Mercurial > repos > mingchen0919 > rmarkdown_fastq_dump
changeset 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 | cd86400bbaed |
| files | fastq_dump_pe.Rmd fastq_dump_pe.xml fastq_dump_pe_render.R fastq_dump_se.Rmd fastq_dump_se.xml fastq_dump_se_render.R |
| diffstat | 6 files changed, 395 insertions(+), 0 deletions(-) [+] |
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) +``` +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastq_dump_pe.xml Wed Sep 27 21:41:29 2017 -0400 @@ -0,0 +1,50 @@ +<tool id="rmarkdown_fastqc_dump_pe" name="fastqc-dump-pe" 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> + </requirements> + <description> + Download and extract paired end reads in fastq or fasta format from NCBI SRA. The output is a list of paired datasets + collection. + </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__}/fastq_dump_pe_render.R' + -i '$sra_accession' + -e $echo + -f $format + + -r $report + -d $report.files_path + -s $sink_message + + -t '${__tool_directory__}/fastq_dump_pe.Rmd' + ]]> + </command> + <inputs> + <param type="text" name="sra_accession" label="SRR/DRR/ERR accessions" optional="false" + help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR6077558,ERR343809"/> + <param type="boolean" name="format" truevalue="fastq" falsevalue="fasta" checked="true" + label="output files in fastq (Yes) or fasta (No)?"/> + <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="Fastq-dump report" /> + <collection type="list:paired" name="list_collection" label="Fastq-dump (paired end reads)"> + <discover_datasets pattern="(?P<identifier_0>[^_]+)_(?P<identifier_1>[^_]+)\.(?P<ext>[^\._]+)?" directory="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/fastq_dump_pe_render.R Wed Sep 27 21:41:29 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
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastq_dump_se.Rmd Wed Sep 27 21:41:29 2017 -0400 @@ -0,0 +1,51 @@ +--- +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$set( + echo = ECHO +) +``` + +# Command line arguments + +```{r 'command line arguments'} +str(opt) +``` + +# Download and extract reads + +```{r 'download and extract reads'} +# create a directory to store read files +dir.create('read_files_directory') +# download and extract reads +sra_accessions = strsplit(gsub(',', ' ', 'SRA_ACCESSION'), ' ')[[1]] +sra_accessions = sra_accessions[sra_accessions != ''] +# loop through SRA accessions to download and extract reads. +for(id in sra_accessions) { + if('FORMAT' == 'fasta') { + command = paste0('fastq-dump --fasta ', '-O read_files_directory ', id) + } else { + command = paste0('fastq-dump ', '-O read_files_directory ', id) + } +} +``` + +* `fastq-dump` command +```{r} +print(command) +``` + +* `command line stdout` + +```{r} +system(command = command, intern = TRUE) +``` +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastq_dump_se.xml Wed Sep 27 21:41:29 2017 -0400 @@ -0,0 +1,48 @@ +<tool id="rmarkdown_fastqc_dump_se" name="fastqc-dump-se" version="1.0.0"> + <requirements> + <requirement type="package" version="1.15.0.6-0">pandoc</requirement> + <requirement type="package" version="1.20.0">r-getopt</requirement> + <requirement type="package" version="1.2">r-rmarkdown</requirement> + <requirement type="package" version="0.3.5">r-htmltools</requirement> + <requirement type="package" version="0.5.0">r-dplyr</requirement> + <requirement type="package" version="0.5.4">parallel-fastq-dump</requirement> + </requirements> + <description> + Download and extract single end reads in fastq or fasta format from NCBI SRA. The output is a list of datasets + collection. + </description> + <stdio> + <!--All stderr are redirected to a file. "XXX" is used to match with nothing--> + <regex match="XXX" + source="stderr" + level="warning" + description="Check the warnings_and_errors.txt file for more details." /> + </stdio> + <command> + <![CDATA[ + Rscript '${__tool_directory__}/fastq_dump_se_render.R' + -i '$sra_accession' + -e $echo + -f $format + + -r $report + -d $report.files_path + -s $sink_message + + -t '${__tool_directory__}/fastq_dump_se.Rmd' + ]]> + </command> + <inputs> + <param type="text" name="sra_accession" label="SRR/DRR/ERR accessions" + help="A list of SRR/DRR/ERR accessions separated by comma or space. e.g. SRR6077558,ERR343809"/> + <param type="boolean" name="format" truevalue="fastq" falsevalue="fasta" checked="true" label="output files in fastq (Yes) or fasta (No)?"/> + <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="Fastq-dump report" /> + <collection type="list" name="list_collection" label="Fastq-dump (single end reads)"> + <discover_datasets pattern="__name_and_ext__" directory="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/fastq_dump_se_render.R Wed Sep 27 21:41:29 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$FASTQ_DUMP_SE_RMD = c('fastq_dump_se_rmd', 't', '1', 'character') + +spec = t(as.data.frame(spec_list)) +opt = getopt(spec) + +#------ Load libraries --------- +library(rmarkdown) +library(htmltools) +library(dplyr) + +#----- 1. create the report directory ------------------------ +dir.create(opt$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_se.Rmd ----------------------- +readLines(opt$fastq_dump_se_rmd) %>% + (function(x) { + gsub('SRA_ACCESSION', opt$sra_accession, x) + }) %>% + (function(x) { + gsub('FORMAT', opt$format, x) + }) %>% + (function(x) { + gsub('ECHO', opt$echo, x) + }) %>% + (function(x) { + gsub('OUTPUT_DIR', opt$output_dir, x) + }) %>% + (function(x) { + fileConn = file('fastq_dump_se.Rmd') + writeLines(x, con=fileConn) + close(fileConn) + }) + +#------ 3. render all Rmd files -------- +render('fastq_dump_se.Rmd', output_file = opt$report_html) + + +#-------4. manipulate outputs ----------------------------- + + + + + +sink() +#/////////// END OF SINK OUTPUT /////////////////////////// \ No newline at end of file