = Outdir)
  return(expdat)
}

dat_mRNA <- get_OmicsData(project = cancer_type,
                          Outdir = "mRNA")
saveRDS(dat_mRNA, file = "TCGA-CESC_mRNA.RDS")

dat_miRNA <- get_OmicsData(project = cancer_type,
                          Outdir = "miRNA")
saveRDS(dat_miRNA, file = "TCGA-CESC_miRNA.RDS")

dat_CNV <- get_OmicsData(project = cancer_type,
                          Outdir = "CNV")
saveRDS(dat_CNV, file = "TCGA-CESC_CNV.RDS")

dat_methy <- get_OmicsData(project = cancer_type,
                          Outdir = "DNA_Methylation")
saveRDS(dat_methy, file = "TCGA-CESC_Methylation.RDS")

Reference

1. TCGA / 癌症简称 / 缩写 / TCGA癌症中英文对照