TCGA hg38 总的外显子基因长度可以用38M或者35
TCGAbiolinks下载:
采用TCGAbiolinks下载存在两种方式,一种是下载基于hg38的下载
#biocLite("maftools")
require(TCGAbiolinks)
require(maftools)
#下载突变数据
LIHC_mutect2 <- GDCquery_Maf(tumor = "LIHC", pipelines = "mutect2")
# Only first 50 to make render faster
datatable(LIHC_mutect2[1:20,],
filter = 'top',
options = list(scrollX = TRUE, keys = TRUE, pageLength = 5),
rownames = FALSE)
下载hg19的突变数据
query.maf.hg19 <- GDCquery(project = "TCGA-CHOL",
data.category = "Simple nucleotide variation",
data.type = "Simple somatic mutation",
access = "open",
file.type = "bcgsc.ca_CHOL.IlluminaHiSeq_DNASeq.1.somatic.maf",
legacy = TRUE)
GDCdownload(query.maf.hg19)
maf <- GDCprepare(query.maf.hg19)
# Only first 50 to make render faster
datatable(maf[1:20,],
filter = 'top',
options = list(scrollX = TRUE, keys = TRUE, pageLength = 5),
rownames = FALSE)