# HG changeset patch
# User mingchen0919
# Date 1506518748 14400
# Node ID 7ec600e7dba7964a9a0aeed151752652874051a1
planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastq_dump commit 6e3aaf47c3178dc89ad303c7fd398c08961064c0-dirty
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_pe.Rmd
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_pe.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/fastq_dump_pe.xml Wed Sep 27 09:25:48 2017 -0400
@@ -0,0 +1,57 @@
+
+
+ pandoc
+ r-getopt
+ r-rmarkdown
+ r-htmltools
+ r-dplyr
+ parallel-fastq-dump
+
+
+ Download and extract single end reads in fastq or fasta format from NCBI SRA. The output is a list of datasets
+ collection.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_pe_render.R
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_se.Rmd
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/fastq_dump_se.Rmd Wed Sep 27 09:25:48 2017 -0400
@@ -0,0 +1,41 @@
+---
+title: 'Fastq-dump: download and extract single 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 ', id, ' -O read_files_directory')
+ } else {
+ command = paste0('fastq-dump ', id, ' -O read_files_directory')
+ }
+ system(command = command)
+}
+```
+
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_se.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/fastq_dump_se.xml Wed Sep 27 09:25:48 2017 -0400
@@ -0,0 +1,52 @@
+
+
+ pandoc
+ r-getopt
+ r-rmarkdown
+ r-htmltools
+ r-dplyr
+ parallel-fastq-dump
+
+
+ Download and extract single end reads in fastq or fasta format from NCBI SRA. The output is a list of datasets
+ collection.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r 7ec600e7dba7 fastq_dump_se_render.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/fastq_dump_se_render.R Wed Sep 27 09:25:48 2017 -0400
@@ -0,0 +1,83 @@
+##======= Handle arguments from command line ========
+# setup R error handline to go to stderr
+options(show.error.messages=FALSE,
+ error=function(){
+ cat(geterrmessage(), file=stderr())
+ quit("no", 1, F)
+ })
+
+# we need that to not crash galaxy with an UTF8 error on German LC settings.
+loc = Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")
+
+# suppress warning
+options(warn = -1)
+
+options(stringsAsFactors=FALSE, useFancyQuotes=FALSE)
+args = commandArgs(trailingOnly=TRUE)
+
+suppressPackageStartupMessages({
+ library(getopt)
+ library(tools)
+})
+
+# column 1: the long flag name
+# column 2: the short flag alias. A SINGLE character string
+# column 3: argument mask
+# 0: no argument
+# 1: argument required
+# 2: argument is optional
+# column 4: date type to which the flag's argument shall be cast.
+# possible values: logical, integer, double, complex, character.
+##------- 1. input data ---------------------
+spec_list=list()
+spec_list$SRA_ACCESSION = c('sra_accession', 'i', '1', 'character')
+spec_list$FORMAT = c('format', 'f', '1', 'character')
+spec_list$ECHO = c('echo', 'e', '1', 'character')
+##--------2. output report and outputs --------------
+spec_list$FASTQ_DUMP_SE_HTML = c('fastq_dump_se_html', 'r', '1', 'character')
+spec_list$OUTPUT_DIR = c('output_dir', 'd', '1', 'character')
+##--------3. Rmd templates in the tool directory ----------
+spec_list$FASTQ_DUMP_SE_RMD = c('fastq_dump_se_rmd', 't', '1', 'character')
+
+spec = t(as.data.frame(spec_list))
+opt = getopt(spec)
+
+#------ Load libraries ---------
+library(rmarkdown)
+library(htmltools)
+library(dplyr)
+
+#----- 1. create the report directory ------------------------
+system(paste0('mkdir -p ', opt$output_dir))
+
+#----- 2. generate Rmd files with Rmd templates --------------
+# a. templates without placeholder variables:
+# copy templates from tool directory to the working directory.
+# b. templates with placeholder variables:
+# substitute variables with user input values and place them in the working directory.
+
+#----- 01 fastq_dump_se.Rmd -----------------------
+readLines(opt$fastq_dump_se_rmd) %>%
+ (function(x) {
+ gsub('SRA_ACCESSION', opt$file_list, x)
+ }) %>%
+ (function(x) {
+ gsub('ECHO', opt$echo, x)
+ }) %>%
+ (function(x) {
+ gsub('FORMAT', opt$format, x)
+ }) %>%
+ (function(x) {
+ gsub('OUTPUT_DIR', opt$fastq_dump_se_dir, x)
+ }) %>%
+ (function(x) {
+ fileConn = file('fastq_dump_se.Rmd')
+ writeLines(x, con=fileConn)
+ close(fileConn)
+ })
+
+#------ 3. render all Rmd files --------
+render('fastq_dump_se.Rmd', output_file = opt$fastq_dump_se_html)
+
+
+#-------4. manipulate outputs -----------------------------
\ No newline at end of file