changeset 7:efb1938c3020 draft

planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_bdss_client commit ea6df97960569d247d64be1549aa90768c9786f4-dirty
author mingchen0919
date Wed, 11 Oct 2017 13:21:54 -0400
parents 415ebc9016da
children 32e9649f6939
files bdss_client.Rmd bdss_client.xml bdss_client_render.R bdss_client_sra_pe.Rmd bdss_client_sra_se.Rmd
diffstat 5 files changed, 203 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client.Rmd	Wed Oct 11 13:21:54 2017 -0400
@@ -0,0 +1,59 @@
+---
+title: 'Download with BDSS client'
+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
+urls = strsplit(gsub(',', ' ', 'URLS'), ' ')[[1]]
+urls = urls[urls != '']
+# loop through SRA accessions to download and extract reads.
+for(url in urls) {
+    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
+    print(system(bdss_command, intern = TRUE))
+}
+move_files_command = 'find . -type f -print0 | xargs -0 mv -t ./read_files_directory'
+print(system(move_files_command, intern = TRUE))
+```
+
+* `fastq-dump` command
+```{r}
+print(command)
+```
+
+* `command line stdout`
+
+```{r}
+system(command = command, intern = TRUE)
+```
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client.xml	Wed Oct 11 13:21:54 2017 -0400
@@ -0,0 +1,46 @@
+<tool id="rmarkdown_bdss_client" name="BDSS client" version="1.0.0">
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="1.20.0">r-getopt</requirement>
+        <requirement type="package" version="1.2">r-rmarkdown</requirement>
+        <requirement type="package" version="0.3.5">r-htmltools</requirement>
+        <requirement type="package" version="0.5.0">r-dplyr</requirement>
+        <requirement type="package" version="0.5.4">parallel-fastq-dump</requirement>
+        <requirement type="package" version="1.95_4.8">r-rcurl</requirement>
+    </requirements>
+    <description>
+        Download data with BDSS client.
+    </description>
+    <stdio>
+        <!--All stderr are redirected to a file. "XXX" is used to match with nothing-->
+        <regex match="XXX"
+               source="stderr"
+               level="warning"
+               description="Check the warnings_and_errors.txt file for more details."/>
+    </stdio>
+    <command>
+        <![CDATA[
+            Rscript '${__tool_directory__}/bdss_client_render.R'
+                -i '$urls'
+                -e $echo
+
+                -r $report
+                -d $report.files_path
+                -s $sink_message
+
+                -t '${__tool_directory__}/bdss_client.Rmd'
+        ]]>
+    </command>
+    <inputs>
+        <param type="text" name="urls" label="URLs to data files" />
+        <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false"
+               label="Display analysis code in report?"/>
+    </inputs>
+    <outputs>
+        <data format="html" name="report" label="BDSS report"/>
+        <data name="output">
+            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory"/>
+        </data>
+        <data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/>
+    </outputs>
+</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_render.R	Wed Oct 11 13:21:54 2017 -0400
@@ -0,0 +1,93 @@
+##======= 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$URLs = c('urls', 'i', '1', 'character')
+spec_list$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)
+library(RCurl)
+
+#----- 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('URLS', opt$sra_accession, x)
+  }) %>%
+  (function(x) {
+    gsub('ECHO', opt$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
--- a/bdss_client_sra_pe.Rmd	Wed Oct 11 11:49:19 2017 -0400
+++ b/bdss_client_sra_pe.Rmd	Wed Oct 11 13:21:54 2017 -0400
@@ -31,8 +31,10 @@
 # loop through SRA accessions to download and extract reads.
 for(id in sra_accessions) {
   if (SRA_BOOLEAN) {
+    
     # build URL from SRA accession
-    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/',
+    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
+                 substr(id, 1, 3), '/',
                  substr(id, 1, 6), '/', id, '/', id, '.sra')
     # download sra file with bdss
     bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)
--- a/bdss_client_sra_se.Rmd	Wed Oct 11 11:49:19 2017 -0400
+++ b/bdss_client_sra_se.Rmd	Wed Oct 11 13:21:54 2017 -0400
@@ -42,7 +42,8 @@
   ## if SRA_BOOLEAN is TRUE, download .sra file and then convert it to fastq/fasta
   if (SRA_BOOLEAN) {
     # build URL from SRA accession
-    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/',
+    url = paste0('ftp://ftp.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/',
+                 substr(id, 1, 3), '/',
                  substr(id, 1, 6), '/', id, '/', id, '.sra')
     # download sra file with bdss
     bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer -u ', url)