# HG changeset patch
# User mingchen0919
# Date 1507681192 14400
# Node ID 614e9553f3660450acb82668ccc0af42c7c1c41b
planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_bdss_client commit 36de2ee9751d1ef5db0c76c217fd5ba262ca3739-dirty
diff -r 000000000000 -r 614e9553f366 bdss_client_sra_pe.Rmd
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_pe.Rmd Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,61 @@
+---
+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) {
+ # build URL from SRA accession
+ url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/',
+ substr(id, 1, 6), '/', id, '/', id, '.sra')
+ # download sra file with bdss
+ bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
+ system(bdss_command, intern = TRUE)
+ # convert .sra to .fastq/.fasta
+ 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)
+ }
+ # command line stdout
+ system(command = command, intern = TRUE)
+}
+# remove all .sra file
+system('rm *.sra', 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)
+```
+
diff -r 000000000000 -r 614e9553f366 bdss_client_sra_pe.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_pe.xml Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,50 @@
+
+
+ pandoc
+ r-getopt
+ r-rmarkdown
+ r-htmltools
+ r-dplyr
+ parallel-fastq-dump
+
+
+ Download and extract paired end reads in fastq or fasta format from NCBI SRA. The output is a list of paired datasets
+ collection.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r 614e9553f366 bdss_client_sra_pe_render.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_pe_render.R Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,96 @@
+##======= 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)
+})
+
+#/////////////////////// SINK WARNINGS AND ERRORS TO A FILE FOR DEBUGGING ///////////
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+
+# 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$REPORT_HTML = c('report_html', 'r', '1', 'character')
+spec_list$OUTPUT_DIR = c('output_dir', 'd', '1', 'character')
+spec_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
+##--------3. Rmd templates in the tool directory ----------
+spec_list$FASTQ_DUMP_PE_RMD = c('fastq_dump_pe_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 ------------------------
+dir.create(opt$output_dir)
+
+#----- 2. generate Rmd files with Rmd templates --------------
+# a. templates without placeholder variables:
+# copy templates from tool directory to the working directory.
+# b. templates with placeholder variables:
+# substitute variables with user input values and place them in the working directory.
+
+#----- 01 fastq_dump_pe.Rmd -----------------------
+readLines(opt$fastq_dump_pe_rmd) %>%
+ (function(x) {
+ gsub('SRA_ACCESSION', opt$sra_accession, x)
+ }) %>%
+ (function(x) {
+ gsub('FORMAT', opt$format, x)
+ }) %>%
+ (function(x) {
+ gsub('ECHO', opt$echo, x)
+ }) %>%
+ (function(x) {
+ gsub('OUTPUT_DIR', opt$output_dir, x)
+ }) %>%
+ (function(x) {
+ fileConn = file('fastq_dump_pe.Rmd')
+ writeLines(x, con=fileConn)
+ close(fileConn)
+ })
+
+#------ 3. render all Rmd files --------
+render('fastq_dump_pe.Rmd', output_file = opt$report_html)
+
+
+#-------4. manipulate outputs -----------------------------
+
+
+
+
+
+sink()
+#/////////// END OF SINK OUTPUT ///////////////////////////
\ No newline at end of file
diff -r 000000000000 -r 614e9553f366 bdss_client_sra_se.Rmd
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_se.Rmd Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,70 @@
+---
+title: 'Fastq-dump: download and extract single end reads into FASTQ/FASTA file'
+output:
+ html_document:
+ number_sections: true
+ toc: true
+ theme: cosmo
+ highlight: tango
+---
+
+```{r setup, include=FALSE, warning=FALSE, message=FALSE}
+knitr::opts_chunk$set(
+ echo = ECHO
+)
+```
+
+# Command line arguments
+
+```{r 'command line arguments'}
+str(opt)
+```
+
+# BDSS configuration file
+
+First, we create a bdss configuration file `bdss.cfg` in the current directory.
+
+```{r}
+system('echo "[metadata_repository]" > bdss.cfg')
+system('echo url=http://bdss.bioinfo.wsu.edu/ >> bdss.cfg')
+```
+
+# 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) {
+ # build URL from SRA accession
+ url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/',
+ substr(id, 1, 6), '/', id, '/', id, '.sra')
+ # download sra file with bdss
+ bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
+ system(bdss_command, intern = TRUE)
+ # convert .sra to .fastq/.fasta
+ if('FORMAT' == 'fasta') {
+ command = paste0('fastq-dump --fasta ', '-O read_files_directory ', id)
+ } else {
+ command = paste0('fastq-dump ', '-O read_files_directory ', id)
+ }
+}
+
+# remove all .sra file
+system('rm *.sra', intern = TRUE)
+```
+
+* `fastq-dump` command
+```{r}
+print(command)
+```
+
+* `command line stdout`
+
+```{r}
+system(command = command, intern = TRUE)
+```
+
diff -r 000000000000 -r 614e9553f366 bdss_client_sra_se.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_se.xml Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,48 @@
+
+
+ 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 614e9553f366 bdss_client_sra_se_render.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra_se_render.R Tue Oct 10 20:19:52 2017 -0400
@@ -0,0 +1,96 @@
+##======= 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)
+})
+
+#/////////////////////// SINK WARNINGS AND ERRORS TO A FILE FOR DEBUGGING ///////////
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+
+# 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$ECHO = c('echo', 'e', '1', 'character')
+##--------2. output report and outputs --------------
+spec_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
+spec_list$OUTPUT_DIR = c('output_dir', 'd', '1', 'character')
+spec_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
+##--------3. Rmd templates in the tool directory ----------
+spec_list$bdss_client_sra_se_RMD = c('bdss_client_sra_se_rmd', 't', '1', 'character')
+
+spec = t(as.data.frame(spec_list))
+opt = getopt(spec)
+
+#------ Load libraries ---------
+library(rmarkdown)
+library(htmltools)
+library(dplyr)
+
+#----- 1. create the report directory ------------------------
+dir.create(opt$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 bdss_client_sra_se.Rmd -----------------------
+readLines(opt$bdss_client_sra_se_rmd) %>%
+ (function(x) {
+ gsub('SRA_ACCESSION', opt$sra_accession, x)
+ }) %>%
+ (function(x) {
+ gsub('FORMAT', opt$format, x)
+ }) %>%
+ (function(x) {
+ gsub('ECHO', opt$echo, x)
+ }) %>%
+ (function(x) {
+ gsub('OUTPUT_DIR', opt$output_dir, x)
+ }) %>%
+ (function(x) {
+ fileConn = file('bdss_client_sra_se.Rmd')
+ writeLines(x, con=fileConn)
+ close(fileConn)
+ })
+
+#------ 3. render all Rmd files --------
+render('bdss_client_sra_se.Rmd', output_file = opt$report_html)
+
+
+#-------4. manipulate outputs -----------------------------
+
+
+
+
+
+sink()
+#/////////// END OF SINK OUTPUT ///////////////////////////
\ No newline at end of file