Downloading GEO data

Aims

In this report, I download the 3409 breast cancer bulk RNA-seq samples and the corresponding clinical annotations, associated with the study: Clinical Value of RNA Sequencing-Based Classifiers for Prediction of the Five Conventional Breast Cancer Biomarkers: A Report From the Population-Based Multicenter Sweden Cancerome Analysis Network—Breast Initiative (GSE96058).

Get clinical features

if(!dir.exists(here::here('data')))
  dir.create(here::here('data'))

## get geo obj
geo <- getGEO(GEO = "GSE96058", GSEMatrix = FALSE)

## fetch metadata
meta <- purrr::map(geo@gsms, ~.x@header$characteristics_ch1) |>
  stack() |>
  tidyr::separate(values, into = c("feature", "value"), sep= ": ") |>
  tidyr::pivot_wider(names_from= feature, values_from = value) |>
  janitor::clean_names()

## map samples
sample <- purrr::map(geo@gsms, ~.x@header$title) |>
  stack() |>
  as_tibble() |>
  mutate(ind = as.character(ind))

## store metadata
meta <- left_join(sample, meta, by = 'ind') |>
  write_csv(here::here("data/metadata.csv"))

Get gene expression profiles

success <- FALSE
attempt <- 1
while (!success && attempt <= 5) {
  tryCatch({
    getGEOSuppFiles("GSE96058", makeDirectory = FALSE,
                    baseDir = here::here('data'),
                    fetch_files = TRUE, filter_regex = 'gene_expression')
    success <- TRUE
    message("Download successful on attempt ", attempt)
  }, error = function(e) {
    message("Download failed on attempt ", attempt, ": ", e$message)
    attempt <<- attempt + 1
    Sys.sleep(5) # wait before retrying
  })
}
if (!success)
  stop(sprintf("Download failed after %s attempts", attempt))