生信个人笔记之TCGA

library("TCGAbiolinks")
###getGDCprojects()$project_id  ##罗列project参数所有内容(癌症种类)
###TCGAbiolinks:::getProjectSummary("TCGA-HNSC")  ##罗列所选癌症的data.category
expquery <- GDCquery(project = "TCGA-HNSC",
                     data.category = "Transcriptome Profiling",
                     data.type = "Gene Expression Quantification",
                     workflow.type = "HTSeq - Counts"
)
GDCdownload(expquery)
expquery2 <- GDCprepare(expquery)
expMatrix <- TCGAanalyze_Preprocessing(expquery2)
##Linux版R语言
##write.table(expMatrix, "../myresult_txt/HNSC_gene_counts_file00.tsv", sep="\t", quote=F, row.names=T)
##Win版R语言
##write.table(expMatrix, "..\\myresult_txt\\HNSC_gene_counts_file00.tsv", sep="\t", quote=F, row.names=T)

 

library("TCGAbiolinks")
query_clin <- GDCquery_clinic(project = "TCGA-HNSC",
                     type = "clinical",
                     save.csv = "FALSE")
GDCdownload(query_clin)

##Linux版R语言
##write.table(query_clin, "../myresult_txt/HNSC_clinical_file00t.tsv", sep="\t", quote=F, col.name = T, row.names=F)
##Win版R语言
write.table(query_clin, "..\\myresult_txt\\HNSC_clinical_file00t.tsv", sep="\t", quote=F, col.name = T, row.names=F)

学习生信，先下载R和Rstudio软件

第一篇参考链接：TCGA数据下载—TCGAbiolinks包参数详解 - 组学大讲堂问答社区 (omicsclass.com)

再安装R里和生信有关的包：

local({r <- getOption("repos")  
 r["CRAN"] <- "http://mirrors.tuna.tsinghua.edu.cn/CRAN/"   
options(repos=r)}) 

if (!requireNamespace("BiocManager", quietly=TRUE)){
    install.packages("BiocManager")
}
options(BioC_mirror="https://mirrors.tuna.tsinghua.edu.cn/bioconductor")
BiocManager::install("TCGAbiolinks")
library(TCGAbiolinks)

1.首先我们需要知道总的数据框架，先输入以下代码，获取GDC数据库详细资料，可在Environment > data查看：

getGDCprojects()

2.获取最新不同癌种ID（知道他们的ID才方便后面下载它所包含的数据）：

getGDCprojects()$project_id

  [1] "TCGA-BRCA"             "GENIE-MSK"            
 [3] "GENIE-VICC"            "GENIE-UHN"            
 [5] "CPTAC-2"               "CMI-ASC"              
 [7] "BEATAML1.0-COHORT"     "CGCI-BLGSP"           
 [9] "BEATAML1.0-CRENOLANIB" "CMI-MPC"              
[11] "CMI-MBC"               "GENIE-GRCC"           
[13] "GENIE-MDA"             "GENIE-JHU"            
[15] "GENIE-NKI"             "FM-AD"                
[17] "VAREPOP-APOLLO"        "WCDT-MCRPC"           
[19] "GENIE-DFCI"            "TARGET-ALL-P3"        
[21] "TARGET-ALL-P2"         "OHSU-CNL"             
[23] "TARGET-ALL-P1"         "MMRF-COMMPASS"        
[25] "TARGET-CCSK"           "ORGANOID-PANCREATIC"  
[27] "NCICCR-DLBCL"          "TARGET-NBL"           
[29] "TARGET-OS"             "TARGET-RT"            
[31] "TARGET-WT"             "TCGA-LAML"            
[33] "CGCI-HTMCP-CC"         "TARGET-AML"           
[35] "HCMI-CMDC"             "TCGA-DLBC"            
[37] "TCGA-CHOL"             "CTSP-DLBCL1"          
[39] "TRIO-CRU"              "TCGA-MESO"            
[41] "TCGA-ACC"              "TCGA-UCS"             
[43] "TCGA-KICH"             "TCGA-PCPG"            
[45] "TCGA-ESCA"             "TCGA-THYM"            
[47] "TCGA-TGCT"             "TCGA-UVM"             
[49] "TCGA-CESC"             "TCGA-BLCA"            
[51] "TCGA-PAAD"             "TCGA-LIHC"            
[53] "TCGA-SKCM"             "TCGA-UCEC"            
[55] "TCGA-PRAD"             "REBC-THYR"            
[57] "TCGA-THCA"             "TCGA-OV"              
[59] "TCGA-LGG"              "TCGA-SARC"            
[61] "CPTAC-3"               "TCGA-COAD"            
[63] "TCGA-READ"             "TCGA-KIRP"            
[65] "TCGA-GBM"              "TCGA-STAD"            
[67] "TCGA-LUAD"             "TCGA-KIRC"            
[69] "TCGA-LUSC"             "TCGA-HNSC"              

3.查看某个癌种（如头颈鳞状细胞癌）的数据类型（data.category）

TCGAbiolinks:::getProjectSummary("TCGA-HNSC")

$file_count
[1] 16694

$data_categories
  file_count case_count               data_category
1       3227        526       Copy Number Variation
2        573        528                    Clinical
3        354        354          Proteome Profiling
4       2776        528     Transcriptome Profiling
5       4104        510 Simple Nucleotide Variation
6       2858        528                 Biospecimen
7        580        528             DNA Methylation
8       2222        528            Sequencing Reads

$case_count
[1] 528

$file_s