TCGAbiolinks--使用R下载TCGA数据

生信老学长
“师兄师兄，我要研究泛癌怎么批次化下载TCGA的数据啊”。嗨，上次告诉你关注我，这次还是再告诉你一次

download_path='./TCGA'#填写你的下载文件夹

setwd(download_path)

project='TCGA-OV'#填写肿瘤项目名称，不会的见推文

library(TCGAbiolinks)

library(SummarizedExperiment)

##下载方面主要分为三个部分

#1、查询 GDCquery()

#2、下载GDCdownload()

#3、读取GDCprepare()

#1、查询 GDCquery()

GDCquery(

project,#项目名称例如TCGA-LIHC 肝癌

data.category,#数据类型，见推文介绍

data.type,#分类后的再详细分类，见推文介绍

workflow.type,#使用的软件或者方法

access,#默认为open即权限

platform,#测序平台 见https://rdrr.io/bioc/TCGAbiolinks/man/GDCquery.html及TCGA

file.type,#一般没用

barcode,#可以指定下载样本条码如TARGET-20-PADZCG-04A-01R

data.format,#可以指定数据格式例如"VCF", "TXT", "BAM","SVS","BCR XML","BCR SSF XML", "TSV", "BCR Auxiliary XML", "BCR OMF XML", "BCR Biotab", "MAF", "BCR PPS XML", "XLSX")

experimental.strategy,#测序类型

sample.type#样本类型，见推文例如Primary Solid TumorTP

)

#查看各参数可填入列表

#project

TCGAbiolinks:::getGDCprojects()$project_id

#data.category

TCGAbiolinks:::getProjectSummary(project)$data_categories

#查询数据示例 转录组 原发性实体瘤和对照

query <- GDCquery(

project = project,

data.category = "Transcriptome Profiling",

data.type = "Gene Expression Quantification",#基因表达量

workflow.type = "STAR - Counts",

sample.type = c('Primary Tumor', 'Control Analyte')

)

#2、下载GDCdownload()

GDCdownload(query, method = "api", files.per.chunk = 100) 

#3、读取GDCprepare()

pre.exp = GDCprepare(query = query)

#查看数据类型

names(assays(pre.exp))

#提取fpkm

fpkm_matrix <- assay(pre.exp, "fpkm_uq_unstrand")

fpkm_matrix[1:5,]

#查看临床

colData(pre.exp)

#查看对应的symbol

rowData(pre.exp)

##查询临床

#indexed clinical: 使用 XML 文件创建的精炼临床数据，XML>indexed

#XML: 原始临床数据

#BCR Biotab: 解析 XML 文件之后的 tsv 文件

query_clin <- GDCquery(

project = project,

data.category = "Clinical",

data.type = "Clinical Supplement",

data.format = "BCR Biotab"

)

GDCdownload(query_clin)

clinical <- GDCprepare(query_clin)

names(clinical)

#获取采样信息

query_Biospecimen <- GDCquery(

project = project,

data.category = "Biospecimen",

data.type = "Biospecimen Supplement",

data.format = "BCR Biotab"

)

GDCdownload(query_Biospecimen)

Biospecimen=GDCprepare(query_Biospecimen)

#切片图像

query_slide <- GDCquery(

project = project,

data.category = "Biospecimen",,

data.type = "Slide Image",

data.format = "SVS" 

)

# 检索特定肿瘤的分子亚型,只有部分有

subtype=TCGAquery_subtype('HNSC')

colnames(subtype)

参考文献

Antonio Colaprico, Tiago Chedraoui Silva, Catharina Olsen, Luciano Garofano, Claudia Cava, Davide Garolini, Thais Sabedot, Tathiane Malta, Stefano M. Pagnotta, Isabella Castiglioni,Michele Ceccarelli, Gianluca Bontempi Houtan Noushmehr. TCGAbiolinks: An R/Bioconductor package for integrative analysis of TCGA data Nucleic Acids Research (05 May 2016) 44 (8): e71.

生信老学长 专业方案撰写和生信支持