Mercurial > repos > mingchen0919 > aurora_fastqc
changeset 2:5f00aef42904 draft
planemo upload commit 58ac10c63c4cc51b4122de0fa07b887ace6df657-dirty
author | mingchen0919 |
---|---|
date | Wed, 25 Apr 2018 15:55:23 -0400 |
parents | 2fbb7d627af1 |
children | 85351cdd4f19 |
files | expose-outputs.sh fastqc.Rmd fastqc.xml fastqc_render.R helper.R run-fastqc.sh shell-script-template.sh |
diffstat | 7 files changed, 122 insertions(+), 92 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/expose-outputs.sh Wed Apr 25 15:55:23 2018 -0400 @@ -0,0 +1,5 @@ +# change directory to tool outputs directory +cd ${REPORT_FILES_PATH} + +# copy outputs from tool outputs directory to corresponding galaxy output path +cp fastqc.html ${REPORT} \ No newline at end of file
--- a/fastqc.Rmd Wed Apr 18 09:04:09 2018 -0400 +++ b/fastqc.Rmd Wed Apr 25 15:55:23 2018 -0400 @@ -40,6 +40,14 @@ }); </script> +```{css} +pre code, pre, code { + white-space: pre !important; + overflow-x: scroll !important; + word-break: keep-all !important; + word-wrap: initial !important; +} +``` ---------------------- @@ -49,14 +57,14 @@ # Run FastQC ```{bash} -sh ${TOOL_INSTALL_DIR}/run-fastqc.sh +sh ${TOOL_INSTALL_DIR}/shell-script-template.sh ``` - -```{r} +```{r echo=FALSE,results='asis'} # display fastqc job script -fastqc_sh = paste0(opt$X_d, '/fastqc.sh') -tags$code(tags$pre(readChar(fastqc_sh, file.info(fastqc_sh)$size ))) +cat('```bash\n') +cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/fastqc.sh')), sep = '\n') +cat('\n```') ``` # Fastqc Output Visualization @@ -396,11 +404,6 @@ - - - - - ----------------------------------------- ## Output
--- a/fastqc.xml Wed Apr 18 09:04:09 2018 -0400 +++ b/fastqc.xml Wed Apr 25 15:55:23 2018 -0400 @@ -71,7 +71,7 @@ </inputs> <outputs> - <data format="html" name="report"/> + <data format="html" name="report" label="${tool.name} on ${on_string}"/> </outputs> <citations> <citation type="bibtex"><![CDATA[
--- a/fastqc_render.R Wed Apr 18 09:04:09 2018 -0400 +++ b/fastqc_render.R Wed Apr 25 15:55:23 2018 -0400 @@ -5,45 +5,52 @@ sink(zz) sink(zz, type = 'message') -#-------------------preparation ----------------- +#============== preparation ==================================== options(stringsAsFactors = FALSE) # import libraries -library(getopt) -library(rmarkdown) -library(htmltools) +#------------------------------------------------------------------ +# 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) + # 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 a unix variable versions for all input values. this is useful when we +# 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 -------------- +#======================== render Rmd files ========================= # NOTICE: -# we should copy all rmarkdown files from tool install directory to current working directory. -# we should render rmarkdown files in the current working directory. +# 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}') -# render Rmd files in order + +#----------------BELOW IS WHERE YOU NEED TO CUSTOMIZE --------------------- render(input = paste0(Sys.getenv('REPORT_FILES_PATH'), '/fastqc.Rmd')) -#------------------------------------------ +# add more lines below if there are more Rmd files to be rendered + +#=============================================================== -#---------------- copy the output html to REPORT and OUTPUT_FILE_TREE---- -system(command = 'cp ${REPORT_FILES_PATH}/fastqc.html ${REPORT}') -#==============the end============== +#============== expose outputs to galaxy history =============== +system(command = 'sh ${TOOL_INSTALL_DIR}/expose-outputs.sh') +#=============================================================== + ##--------end of code rendering .Rmd templates---------------- sink()
--- a/helper.R Wed Apr 18 09:04:09 2018 -0400 +++ b/helper.R Wed Apr 25 15:55:23 2018 -0400 @@ -4,9 +4,14 @@ #' 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) +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)) { @@ -19,10 +24,12 @@ 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]) + df2 = data.frame( + long_flags = long_flags, + short_flags = df[, 1], + argument_mask = df[, 2], + data_type = df[, 3] + ) as.matrix(df2) } @@ -30,43 +37,46 @@ #' \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 = '.'){ +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 = 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) - # hide vakata-jstree-3.3.5 folder - #jstree_index = grep(pattern = 'vakata-jstree-3.3.5', x = dirs) - #dirs = dirs[-jstree_index] - 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$attribs = list('data-jstree'='{"icon":"jstree-file"}') + dirs = list.dirs(path = dir, + recursive = FALSE, + full.names = TRUE) + tags$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$attribs = list('data-jstree' = '{"icon":"jstree-folder"}') li_item - }) - } - }, - { - if (length(dirs) > 0) { - lapply(dirs, function(x){ - x_path = strsplit(x, paste0(output_dir, '/'))[[1]][2] - li_item = tags$li(x_path, file_tree(x)) - li_item$attribs = list('data-jstree'='{"icon":"jstree-folder"}') - li_item - }) - } + } + }) } - ) + }) }
--- a/run-fastqc.sh Wed Apr 18 09:04:09 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,31 +0,0 @@ - -#create extra file directory -mkdir -p ${X_d} - -cd ${X_d} -cp ${X_r} ${X_d}/read_1.fq -cp ${X_R} ${X_d}/read_2.fq - -cat >temp.sh <<EOL -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 -EOL - -grep -v None temp.sh > fastqc.sh -rm temp.sh - -# run fastqc -sh fastqc.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/shell-script-template.sh Wed Apr 25 15:55:23 2018 -0400 @@ -0,0 +1,36 @@ +# 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