GDC annotations for male/female, stratified by tumor type

library(dplyr)
library(TCGAbiolinks)
library(SummarizedExperiment)

1 Get TCGA projects in GDC

projects <- getGDCprojects()[,c(7,9)]
projects[order(projects$project_id),] 

tcga.projects <- grep("TCGA",sort(projects$project_id),invert = FALSE,value = TRUE)
tcga.projects

##  [1] "TCGA-ACC"  "TCGA-BLCA" "TCGA-BRCA" "TCGA-CESC" "TCGA-CHOL" "TCGA-COAD"
##  [7] "TCGA-DLBC" "TCGA-ESCA" "TCGA-GBM"  "TCGA-HNSC" "TCGA-KICH" "TCGA-KIRC"
## [13] "TCGA-KIRP" "TCGA-LAML" "TCGA-LGG"  "TCGA-LIHC" "TCGA-LUAD" "TCGA-LUSC"
## [19] "TCGA-MESO" "TCGA-OV"   "TCGA-PAAD" "TCGA-PCPG" "TCGA-PRAD" "TCGA-READ"
## [25] "TCGA-SARC" "TCGA-SKCM" "TCGA-STAD" "TCGA-TGCT" "TCGA-THCA" "TCGA-THYM"
## [31] "TCGA-UCEC" "TCGA-UCS"  "TCGA-UVM"

2 Get clinical information

gender.by.project <- plyr::adply(tcga.projects,.margins = 1,.fun = function(proj) {
  clin <- GDCquery_clinic(proj)
    clin[,c("disease","bcr_patient_barcode","gender")]
},.id = NULL)

3 Final table

gender.by.project %>%
    as.data.frame() %>%
  DT::datatable(filter = 'top',
                style = "bootstrap",
                extensions = 'Buttons',
                options = list(scrollX = TRUE, 
                               dom = 'Bfrtip',
                               buttons = I('colvis'),
                               keys = TRUE, 
                               pageLength = 10), 
                rownames = FALSE,
                caption = "TCGA gender samples table")

4 Plots

gender.by.project %>% 
    dplyr::filter(gender %in% c("female","male")) %>% 
    plyr::count(vars = c("gender","disease"))  -> cts

cts

ggpubr::ggbarplot(cts,y = "freq",x = "gender",facet.by = "disease",color = "gender",fill = "gender")