前言

之前一直在用RTCGA包下載數(shù)據(jù)，看著永不更新的數(shù)據(jù)，心里總覺得怪怪的，于是下定決心重新學(xué)習(xí)一個(gè)好用的包——TCGAbiolinks。這個(gè)包調(diào)用GDC的API，應(yīng)該是最新的數(shù)據(jù)。
主要參考：TCGAbiolinks: TCGAbiolinks: An R/Bioconductor package for integrative analysis with GDC data

下載數(shù)據(jù)

直接上代碼

# if (!requireNamespace("BiocManager", quietly=TRUE))
#   install.packages("BiocManager")
# BiocManager::install("TCGAbiolinks")
 

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


#下面填入要下載的癌癥種類
request_cancer=c("PRAD","BLCA","KICH","KIRC","KIRP")
for (i in request_cancer) {
  cancer_type=paste("TCGA",i,sep="-")
  print(cancer_type)
  #下載臨床數(shù)據(jù)
  clinical <- GDCquery_clinic(project = cancer_type, type = "clinical")
  write.csv(clinical,file = paste(cancer_type,"clinical.csv",sep = "-"))
  
  #下載rna-seq的counts數(shù)據(jù)
  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 = "-"))
  
  #下載miRNA數(shù)據(jù)
  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 = "-"))
  
  #下載Copy Number Variation數(shù)據(jù)
  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 = "-"))
  
  #下載甲基化數(shù)據(jù)
  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 = "-"))
}

常用的一些數(shù)據(jù)基本都下下來了，放在當(dāng)前目錄下。