diff fastq_dump_pe.Rmd @ 0:1a11c4fd13d0 draft

planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastq_dump commit 65063d5b207a70df38a0bcb6fb57a8f9170d9e9b
author mingchen0919
date Wed, 27 Sep 2017 21:41:29 -0400
parents
children 58d48d1157ed
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/fastq_dump_pe.Rmd	Wed Sep 27 21:41:29 2017 -0400
@@ -0,0 +1,54 @@
+---
+title: 'Fastq-dump: download and extract paired end reads into FASTQ/FASTA file'
+output:
+    html_document:
+      number_sections: true
+      toc: true
+      theme: cosmo
+      highlight: tango
+---
+
+```{r setup, include=FALSE, warning=FALSE, message=FALSE}
+knitr::opts_chunk$set(
+  echo = ECHO
+)
+```
+
+# Command line arguments
+
+```{r 'command line arguments'}
+str(opt)
+```
+
+# Download and extract reads
+
+```{r 'download and extract reads'}
+# create a directory to store read files
+dir.create('read_files_directory')
+# download and extract reads
+sra_accessions = strsplit(gsub(',', ' ', 'SRA_ACCESSION'), ' ')[[1]]
+sra_accessions = sra_accessions[sra_accessions != '']
+# loop through SRA accessions to download and extract reads.
+for(id in sra_accessions) {
+  if('FORMAT' == 'fasta') {
+    command = paste0('fastq-dump --fasta --split-files ', '-O read_files_directory ', id)
+  } else {
+    command = paste0('fastq-dump --split-files ', '-O read_files_directory ', id)
+  }
+  # fastq-dump command
+  print(command)
+  # command line stdout
+  system(command = command, intern = TRUE)
+}
+```
+
+
+# Rename files
+
+```{r}
+old_files = paste0('./read_files_directory/', list.files('./read_files_directory'))
+new_files = gsub('_1', '_forward', old_files)
+new_files = gsub('_2', '_reverse', new_files)
+file.rename(old_files, new_files)
+```
+