TCGA数据下载-R包TCGAbiolinks下载数据

TCGAbiolinks 是一个用于TCGA数据综合分析的R/BioConductor软件包，能够通过GDC Application Programming Interface (API)访问 National Cancer Institute (NCI) Genomic Data Commons (GDC) ，来搜索、下载和准备TCGA相关数据，以便在R中进行分析。

TCGA数据库提供的下载数据入口：https://portal.gdc.cancer.gov


rm(list = ls()) ##魔幻操作，一键清空~

options(stringsAsFactors = F)

#安装包&加载包

if (!require(TCGAbiolinks)) {

  install.packages("TCGAbiolinks")

  library(TCGAbiolinks)}

if (!require(SummarizedExperiment)) {

  install.packages("SummarizedExperiment")

  library(SummarizedExperiment)}

#TCGAbiolinks:::getGDCprojects()$project_id ##查询各个癌种的项目id

#TCGAbiolinks:::getProjectSummary("TCGA-LUAD") ##查看project中有哪些数据类型，如查询"TCGA-LUAD"

#一般包括3步，GDCquery、GDCdownload和GDCprepare

#数据检索GDCquery

#1)下载转录组数据（counts）

query <- GDCquery(project = "TCGA-LUAD",#各个癌种的项目id

                  data.category = "Transcriptome Profiling",#数据类型，转录组数据

                  data.type = "Gene Expression Quantification",

                  workflow.type = "HTSeq - Counts")

#进行下载，若本地有，则进行报告,无则下载

#GDCdownload(query)

GDCdownload(query,

            method = "api",

            files.per.chunk = 20)# 拆分下载，减少下载失败风险

#将下载的数据进行整理

data<-GDCprepare(query,save=FALSE)####一般到GDCprepare就齐活了

LUAD_Data <- assay(data)

dim(LUAD_Data)

save(data,file='LUAD_counts.Rdata')

write.csv(data,file="TCGAbiolinks-LUAD-counts.csv")

#data <- GDCprepare(query = query, save = TRUE, save.filename ="LUAD_counts.Rdata")

#summarizedExperiment|是否生成summarizedExperiment对象，默认TRUE

#2)下载转录组数据FPKM

query <- GDCquery(

  project = "TCGA-LUAD",

  data.category = "Transcriptome Profiling",

  data.type = "Gene Expression Quantification",

  workflow.type = "HTSeq - FPKM")

GDCdownload(query, files.per.chunk = 20)

Data<- GDCprepare(

  query,

  save = T,

  save.filename = "LUAD_mRNA_FPKM.rdata")

write.csv(data,file="TCGAbiolinks-LUAD-FPKM.csv")

#3）临床信息下载

clinic <- GDCquery_clinic(project = "TCGA-LUAD",

                          type = 'Clinical')

dim(clinic)

#4)miRNA data数据下载

query <- GDCquery(project = "TCGA-LUAD",

                  data.category = "Transcriptome Profiling",

                  data.type = "miRNA Expression Quantification",

                  workflow.type = "BCGSC miRNA Profiling")

GDCdownload(query,

            method = "api",

            files.per.chunk = 20)

mir_exp<- GDCprepare(query = query,

                     summarizedExperiment=F)# set F

write.csv(mir_exp,file="TCGAbiolinks-LUAD-miRNA.csv")

save(mir_exp,file="LUAD_miRNA_raw.Rdata")

#5)体细胞突变下载

data<-GDCquery_Maf("LUAD",pipelines = "mutect2")

save(data,file = "LUAD_mut.Rdata")

write.csv(data,file="TCGAbiolinks-LUAD-mutect2.csv")

#6)拷贝数变异数据(GISTIC2)

query <- GDCquery(

  project = "TCGA-LUAD",

  data.category = "Copy Number Variation",

  data.type = "Gene Level Copy Number Scores",

  access="open"

)

GDCdownload(query, files.per.chunk = 20)

LUAD_GISTIC2<-GDCprepare(query,save = F)

write.csv(LUAD_GISTIC2,file="TCGAbiolinks-LUAD_GISTIC2.csv")

save(LUAD_GISTIC2,file="LUAD_GISTIC2.Rdata")

#7)DNA甲基化

query <- GDCquery(

  project = "TCGA-LUAD",

  data.category = "DNA Methylation",

  platform = "Illumina Human Methylation 450"

)

GDCdownload(query, files.per.chunk = 100)

LUAD_DNAme<-GDCprepare(query,

           save = F)

write.csv(LUAD_DNAme,file="TCGAbiolinks-LUAD-methylation 450.csv")

save(LUAD_DNAme,file="LUAD_methylation.Rdata")