changeset 0:512d008295db draft default tip

planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_bdss_client_main commit d9ab791a7ce12362dc6e28c0a518a3f23dd581fe-dirty
author mingchen0919
date Tue, 17 Oct 2017 14:09:01 -0400
parents
children
files bdss_client.Rmd bdss_client.xml bdss_client_render.R bdss_client_sra.Rmd bdss_client_sra.xml bdss_client_sra_render.R
diffstat 6 files changed, 440 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client.Rmd	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,52 @@
+---
+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,
+  error=TRUE
+)
+```
+
+# 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 data
+
+```{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) {
+    print(url)
+    bdss_command = paste0('/tool_deps/_conda/bin/bdss transfer --destination read_files_directory -u ', url)
+    print(bdss_command)
+    print(system(bdss_command, intern = TRUE))
+}
+# all files that need to be saved should be moved to REPORT_DIR directory
+# print(system('mv read_files_directory REPORT_DIR', intern = TRUE))
+```
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client.xml	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,47 @@
+<tool id="rmarkdown_bdss_client" name="BDSS client" version="1.0.3">
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="3.3.2">r-base</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" area="true" size="5x25" 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 client report"/>
+        <data name="output" label="BDSS downloaded data">
+            <discover_datasets pattern="__name_and_ext__" directory="read_files_directory" visible="true"/>
+        </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	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,82 @@
+library(getopt)
+library(rmarkdown)
+library(htmltools)
+library(dplyr)
+library(RCurl)
+
+
+##============ Sink warnings and errors to a file ==============
+## use the sink() function to wrap all code within it.
+##==============================================================
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+##---------below is the code for rendering .Rmd templates-----
+
+  ##=============STEP 1: handle command line arguments==========
+  ##
+  ##============================================================
+  # 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.
+  #-------------------------------------------------------------
+  #++++++++++++++++++++ Best practice ++++++++++++++++++++++++++
+  # 1. short flag alias should match the flag in the command section in the XML file.
+  # 2. long flag name can be any legal R variable names
+  # 3. two names in args_list can have common string but one name should not be a part of another name.
+  #    for example, one name is "ECHO", if another name is "ECHO_XXX", it will cause problems.
+  #+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+  ##------- 1. input data ---------------------
+  args_list=list()
+  args_list$URLS = c('urls', 'i', '1', 'character')
+  args_list$ECHO = c('echo', 'e', '1', 'character')
+  ##--------2. output report and outputs --------------
+  args_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
+  args_list$REPORT_DIR = c('report_dir', 'd', '1', 'character')
+  args_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
+  ##--------3. Rmd templates in the tool directory ----------
+  args_list$BDSS_CLIENT_RMD = c('bdss_client_rmd', 't', '1', 'character')
+  
+  opt = getopt(t(as.data.frame(args_list)))
+  
+  
+  ##=======STEP 2: create report directory (optional)==========
+  ##
+  ##===========================================================
+  dir.create(opt$report_dir)
+  
+  ##=STEP 3: replace placeholders in .Rmd with argument values=
+  ##
+  ##===========================================================
+  #++ need to replace placeholders with args values one by one+
+  #----- 01 bdss_client.Rmd -----------------------
+  readLines(opt$bdss_client_rmd) %>%
+    (function(x) {
+      gsub('URLS', opt$urls, x)
+    }) %>%
+    (function(x) {
+      gsub('ECHO', opt$echo, x)
+    }) %>%
+    (function(x) {
+      gsub('REPORT_DIR', opt$report_dir, x)
+    }) %>%
+    (function(x) {
+      fileConn = file('bdss_client.Rmd')
+      writeLines(x, con=fileConn)
+      close(fileConn)
+    })
+  
+  ##=============STEP 4: render .Rmd templates=================
+  ##
+  ##===========================================================
+  render('bdss_client.Rmd', output_file = opt$report_html)
+
+
+##--------end of code rendering .Rmd templates----------------
+sink()
+##=========== End of sinking output=============================
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra.Rmd	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,105 @@
+---
+title: 'Download and extract single end fastq/fasta data with BDSS client from SRA accessions'
+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,
+  error=TRUE
+)
+```
+
+# 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 two directories, one for single end and the other for paired end SRA reads.
+dir.create('se_read_files_directory')
+dir.create('pe_read_files_directory')
+# download and extract reads (single end)
+sra_ids_se = strsplit(gsub(',', ' ', 'SRA_IDS_SE'), ' ')[[1]]
+sra_ids_se = sra_ids_se[sra_ids_se != '']
+# loop through SRA accessions to download and extract reads.
+for(id in sra_ids_se) {
+    # build URL from SRA id
+    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)
+    system(bdss_command, intern = TRUE)
+    # convert .sra to .fastq/.fasta
+    if('FORMAT' == 'fasta') {
+      command = paste0('fastq-dump --fasta -O se_read_files_directory ', id, '.sra')
+    } else {
+      command = paste0('fastq-dump -O se_read_files_directory ', id, '.sra')
+    }
+    cat('----convert SRA to fastq/fasta------\n')
+    print(system(command, intern = TRUE))
+}
+
+# download and extract reads (paired end)
+sra_ids_pe = strsplit(gsub(',', ' ', 'SRA_IDS_PE'), ' ')[[1]]
+sra_ids_pe = sra_ids_pe[sra_ids_pe != '']
+# loop through SRA accessions to download and extract reads.
+for(id in sra_ids_pe) {
+    # build URL from SRA id
+    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)
+    system(bdss_command, intern = TRUE)
+    # convert .sra to .fastq/.fasta
+    if('FORMAT' == 'fasta') {
+      command = paste0('fastq-dump --fasta --split-files -O pe_read_files_directory ', id, '.sra')
+    } else {
+      command = paste0('fastq-dump --split-files -O pe_read_files_directory ', id, '.sra')
+    }
+    cat('----convert SRA to fastq/fasta------\n')
+    command_stdout = system(command, intern = TRUE)
+    print(command_stdout)
+    if(!(paste0(id, '_2.FORMAT') %in% list.files('pe_read_files_directory'))) {
+      # this is not a paired end SRA file. The corresponding file will be deleted.
+      cat(paste0(id, ' is not paired end SRA, the corresponding fastq/fasta file will deleted.'))
+      system(paste0('rm pe_read_files_directory/', id, '_1.*'), intern = TRUE)
+    }
+    
+}
+
+cat('-----single end files----\n')
+list.files('./se_read_files_directory')
+cat('-----paired end files----\n')
+list.files('./pe_read_files_directory')
+
+cat('-----Renaming files------\n')
+# rename files for paired end reads
+old_files = paste0('./pe_read_files_directory/', list.files('./pe_read_files_directory'))
+print(old_files)
+new_files = gsub('_1', '_forward', old_files)
+new_files = gsub('_2', '_reverse', new_files)
+print(new_files)
+file.rename(old_files, new_files)
+```
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bdss_client_sra.xml	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,64 @@
+<tool id="rmarkdown_bdss_client_sra" name="BDSS client SRA" version="1.0.3">
+    <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement>
+        <requirement type="package" version="3.3.2">r-base</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 and generate list (single end SRA data) and list:paired dataset collection
+        (paired end SRA data).
+    </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_sra_render.R'
+                -i '$sra_ids_se'
+                -p '$sra_ids_pe'
+                -f $format
+                -e $echo
+
+                -r $report
+                -d $report.files_path
+                -s $sink_message
+
+                -t '${__tool_directory__}/bdss_client_sra.Rmd'
+        ]]>
+    </command>
+    <inputs>
+        <param type="text" name="sra_ids_se" area="true" size="5x25" label="SRR/DRR/ERR accessions of single end SRA"
+               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR039885"/>
+        <param type="text" name="sra_ids_pe" area="true" size="5x25" label="SRR/DRR/ERR accessions of paired end SRA"
+               help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. ERR1748507"/>
+        <param type="select" name="format" label="Output format">
+            <option value="fastq" selected="true">fastq</option>
+            <option value="fasta">fasta</option>
+        </param>
+        <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 client report"/>
+        <!--list dataset collection for single end SRA data-->
+        <collection type="list" name="list_collection" label="BDSS download data (single end reads)">
+            <discover_datasets pattern="__name_and_ext__" directory="se_read_files_directory"/>
+        </collection>
+        <!--list:paired dataset collection for paired end SRA data-->
+        <collection type="list:paired" name="list:paired_collection" label="BDSS download data (paired end reads)">
+            <discover_datasets
+                    pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.(?P&lt;ext&gt;[^\._]+)?"
+                    directory="pe_read_files_directory"/>
+        </collection>
+        <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_sra_render.R	Tue Oct 17 14:09:01 2017 -0400
@@ -0,0 +1,90 @@
+library(getopt)
+library(rmarkdown)
+library(htmltools)
+library(dplyr)
+library(RCurl)
+
+
+##============ Sink warnings and errors to a file ==============
+## use the sink() function to wrap all code within it.
+##==============================================================
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+##---------below is the code for rendering .Rmd templates-----
+
+##=============STEP 1: handle command line arguments==========
+##
+##============================================================
+# 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.
+#-------------------------------------------------------------
+#++++++++++++++++++++ Best practice ++++++++++++++++++++++++++
+# 1. short flag alias should match the flag in the command section in the XML file.
+# 2. long flag name can be any legal R variable names
+# 3. two names in args_list can have common string but one name should not be a part of another name.
+#    for example, one name is "ECHO", if another name is "ECHO_XXX", it will cause problems.
+#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+##------- 1. input data ---------------------
+args_list=list()
+args_list$SRA_IDS_SE = c('sra_ids_se', 'i', '1', 'character')
+args_list$SRA_IDS_PE = c('sra_ids_pe', 'p', '1', 'character')
+args_list$FORMAT = c('format', 'f', '1', 'character')
+args_list$ECHO = c('echo', 'e', '1', 'character')
+##--------2. output report and outputs --------------
+args_list$REPORT_HTML = c('report_html', 'r', '1', 'character')
+args_list$REPORT_DIR = c('report_dir', 'd', '1', 'character')
+args_list$SINK_OUTPUT = c('sink_message', 's', '1', 'character')
+##--------3. Rmd templates in the tool directory ----------
+args_list$BDSS_CLIENT_RMD = c('bdss_client_rmd', 't', '1', 'character')
+
+opt = getopt(t(as.data.frame(args_list)))
+
+
+##=======STEP 2: create report directory (optional)==========
+##
+##===========================================================
+dir.create(opt$report_dir)
+
+##=STEP 3: replace placeholders in .Rmd with argument values=
+##
+##===========================================================
+#++ need to replace placeholders with args values one by one+
+#----- 01 bdss_client.Rmd -----------------------
+readLines(opt$bdss_client_rmd) %>%
+  (function(x) {
+    gsub('SRA_IDS_SE', opt$sra_ids_se, x)
+  }) %>%
+  (function(x) {
+    gsub('SRA_IDS_PE', opt$sra_ids_pe, x)
+  }) %>%
+  (function(x) {
+    gsub('FORMAT', opt$format, x)
+  }) %>%
+  (function(x) {
+    gsub('ECHO', opt$echo, x)
+  }) %>%
+  (function(x) {
+    gsub('REPORT_DIR', opt$report_dir, x)
+  }) %>%
+  (function(x) {
+    fileConn = file('bdss_client.Rmd')
+    writeLines(x, con=fileConn)
+    close(fileConn)
+  })
+
+##=============STEP 4: render .Rmd templates=================
+##
+##===========================================================
+render('bdss_client.Rmd', output_file = opt$report_html)
+
+
+##--------end of code rendering .Rmd templates----------------
+sink()
+##=========== End of sinking output=============================
\ No newline at end of file