Read a tabular file including 2 columns: ID and URLs, scan urls to read files for each ID, generate a bash file to download the scanned URLs using ascp

download.r

library(readxl)
library(readr)
library(dplyr)
library(stringr)
library(glue)

setwd("~/Documents/bioinformatics/")
ids <- read_excel("NCTC_pacbio.xlsx", col_names = c("strains", "run_acc")) %>% 
  mutate(run_acc = gsub("https://www.ebi.ac.uk/ena/data/view/", "", run_acc)) %>% 
  mutate(run_acc_url = glue("https://www.ebi.ac.uk/ena/data/warehouse/filereport?accession={run_acc}&result=read_run&fields=run_accession,submitted_ftp,submitted_md5"))

url_to_replace <- "ftp.sra.ebi.ac.uk/"
url_replace_by <- "[email protected]:/"

aspc_command <- "ascp -QT -l 300m -P33001 -i \"/Users/leviet/Applications/Aspera CLI/etc/asperaweb_id_dsa.openssh\""
sh_file <- "download.sh"

if (file.exists(sh_file)) {
  file.remove(ssh_file)
}

for (i in seq_along(ids$run_acc_url)) {
  output <- ids$strains[i]
  tbl <- read.table(ids$run_acc_url[i], header = T) %>% 
    pull(submitted_ftp) %>% 
    as.character() %>% 
    str_split(";") %>% 
    unlist() %>% 
    gsub(url_to_replace,url_replace_by,.)  
  
  for( i in seq_along(tbl) ){
    ext <- case_when(
      grepl("1.bax.h5", tbl[i]) ~ ".1.bax.h5",
      grepl("2.bax.h5", tbl[i]) ~ ".2.bax.h5",
      grepl("3.bax.h5", tbl[i]) ~ ".3.bax.h5",
      grepl("bas.h5", tbl[i]) ~ ".bas.h5",
      grepl("metadata", tbl[i]) ~ ".metadata.xml"
    )
    line <- glue("{aspc_command} {tbl[i]} {output}{ext}\n")
    write(line,sh_file,append = T)
  }
  
}

samples.tsv