Read length GDC

library(purrr)
library(GenomicDataCommons)

1 Query

query = files() %>%
  GenomicDataCommons::select(
    c(grep("length",available_fields('files'),value = TRUE),
      "file_name",
      "cases.samples.portions.submitter_id"
  )) %>%
    filter(~ cases.project.project_id == 'TCGA-GBM' &
               data_type == 'Aligned Reads' &
               experimental_strategy == 'RNA-Seq' &
               data_format == 'BAM') 

result <- query %>%  response_all() 
result <- result$results    

Some results are lists, we will unlist them.

result <- cbind(result, map_df(result$analysis$metadata$read_groups,~.x))
result <- cbind(result, map_df(result$cases,~.x))
result <- cbind(result, map_df(result$cases,~.x))
result <- cbind(result, map_df(result$samples,~.x))
result <- cbind(result, map_df(result$portions,~.x))

result <- result %>% dplyr::select(
    c("submitter_id",
      "read_length",
      "file_name",
      "file_id"
    )
)
head(result)

2 Results

result

dim(result)

## [1] 174   4

result[1,] %>% t

##              1                                                          
## submitter_id "TCGA-06-0211-01A-01"                                      
## read_length  "76"                                                       
## file_name    "b9e2c5fc-8cfb-4383-a5cf-8a1cc05eadc0_gdc_realn_rehead.bam"
## file_id      "a9080cf2-80e8-4453-8708-353ab0cbe82d"