Mercurial > repos > mingchen0919 > aurora_fastqc_site
changeset 8:94762f1cb779 draft
planemo upload commit 76f9ca75d5b1c0c0fad6c10876d9dfeba7d5ecff-dirty
| author | mingchen0919 |
|---|---|
| date | Mon, 30 Apr 2018 16:15:39 -0400 |
| parents | 3f92c10de274 |
| children | 9e7e22e4eb08 |
| files | 01_evaluation_overview.Rmd 02_per_base_sequence_quality.Rmd 03_per_tile_sequence_quality.Rmd 04_per_sequence_quality_score.Rmd 05_per_base_sequence_content.Rmd 06_per_sequence_gc_content.Rmd 07_per_base_n_content.Rmd 08_sequence_length_distribution.Rmd 09_sequence_duplication_levels.Rmd 10_adapter_content.Rmd 11_kmer_content.Rmd _site.yml build-and-run-job-scripts.sh command-line-arguments.csv expose-outputs-to-galaxy-history.sh expose-outputs.sh fastqc_site.xml fastqc_site_render.R getopt_specification.csv helper.R index.Rmd rmarkdown_report.xml rmarkdown_report_render.R shell-script-template.sh |
| diffstat | 24 files changed, 399 insertions(+), 387 deletions(-) [+] |
line wrap: on
line diff
--- a/01_evaluation_overview.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/01_evaluation_overview.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -9,23 +9,20 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` # Run FastQC ```{bash} -sh ${TOOL_INSTALL_DIR}/shell-script-template.sh +sh ${TOOL_INSTALL_DIR}/build-and-run-job-scripts.sh ``` ```{r echo=FALSE,results='asis'} # display fastqc job script cat('```bash\n') -cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/fastqc.sh')), sep = '\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/job-1-script.sh')), sep = '\n') cat('\n```') ```
--- a/02_per_base_sequence_quality.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/02_per_base_sequence_quality.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,14 +3,10 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` - ### Per base sequence quality ```{r 'per base sequence quality', fig.width=10}
--- a/03_per_tile_sequence_quality.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/03_per_tile_sequence_quality.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Per tile sequence quality
--- a/04_per_sequence_quality_score.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/04_per_sequence_quality_score.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,14 +3,10 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` - ### Per sequence quality score ```{r 'Per sequence quality score', fig.width=10}
--- a/05_per_base_sequence_content.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/05_per_base_sequence_content.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,14 +3,10 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` - ### Per base sequence content ```{r 'Per base sequence content', fig.width=10}
--- a/06_per_sequence_gc_content.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/06_per_sequence_gc_content.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Per sequence GC content
--- a/07_per_base_n_content.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/07_per_base_n_content.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Per base N content
--- a/08_sequence_length_distribution.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/08_sequence_length_distribution.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Sequence Length Distribution
--- a/09_sequence_duplication_levels.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/09_sequence_duplication_levels.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ```
--- a/10_adapter_content.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/10_adapter_content.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Adapter Content
--- a/11_kmer_content.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/11_kmer_content.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -3,11 +3,8 @@ --- ```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set( - echo = as.logical(opt$X_e), - error = TRUE, - eval = TRUE -) +knitr::opts_knit$set(progress = FALSE) +knitr::opts_chunk$set(error = TRUE, echo = FALSE) ``` ### Kmer Content {.tabset}
--- a/_site.yml Mon Apr 30 10:15:54 2018 -0400 +++ b/_site.yml Mon Apr 30 16:15:39 2018 -0400 @@ -4,9 +4,6 @@ title: "FastQC" type: inverse left: - - text: "Home" - icon: fa-home - href: index.html - text: "Evaluation Overview" href: 01_evaluation_overview.html - text: "Evaluation by data module" @@ -31,6 +28,7 @@ href: 10_adapter_content.html - text: "Kmer Content" href: 11_kmer_content.html + output: html_document: theme: cosmo
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/build-and-run-job-scripts.sh Mon Apr 30 16:15:39 2018 -0400 @@ -0,0 +1,32 @@ +# run SHELL_SCRIPT within tool outputs directory +cd ${REPORT_FILES_PATH} + +# build job-script.sh +cat >temp.sh <<EOF + +cp ${X_r} read_1.fq +cp ${X_R} read_2.fq + +fastqc \\ + -q \\ + -c ${X_c} \\ + -l ${X_l} \\ + ${X_d}/read_1.fq > read_1.log.txt 2>&1 + +fastqc \\ + -q \\ + -c ${X_c} \\ + -l ${X_l} \\ + ${X_d}/read_2.fq > read_2.log.txt 2>&1 + +EOF + +grep -v None temp.sh > job-1-script.sh +rm temp.sh + +# run SHELL_SCRIPT +sh job-1-script.sh + +# unzip outputs +unzip -q read_1_fastqc.zip +unzip -q read_2_fastqc.zip \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/command-line-arguments.csv Mon Apr 30 16:15:39 2018 -0400 @@ -0,0 +1,9 @@ +short flag,argument mask,data type,variable name +o,1,character,report +d,1,character,report.files_path +r,1,character,reads_1 +n,1,character,reads_1.name +R,1,character,reads_2 +N,1,character,reads_2.name +c,1,character,contaminants +l,1,character,limits \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/expose-outputs-to-galaxy-history.sh Mon Apr 30 16:15:39 2018 -0400 @@ -0,0 +1,11 @@ +# change directory to tool outputs directory +cd ${REPORT_FILES_PATH} + +# copy outputs from tool outputs directory to corresponding galaxy output path +if [ -e rmarkdown_report.html ]; then + cp rmarkdown_report.html ${REPORT} +fi + +if [ -e index.html ]; then + cp index.html ${REPORT} +fi
--- a/expose-outputs.sh Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,5 +0,0 @@ -# change directory to tool outputs directory -cd ${REPORT_FILES_PATH} - -# copy outputs from tool outputs directory to corresponding galaxy output path -cp index.html ${REPORT} \ No newline at end of file
--- a/fastqc_site.xml Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,124 +0,0 @@ -<tool name="aurora_fastqc_site" id='aurora_fastqc_site' version="2.2.1"> - <description> - Evaluate short reads with FastQC software on a single or a paired of untrimmed and trimmed reads - files. - </description> - <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="1.3">r-rmarkdown</requirement> - <requirement type="package" version="1.8.4">r-plyr</requirement> - <requirement type="package" version="1.1.0">r-stringr</requirement> - <requirement type="package" version="0.2">r-dt</requirement> - <requirement type="package" version="1.4.2">r-reshape2</requirement> - <requirement type="package" version="4.5.6">r-plotly</requirement> - <requirement type="package" version="0.3.5">r-htmltools</requirement> - <requirement type="package" version="0.11.5">fastqc</requirement> - <requirement type="package" version="0.9.10">xorg-libxrender</requirement> - <requirement type="package" version="1.2.2">xorg-libsm</requirement> - <requirement type="package" version="6.0">unzip</requirement> - </requirements> - <stdio> - <regex match="XXX" source="stderr" level="warning" - description="Check the warnings_and_errors.txt file for more details."/> - </stdio> - <command><![CDATA[ - - ######### each aurora tool generates a html file and have an files path directory associated with it. - mkdir -p $report.files_path && - - ######### three important paths: - ######### 1. path to tool installation directory - ######### 2. path to report html - ######### 3. path to files_path directory associated with the report output. - export TOOL_INSTALL_DIR='${__tool_directory__}' && - export REPORT='$report' && - export REPORT_FILES_PATH='$report.files_path' && - - ############ copy jstree directory cp -r ${__tool_directory__}/vakata-jstree-3.3.5 ./ && - - ############ create a hidden file to store r markdown rendering log - touch $report.files_path/.r_rendering.log.txt && - - Rscript '${__tool_directory__}/fastqc_site_render.R' - - -o $report - -d $report.files_path - - -r $reads_1 - -n '$reads_1.name' - -R $reads_2 - -N '$reads_2.name' - -c $contaminants - -l $limits - - ]]></command> - <inputs> - <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="reads_1" type="data" optional="false" - label="Short reads before trimming" - help="Short reads data from history. This could be reads before trimming."/> - <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="reads_2" type="data" label="Short reads after trimming" - help="Short reads data from history. This could be reads after trimming."/> - <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list" - help="Specifies a non-default file which contains the list of adapter sequences which will be explicitly - searched against the library. The file must contain sets of named adapters in the form name[tab]sequence. - Lines prefixed with a hash will be ignored."/> - <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file" - help="Specifies a non-default file which contains a set of criteria which will be used to determine the - warn/error limits for the various modules. This file can also be used to selectively remove some modules - from the output all together. The format needs to mirror the default limits.txt file found in the - Configuration folder."/> - - </inputs> - <outputs> - <data format="html" name="report" label="${tool.name} on ${on_string}"/> - </outputs> - <citations> - <citation type="bibtex"><![CDATA[ - @misc{bioinformatics2014fastqc, - title={FastQC}, - author={Bioinformatics, Babraham}, - year={2014} - } - ]]></citation> - <citation type="bibtex"><![CDATA[ - @article{allaire2016rmarkdown, - title={rmarkdown: Dynamic Documents for R, 2016}, - author={Allaire, J and Cheng, Joe and Xie, Yihui and McPherson, Jonathan and Chang, Winston and Allen, Jeff - and Wickham, Hadley and Atkins, Aron and Hyndman, Rob}, - journal={R package version 0.9}, - volume={6}, - year={2016} - } - ]]></citation> - <citation type="bibtex"><![CDATA[ - @book{xie2015dynamic, - title={Dynamic Documents with R and knitr}, - author={Xie, Yihui}, - volume={29}, - year={2015}, - publisher={CRC Press} - } - ]]></citation> - <citation type="bibtex"><![CDATA[ - @misc{plotly2017, - title = {plotly: Create Interactive Web Graphics via 'plotly.js'}, - author = {Carson Sievert and Chris Parmer and Toby Hocking and Scott Chamberlain and Karthik Ram and - Marianne Corvellec and Pedro Despouy}, - year = {2017}, - note = {R package version 4.6.0}, - url = {https://CRAN.R-project.org/package=plotly}, - } - ]]></citation> - <citation type="bibtex"><![CDATA[ - @Book{ggplot22016, - author = {Hadley Wickham}, - title = {ggplot2: Elegant Graphics for Data Analysis}, - publisher = {Springer-Verlag New York}, - year = {2009}, - isbn = {978-0-387-98140-6}, - url = {http://ggplot2.org}, - } - ]]></citation> - </citations> -</tool> \ No newline at end of file
--- a/fastqc_site_render.R Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,54 +0,0 @@ -##============ Sink warnings and errors to a file ============== -## use the sink() function to wrap all code within it. -##============================================================== -zz = file(paste0(Sys.getenv('REPORT_FILES_PATH'), '/.r_rendering.log.txt')) -sink(zz) -sink(zz, type = 'message') - -#============== preparation ==================================== -options(stringsAsFactors = FALSE) -# import libraries -#------------------------------------------------------------------ -# ADD MORE LIBRARIES HERE IF YOUR TOOL DEPENDS ON OTHER R LIBRARIES -#------------------------------------------------------------------ -library('getopt') -library('rmarkdown') -library('htmltools') - - -# load helper functions -source(paste0(Sys.getenv('TOOL_INSTALL_DIR'), '/helper.R')) -# import getopt specification matrix from a csv file -opt = getopt(getopt_specification_matrix('getopt_specification.csv', - tool_dir=Sys.getenv('TOOL_INSTALL_DIR'))) -# define environment variables for all input values. this is useful when we -# want to use input values by other programming language in r markdown -do.call(Sys.setenv, opt[-1]) -#=============================================================== - - -#======================== render Rmd files ========================= -# NOTICE: -# we should copy all rmarkdown files from tool install directory to REPORT_FILES_PATH directory. -# and render rmarkdown files in the REPORT_FILES_PATH directory. -file.copy(from = paste0(Sys.getenv('TOOL_INSTALL_DIR'), '/vakata-jstree-3.3.5'), - to = Sys.getenv('REPORT_FILES_PATH'), recursive = TRUE) -system(command = 'cp -r ${TOOL_INSTALL_DIR}/*.Rmd ${REPORT_FILES_PATH}') -# for rendering a site -system(command = 'cp -r ${TOOL_INSTALL_DIR}/_site.yml ${REPORT_FILES_PATH}') - -#----------------BELOW IS WHERE YOU NEED TO CUSTOMIZE --------------------- -render(input = paste0(Sys.getenv('REPORT_FILES_PATH'), '/rmarkdown_report.Rmd')) -# add more lines below if there are more Rmd files to be rendered - -#=============================================================== - - -#============== expose outputs to galaxy history =============== -system(command = 'sh ${TOOL_INSTALL_DIR}/expose-outputs.sh') -#=============================================================== - - -##--------end of code rendering .Rmd templates---------------- -sink() -##=========== End of sinking output=============================
--- a/getopt_specification.csv Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -short flag,argument mask,data type,variable name -o,1,character,report -d,1,character,report.files_path -r,1,character,reads_1 -n,1,character,reads_1.name -R,1,character,reads_2 -N,1,character,reads_2.name -c,1,character,contaminants -l,1,character,limits \ No newline at end of file
--- a/helper.R Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,82 +0,0 @@ -#' \code{getopt_specification_matrix} returns a getopt specification matrix. -#' -#' @param specification_file a cvs file within the \code{galaxy_tool_directory} which stores getopt specification matrix data. -#' The first column are short flags, the second column are argument masks, the third column -#' is data types. The fourth column are variable names used in the tool XML. These three columns are required. -#' @param gtg_name the name of a running GTG. -getopt_specification_matrix = function(specification_file, - gtg_name = 'gtg', - tool_dir = Sys.getenv('TOOL_DIR')) { - df = read.csv( - paste0(tool_dir, '/', specification_file), - header = TRUE, - stringsAsFactors = FALSE - ) - # check if there are duplicated short flags - short_flags = df[, 1] - if (length(unique(short_flags)) < length(short_flags)) { - cat('----Duplicated short flags found ----\n') - cat('short flags: ', df[, 1][duplicated(df[, 1])], '\n') - stop('Duplicated short flags are not allowed.') - } - - # use short flags to generate long flags - long_flags = paste0('X_', df[, 1]) - - # specification matrix - df2 = data.frame( - long_flags = long_flags, - short_flags = df[, 1], - argument_mask = df[, 2], - data_type = df[, 3] - ) - - as.matrix(df2) -} - - - -#' \code{file_tree} generate file tree of a directory in the format of HTML lists. -#' -#' @param dir the path to the directory for generating the file tree. -#' @param output_dir the REPORT_FILES_PATH folder name, which has the name style: dataset_NUMBER_files. -# define a recursive function to build html string of the file tree -file_tree = function(dir = '.') { - # get the OUTPUT_DIR folder data: dataset_NUMBER_files - report_files_path = Sys.getenv('REPORT_FILES_PATH') - output_dir = tail(strsplit(report_files_path, '/')[[1]], 1) - - files = list.files(path = dir, - recursive = FALSE, - full.names = TRUE) - # files also include directorys, need to remove directorys - files = files[!dir.exists(files)] - dirs = list.dirs(path = dir, - recursive = FALSE, - full.names = TRUE) - tags$ul({ - if (length(files) > 0) { - lapply(files, function(x) { - path_end = tail(strsplit(x, '/')[[1]], 1) - href_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] - li_item = tags$li(tags$a(path_end, href = href_path)) - li_item$attribs = list('data-jstree' = '{"icon":"jstree-file"}') - li_item - }) - } - }, - { - if (length(dirs) > 0) { - lapply(dirs, function(x) { - path_end = tail(strsplit(x, '/')[[1]], 1) - # hide vakata-jstree-3.3.5 folder - if (path_end != 'vakata-jstree-3.3.5') { - # x_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] - li_item = tags$li(path_end, file_tree(x)) - li_item$attribs = list('data-jstree' = '{"icon":"jstree-folder"}') - li_item - } - }) - } - }) -}
--- a/index.Rmd Mon Apr 30 10:15:54 2018 -0400 +++ b/index.Rmd Mon Apr 30 16:15:39 2018 -0400 @@ -1,22 +1,52 @@ ---- -title: "FastQC Report" -output: html_document ---- + -```{r setup, include=FALSE, warning=FALSE, message=FALSE} -knitr::opts_chunk$set(echo = TRUE, error = TRUE) +```{css echo=FALSE} +# code chunks scrollable +pre code, pre, code { + white-space: pre !important; + overflow-x: scroll !important; + word-break: keep-all !important; + word-wrap: initial !important; +} ``` +```{r, echo=FALSE} +# to make the css theme to work, <link></link> tags cannot be added directly +# as <script></script> tags as below. +# it has to be added using a code chunk with the htmltool functions!!! +css_link = tags$link() +css_link$attribs = list(rel="stylesheet", href="vakata-jstree-3.3.5/dist/themes/default/style.min.css") +css_link +``` -## References - -* Bioinformatics, Babraham (2014). FastQC. +```{r, eval=FALSE, echo=FALSE} +# this code chunk is purely for adding comments +# below is to add jQuery and jstree javascripts +``` +<script src="https://code.jquery.com/jquery-3.3.1.min.js"></script> +<script src="vakata-jstree-3.3.5/dist/jstree.min.js"></script> -* Allaire, J and Cheng, Joe and Xie, Yihui and McPherson, Jonathan and Chang, Winston and Allen, Jeff and Wickham, Hadley and Atkins, Aron and Hyndman, Rob (2016). rmarkdown: Dynamic Documents for R, 2016. In R package version 0.9, 6. - -* Xie, Yihui (2015). Dynamic Documents with R and knitr, CRC Press, Vol.29. +```{r, eval=FALSE, echo=FALSE} +# this code chunk is purely for adding comments +# javascript code below is to build the file tree interface +# see this for how to implement opening hyperlink: https://stackoverflow.com/questions/18611317/how-to-get-i-get-leaf-nodes-in-jstree-to-open-their-hyperlink-when-clicked-when +``` +<script> + $(function () { + // create an instance when the DOM is ready + $('#jstree').jstree().bind("select_node.jstree", function (e, data) { + window.open( data.node.a_attr.href, data.node.a_attr.target ) + }); + }); +</script> -* Carson Sievert and Chris Parmer and Toby Hocking and Scott Chamberlain and Karthik Ram and Marianne Corvellec and Pedro Despouy (2017). plotly: Create Interactive Web Graphics via 'plotly.js'. R package version 4.6.0. [Link] +## Outputs -* Wickham, H. (2016). ggplot2: elegant graphics for data analysis. Springer. Chicago +```{r, echo=FALSE} +# create a div container to store the file tree interface +tags$div( + id="jstree", + file_tree(Sys.getenv('REPORT_FILES_PATH')) +) +```
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rmarkdown_report.xml Mon Apr 30 16:15:39 2018 -0400 @@ -0,0 +1,111 @@ +<tool name="aurora_fastqc_site" id='aurora_fastqc_site' version="2.2.1"> + <description> + Evaluate short reads with FastQC software on a single or a paired of untrimmed and trimmed reads + files. + </description> + <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="1.3">r-rmarkdown</requirement> + <requirement type="package" version="1.8.4">r-plyr</requirement> + <requirement type="package" version="1.1.0">r-stringr</requirement> + <requirement type="package" version="0.2">r-dt</requirement> + <requirement type="package" version="1.4.2">r-reshape2</requirement> + <requirement type="package" version="4.5.6">r-plotly</requirement> + <requirement type="package" version="0.3.5">r-htmltools</requirement> + <requirement type="package" version="0.11.5">fastqc</requirement> + <requirement type="package" version="0.9.10">xorg-libxrender</requirement> + <requirement type="package" version="1.2.2">xorg-libsm</requirement> + <requirement type="package" version="6.0">unzip</requirement> + </requirements> + <stdio> + <regex match="XXX" source="stderr" level="warning" + description="Check the warnings_and_errors.txt file for more details."/> + </stdio> + <command><![CDATA[ + + ######### each aurora tool generates a html file and have an files path directory associated with it. + mkdir -p $report.files_path && + + ######### three important paths: + ######### 1. path to tool installation directory + ######### 2. path to report html + ######### 3. path to files_path directory associated with the report output. + export TOOL_INSTALL_DIR='${__tool_directory__}' && + export REPORT='$report' && + export REPORT_FILES_PATH='$report.files_path' && + + ############ copy jstree directory cp -r ${__tool_directory__}/vakata-jstree-3.3.5 ./ && + + ############ create a hidden file to store r markdown rendering log + touch $report.files_path/.r_rendering.log.txt && + + Rscript '${__tool_directory__}/rmarkdown_report_render.R' + + -o $report + -d $report.files_path + + -r $reads_1 + -n '$reads_1.name' + -R $reads_2 + -N '$reads_2.name' + -c $contaminants + -l $limits + + ]]></command> + <inputs> + <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="reads_1" type="data" optional="false" + label="Short reads before trimming" + help="Short reads data from history. This could be reads before trimming."/> + <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="reads_2" type="data" label="Short reads after trimming" + help="Short reads data from history. This could be reads after trimming."/> + <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list" + help="Specifies a non-default file which contains the list of adapter sequences which will be explicitly + searched against the library. The file must contain sets of named adapters in the form name[tab]sequence. + Lines prefixed with a hash will be ignored."/> + <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file" + help="Specifies a non-default file which contains a set of criteria which will be used to determine the + warn/error limits for the various modules. This file can also be used to selectively remove some modules + from the output all together. The format needs to mirror the default limits.txt file found in the + Configuration folder."/> + + </inputs> + <outputs> + <data format="html" name="report" label="${tool.name} on ${on_string}"/> + </outputs> + <citations> + <citation type="bibtex"><![CDATA[ + @online{jstree, + author={Bozhanov, Ivan}, + year = 2018, + url = {https://www.jstree.com/} + } + ]]></citation> + <citation type="bibtex"><![CDATA[ + @misc{bioinformatics2014fastqc, + title={FastQC}, + author={Bioinformatics, Babraham}, + year={2014} + } + ]]></citation> + <citation type="bibtex"><![CDATA[ + @article{allaire2016rmarkdown, + title={rmarkdown: Dynamic Documents for R, 2016}, + author={Allaire, J and Cheng, Joe and Xie, Yihui and McPherson, Jonathan and Chang, Winston and Allen, Jeff + and Wickham, Hadley and Atkins, Aron and Hyndman, Rob}, + journal={R package version 0.9}, + volume={6}, + year={2016} + } + ]]></citation> + <citation type="bibtex"><![CDATA[ + @book{xie2015dynamic, + title={Dynamic Documents with R and knitr}, + author={Xie, Yihui}, + volume={29}, + year={2015}, + publisher={CRC Press} + } + ]]></citation> + </citations> +</tool> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rmarkdown_report_render.R Mon Apr 30 16:15:39 2018 -0400 @@ -0,0 +1,167 @@ +##============ Sink warnings and errors to a file ============== +## use the sink() function to wrap all code within it. +##============================================================== +zz = file(paste0(Sys.getenv('REPORT_FILES_PATH'), '/.r_rendering.log.txt')) +sink(zz) +sink(zz, type = 'message') + +#============== preparation ==================================== +# import libraries +#------------------------------------------------------------------ +# ADD MORE LIBRARIES HERE IF YOUR TOOL DEPENDS ON OTHER R LIBRARIES +#------------------------------------------------------------------ +library('getopt') +library('rmarkdown') +library('htmltools') +library('plyr') +library('dplyr') +library('stringr') +library('DT') +library('reshape2') +library('plotly') +#------------------------------------------------------------------ +options(stringsAsFactors = FALSE) + + +# define two helper functions +#-----: helper function 1 +#' \code{getopt_specification_matrix} returns a getopt specification matrix. +#' +#' @param specification_file a cvs file within the \code{galaxy_tool_directory} which stores getopt specification matrix data. +#' The first column are short flags, the second column are argument masks, the third column +#' is data types. The fourth column are variable names used in the tool XML. These three columns are required. +#' @param gtg_name the name of a running GTG. +getopt_specification_matrix = function(specification_file, + gtg_name = 'gtg', + tool_dir = Sys.getenv('TOOL_INSTALL_DIR')) { + df = read.csv( + paste0(tool_dir, '/', specification_file), + header = TRUE, + stringsAsFactors = FALSE + ) + # check if there are duplicated short flags + short_flags = df[, 1] + if (length(unique(short_flags)) < length(short_flags)) { + cat('----Duplicated short flags found ----\n') + cat('short flags: ', df[, 1][duplicated(df[, 1])], '\n') + stop('Duplicated short flags are not allowed.') + } + + # use short flags to generate long flags + long_flags = paste0('X_', df[, 1]) + + # specification matrix + df2 = data.frame( + long_flags = long_flags, + short_flags = df[, 1], + argument_mask = df[, 2], + data_type = df[, 3] + ) + + as.matrix(df2) +} + +#-----: helper function 2 +#' \code{file_tree} generate file tree of a directory in the format of HTML lists. +#' +#' @param dir the path to the directory for generating the file tree. +#' @param output_dir the REPORT_FILES_PATH folder name, which has the name style: dataset_NUMBER_files. +# define a recursive function to build html string of the file tree +file_tree = function(dir = '.') { + # get the OUTPUT_DIR folder data: dataset_NUMBER_files + report_files_path = Sys.getenv('REPORT_FILES_PATH') + output_dir = tail(strsplit(report_files_path, '/')[[1]], 1) + + files = list.files(path = dir, + recursive = FALSE, + full.names = TRUE) + # files also include directorys, need to remove directorys + files = files[!dir.exists(files)] + dirs = list.dirs(path = dir, + recursive = FALSE, + full.names = TRUE) + tags$ul({ + if (length(files) > 0) { + lapply(files, function(x) { + path_end = tail(strsplit(x, '/')[[1]], 1) + href_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] + li_item = tags$li(tags$a(path_end, href = href_path)) + li_item$attribs = list('data-jstree' = '{"icon":"jstree-file"}') + li_item + }) + } + }, + { + if (length(dirs) > 0) { + lapply(dirs, function(x) { + path_end = tail(strsplit(x, '/')[[1]], 1) + # hide vakata-jstree-3.3.5 folder + if (path_end != 'vakata-jstree-3.3.5') { + # x_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] + li_item = tags$li(path_end, file_tree(x)) + li_item$attribs = list('data-jstree' = '{"icon":"jstree-folder"}') + li_item + } + }) + } + }) +} +#----------------- end of help functions ------------------------- + + +# import getopt specification matrix from a csv file +opt = getopt(getopt_specification_matrix('command-line-arguments.csv', + tool_dir = Sys.getenv('TOOL_INSTALL_DIR'))) +# define environment variables for all input values. this is useful when we +# want to use input values by other programming language in r markdown +do.call(Sys.setenv, opt[-1]) +#=============================================================== + + +#======================== render Rmd files ========================= +# copy jstree javascript library to tool output directory +file.copy( + from = paste0(Sys.getenv('TOOL_INSTALL_DIR'), '/vakata-jstree-3.3.5'), + to = Sys.getenv('REPORT_FILES_PATH'), + recursive = TRUE +) + +# if '_site.yml' file exists, this tool is assumed to render a website. +# otherwise, it renders a single html. +if (file.exists(paste0(Sys.getenv('TOOL_INSTALL_DIR'), '/_site.yml'))) { + # render a website + system(command = 'cp -r ${TOOL_INSTALL_DIR}/*.Rmd ${REPORT_FILES_PATH}') + system(command = 'cp -r ${TOOL_INSTALL_DIR}/_site.yml ${REPORT_FILES_PATH}') + render_site(input = Sys.getenv('REPORT_FILES_PATH')) +} else { + # render a single html + system(command = 'cp -r ${TOOL_INSTALL_DIR}/rmarkdown_report.Rmd ${REPORT_FILES_PATH}') + # add a few lines to 'rmarkdown_report.Rmd' to generate file tree outputs + jstree_lines = ' + + ## Outputs + + ```{r, echo=FALSE} + # create a div container to store the file tree interface + library(htmltools) + tags$div( + id="jstree", + file_tree(Sys.getenv(\'REPORT_FILES_PATH\')) + ) + ``` + ' + write(x = jstree_lines, append = TRUE, + file = paste0(Sys.getenv('REPORT_FILES_PATH'), '/rmarkdown_report.Rmd')) + render(input = paste0(Sys.getenv('REPORT_FILES_PATH'), '/rmarkdown_report.Rmd')) +} +#=============================================================== + + +#============== expose outputs to galaxy history =============== +system(command = 'sh ${TOOL_INSTALL_DIR}/expose-outputs-to-galaxy-history.sh') +#=============================================================== + + +##--------end of code rendering .Rmd templates---------------- +sink() +##=========== End of sinking output=============================
--- a/shell-script-template.sh Mon Apr 30 10:15:54 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,36 +0,0 @@ -# SHELL_SCRIPT file name -SHELL_SCRIPT='fastqc.sh' - -# run SHELL_SCRIPT within tool outputs directory -cd ${REPORT_FILES_PATH} - -# build job-script.sh -cat >temp.sh <<EOF - -cp ${X_r} read_1.fq -cp ${X_R} read_2.fq - -fastqc \\ - -q \\ - -c ${X_c} \\ - -l ${X_l} \\ - ${X_d}/read_1.fq > /dev/null 2>&1 - -fastqc \\ - -q \\ - -c ${X_c} \\ - -l ${X_l} \\ - ${X_d}/read_2.fq > /dev/null 2>&1 - -EOF - -grep -v None temp.sh > ${SHELL_SCRIPT} -rm temp.sh - -# run SHELL_SCRIPT -sh ${SHELL_SCRIPT} - - -# unzip outputs -unzip -q read_1_fastqc.zip -unzip -q read_2_fastqc.zip \ No newline at end of file