get_all_clin.R

# This code will get all clinical indexed data from TCGA
library(TCGAbiolinks)
library(data.table)
clinical <- TCGAbiolinks:::getGDCprojects()$project_id %>% 
            regexPipes::grep("TCGA",value=T) %>% 
            sort %>% 
            plyr::alply(1,GDCquery_clinic, .progress = "text") %>% 
            rbindlist
readr::write_csv(clinical,path = paste0("all_clin_indexed.csv"))

# This code will get all clinical XML data from TCGA
getclinical <- function(proj){
    message(proj)
    while(1){
        result = tryCatch({
            query <- GDCquery(project = proj, data.category = "Clinical")
            GDCdownload(query)
            clinical <- GDCprepare_clinic(query, clinical.info = "patient")
            for(i in c("admin","radiation","follow_up","drug","new_tumor_event")){
                message(i)
                aux <- GDCprepare_clinic(query, clinical.info = i)
                if(is.null(aux)) next
                # add suffix manually if it already exists
                replicated <- which(grep("bcr_patient_barcode",colnames(aux), value = T,invert = T) %in% colnames(clinical))
                colnames(aux)[replicated] <- paste0(colnames(aux)[replicated],".",i)
                if(!is.null(aux)) clinical <- merge(clinical,aux,by = "bcr_patient_barcode", all = TRUE)
            }
            readr::write_csv(clinical,path = paste0(proj,"_clinical_from_XML.csv")) # Save the clinical data into a csv file
            return(clinical)
        }, error = function(e) {
            message(paste0("Error clinical: ", proj))
        })
    }
}
clinical <- TCGAbiolinks:::getGDCprojects()$project_id %>% 
    regexPipes::grep("TCGA",value=T) %>% 
    sort %>% 
    plyr::alply(1,getclinical, .progress = "text") %>% 
    rbindlist(fill = TRUE) %>% setDF
readr::write_csv(clinical,path = paste0("all_clin_XML.csv"))

# Get all batch numbers for each patient
library(TCGAbiolinks)
getBatch <- function(proj){
    message(proj)
    while(1){
        result = tryCatch({
            query <- GDCquery(project = proj, data.category = "Biospecimen")
            GDCdownload(query)
            clinical <- GDCprepare_clinic(query, clinical.info = "admin")
            readr::write_csv(clinical,path = paste0(proj,"_batch_from_XML.csv")) # Save the clinical data into a csv file
            return(clinical)
        }, error = function(e) {
            message(paste0("Error clinical: ", proj))
        })
    }
}
biospecimen <- TCGAbiolinks:::getGDCprojects()$project_id %>% 
    regexPipes::grep("TCGA",value=T) %>% 
    sort %>% 
    plyr::alply(1,getBatch, .progress = "text") %>% 
    rbindlist(fill = TRUE) %>% setDF

readr::write_csv(biospecimen,path = paste0("biospecimen_from_XML.csv"))

merge_clin.md

From this post https://support.bioconductor.org/p/89315/

library('TCGAbiolinks')
library('plyr')
library('devtools')
projects <- TCGAbiolinks:::getGDCprojects()$project_id
projects <- projects[grepl('^TCGA', projects, perl = TRUE)]

clin <- lapply(projects, function(p) {
    message(paste(Sys.time(), 'processing project', p))
    result <- tryCatch({
        query <- GDCquery(project = p, data.category = 'Clinical')
        GDCdownload(query)
        GDCprepare_clinic(query, clinical.info = 'patient')
    }, error = function(e) {
        message(paste0('Error clinical: ', p))
        return(NULL)
    })
    return(result)
})
names(clin) <- projects

## Merge all
clin_all <- rbind.fill(clin)

## Fix columns that have '' that should be NAs
for(j in seq_len(ncol(clin_all))) {
    i <- which(clin_all[, j] == '')
    if(length(i) > 0) clin_all[i, j] <- NA
}

save(clin_all, file = 'clin_all.Rdata')

write.table(clin_all, file = 'clin_all.tsv', quote = FALSE, row.names = FALSE,
    sep = '\t')

## Reproducibility info
Sys.time()
options(width = 120)
session_info()