# HG changeset patch # User mingchen0919 # Date 1529504685 14400 # Node ID a1448d1f2ee4c8eb40bcc17f5675557a24d509e5 planemo upload diff -r 000000000000 -r a1448d1f2ee4 1-index-genome.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/1-index-genome.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,11 @@ +# create genome directory for genome indices. +mkdir -p ${X_d}/genomeDir + +STAR \ + --runMode genomeGenerate \ + --genomeDir ${X_d}/genomeDir \ + --genomeFastaFiles $( echo ${X_A} | sed 's/,/ /g' ) \ + --sjdbGTFfile ${X_B} \ + --sjdbOverhang ${X_C} \ + > genome-indexing.log.txt 2>&1 + \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 2-mapping.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/2-mapping.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,6 @@ +STAR \ + --genomeDir ${X_d}/genomeDir \ + --readFilesIn \ + ${X_F} \ + ${X_R} \ + > mapping.log.txt 2>&1 \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 3-sam2bam.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/3-sam2bam.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,1 @@ +samtools sort -o Aligned.out.sorted.bam Aligned.out.sam \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 4-flagstat.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/4-flagstat.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,1 @@ +samtools flagstat Aligned.out.sorted.bam > flagstat.txt \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 htseq_count.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/htseq_count.xml Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,59 @@ + + ultrafasta universal RNA-Seq aligner + + + pandocr-getoptr-rmarkdown + + + + + + + + diff -r 000000000000 -r a1448d1f2ee4 run-star-jobs.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/run-star-jobs.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,15 @@ +cd ${REPORT_FILES_PATH} + +# index genome +grep -v None ${TOOL_INSTALL_DIR}/1-index-genome.sh > 1-index-genome.sh +sh 1-index-genome.sh + +# mapping +grep -v None ${TOOL_INSTALL_DIR}/1-mapping.sh > 1-mapping.sh +sh 1-mapping.sh + +# convert sam to bam +sh 3-sam2bam.sh + +# mapping evaluation +sh 4-flagstat.sh \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 star.Rmd --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/star.Rmd Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,108 @@ +--- +title: 'Aurora Tool Report' +output: + html_document: + highlight: pygments +--- + +```{r setup, include=FALSE, warning=FALSE, message=FALSE} +knitr::opts_chunk$set(error = TRUE, echo = FALSE) +``` + +```{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, tags cannot be added directly +# as 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 +``` + +```{r, eval=FALSE, echo=FALSE} +# this code chunk is purely for adding comments +# below is to add jQuery and jstree javascripts +``` + + + +--- +# 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 +--- + + +--- +# ADD YOUR DATA ANALYSIS CODE AND MARKUP TEXT BELOW TO EXTEND THIS R MARKDOWN FILE +--- + + + +## Job scripts + +```{bash, echo=FALSE} +sh ${TOOL_INSTALL_DIR}/run-star-jobs.sh +``` + +### Index genome + +```{r echo=FALSE,results='asis'} +# display content of the job-script.sh file. +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/1-index-genome.sh')), sep = '\n') +cat('\n```') +``` + +### Mapping + +```{r echo=FALSE,results='asis'} +# display content of the job-script.sh file. +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/2-mapping.sh')), sep = '\n') +cat('\n```') +``` + +### SAM to sorted BAM + +```{r echo=FALSE,warning=FALSE,results='asis'} +# display content of the job-script.sh file. +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/3-sam2bam.sh')), sep = '\n') +cat('\n```') +``` + +### Mapping evaluation + +```{r echo=FALSE,warning=FALSE,results='asis'} +# display content of the job-script.sh file. +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/4-flagstat.sh')), sep = '\n') +cat('\n```') +``` + + +### Mapping evaluation results + +```{r echo=FALSE,warning=FALSE,results='asis'} +# display content of the job-script.sh file. +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/5-flagstat.txt')), sep = '\n') +cat('\n```') +``` \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 star.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/star.xml Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,61 @@ + + ultrafast universal RNA-Seq aligner + + + pandocr-getoptr-rmarkdownstarsamtools + + + + + + + + diff -r 000000000000 -r a1448d1f2ee4 star_galaxy_outputs.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/star_galaxy_outputs.sh Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,15 @@ +# 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 + +if [ -e "Aligned.out.sorted.bam" ]; then + cp index.html ${REPORT} +fi \ No newline at end of file diff -r 000000000000 -r a1448d1f2ee4 star_getopt.csv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/star_getopt.csv Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,9 @@ +short flag,argument mask,data type,variable name +o,1,character,report +d,1,character,report.files_path +A,1,character,genomeFastaFiles +B,1,character,sjdbGTFfile +C,1,character,sjdbOverhang +F,1,character,first_reads +R,1,character,second_reads +S,1,character,sorted_bam diff -r 000000000000 -r a1448d1f2ee4 star_render.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/star_render.R Wed Jun 20 10:24:45 2018 -0400 @@ -0,0 +1,159 @@ +##============ 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'), '/rmarkdown_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') +#------------------------------------------------------------------ +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$attribs = list('data-jstree' = '{"icon":"jstree-file"}') + li_item + }) + } + }, + { + if (length(dirs) > 0) { + lapply(dirs, function(x) { + path_end = tail(strsplit(x, '/')[[1]], 1) + # hide vakata-jstree-3.3.5 folder + if (!(path_end %in% c('vakata-jstree-3.3.5', 'rmarkdown_report_files', 'site_libs'))) { + # x_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] + li_item = tags$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('star_getopt.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]) +# add current job working directory +Sys.setenv(JOB_WORKING_DIR=getwd()) +#=============================================================== + + +#======================== 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}/star.Rmd ${REPORT_FILES_PATH}') + # add a few lines to 'star.Rmd' to generate file tree outputs + jstree_lines = ' +## Outputs + +```{r, echo=FALSE} +tags$div(id="jstree", file_tree(Sys.getenv(\'REPORT_FILES_PATH\'))) +```' + write( + x = jstree_lines, + append = TRUE, + file = paste0(Sys.getenv('REPORT_FILES_PATH'), '/star.Rmd') + ) + render(input = paste0(Sys.getenv('REPORT_FILES_PATH'), '/star.Rmd')) +} +#=============================================================== + + +#============== expose outputs to galaxy history =============== +system(command = 'sh ${TOOL_INSTALL_DIR}/star_galaxy_outputs.sh') +#=============================================================== + + +##--------end of code rendering .Rmd templates---------------- +sink() +##=========== End of sinking output============================= diff -r 000000000000 -r a1448d1f2ee4 vakata-jstree-3.3.5.zip Binary file vakata-jstree-3.3.5.zip has changed