TCGAbiolinks (一) 获得counts矩阵

发布于 2022-03-31  248 次阅读

加载包

  • 更新包：
  • BiocManager::install("BioinformaticsFMRP/TCGAbiolinksGUI.data")
  • BiocManager::install("BioinformaticsFMRP/TCGAbiolinks")
  • packageVersion("TCGAbiolinks") # 2.25.0
library(TCGAbiolinks)
library(plyr)
library(SummarizedExperiment)

 

查看信息

# 查看癌症类型
TCGAbiolinks:::getGDCprojects()$project_id 
# 查看对应癌症的数据类型
TCGAbiolinks:::getProjectSummary('TCGA-PRAD') # 以前列腺癌为例

 

筛选数据

# 一般的前列腺癌 GDC Data Portal 是 hg38 的
PRAD <- GDCquery(project = 'TCGA-PRAD',
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification", 
                  workflow.type = "STAR - Counts")

# 选择病例列 ，不加cols参数则是完整结果的全部列
PRAD_cases <- getResults(PRAD,cols=c("cases"))

# 选择癌组织数据
PRAD_tp  <- TCGAquery_SampleTypes(barcode = PRAD_cases, typesample = "TP")

PRAD_D <- GDCquery(project = 'TCGA-PRAD',
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification", 
                  workflow.type = "STAR - Counts",
                  barcode = PRAD_tp)

 

获取数据

PRAD_D <- GDCquery(project = 'TCGA-PRAD',
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification", 
                  workflow.type = "STAR - Counts",
                  barcode = PRAD_tp)

GDCdownload(query = PRAD_D)

PRAD <- GDCprepare(query = PRAD_D, save = TRUE, save.filename = "PRAD.rda")

 

获取矩阵

counts <- [email protected]@data$unstranded
colnames(counts) <- [email protected]$patient
rownames(counts) <- [email protected]$gene_name

 

一枚爱好探索的医学生