library(TCGAbiolinks)
# 獲取GDC工程的各種參數(shù),如腫瘤種類等
GDCprojects=getGDCprojects()
saveRDS(object = GDCprojects,
file = "G:\\GDCdata\\GDCprojects.rds")
建立查詢
GDCquery(
project,
data.category,
data.type,
workflow.type,
legacy = FALSE,
access,
platform,
file.type,
barcode,
data.format,
experimental.strategy,
sample.type
)
project:腫瘤種類秩彤〈垡螅可用TCGAbiolinks:::getGDCprojects()$project_id 查詢可填的值
data.category官研,用TCGAbiolinks:::getProjectSummary("TCGA-BRCA") 查詢,其中TCGA-BRCA來自上次查詢將結(jié)果
主要是以下其中一種:
- Biospecimen
- Clinical
- Copy Number Variation
- DNA Methylation
- Sequencing Reads
- Simple Nucleotide Variation
- Transcriptome Profiling
sample.type:樣本類型诈乒,取值可以是三列中的任意一個值
下載并保存
# 下載引用內(nèi)容
GDCdownload(query = query_TCGA,directory = "G:\\GDCdata")
# 提取下載內(nèi)容,注意路徑與下載路徑一致
tcga_data <- GDCprepare(query_TCGA,directory = "G:\\GDCdata")
查詢結(jié)果保存,注意婆芦,不是具體數(shù)據(jù)怕磨,是查詢結(jié)果描述,約等于PDATA
data <- getResults(query)