changeset 6:7c54fd452b8e draft

add kableExtra package
author mingchen0919
date Wed, 18 Apr 2018 15:59:38 -0400
parents aacd5f53ac99
children 63cde8d7f89c
files helper.R htseq_count.Rmd htseq_count.xml htseq_count_render.R run_htseq-count.sh
diffstat 5 files changed, 90 insertions(+), 16 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/helper.R	Wed Apr 18 15:59:38 2018 -0400
@@ -0,0 +1,72 @@
+#' \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)
+  # 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"}')
+          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/htseq_count.Rmd	Wed Apr 18 13:17:28 2018 -0400
+++ b/htseq_count.Rmd	Wed Apr 18 15:59:38 2018 -0400
@@ -42,29 +42,31 @@
 -----------------------------------------
 
 
-```{bash, echo=FALSE}
-sh ${TOOL_INSTALL_DIR}/run_htseq-count.sh
-```
-
 ## Job script
 
 * htseq-count analysis: [htseq-count.sh](htseq-count.sh)
 
+```{bash, echo=FALSE}
+sh ${TOOL_INSTALL_DIR}/run_htseq-count.sh
+```
+
+
 ## Counts
 
-```{r}
+```{r, echo=TRUE}
 count_data = read.table(paste0(opt$X_d, '/counts.txt'), row.names = 1)
 sample_names = trimws(strsplit(opt$X_B, ',')[[1]])
 colnames(count_data) = rep(sample_names, length = ncol(count_data))
-DT::datatable(count_data, caption = "htseq counts for each sample")
+kable(head(count_data))
 ```
 
-```{r}
+```{r, echo=FALSE}
 # save count data as an R object
 save(count_data, file = paste0(opt$X_d, '/counts.RData'))
 ```
 
-```{bash}
+```{bash, echo=FALSE}
+# expose counts.RData to galaxy history
 cp ${X_d}/counts.RData ${X_O}
 ```
 
--- a/htseq_count.xml	Wed Apr 18 13:17:28 2018 -0400
+++ b/htseq_count.xml	Wed Apr 18 15:59:38 2018 -0400
@@ -5,7 +5,7 @@
         <requirement type="package" version="1.20.0">r-getopt</requirement>
         <requirement type="package" version="1.6">r-rmarkdown</requirement>
         <requirement type="package" version="0.9.1">htseq</requirement>
-        <requirement type="package" version="0.2">r-dt</requirement>
+        <requirement type="package" version="0.8.0">r-kableextra</requirement>
     </requirements>
     <stdio>
         <regex match="XXX" source="stderr" level="warning"
@@ -27,8 +27,6 @@
         ############ create a hidden file to store r markdown rendering log
         echo '------ Rmd rendering log -------\n' > $report.files_path/.r_rendering.log.txt &&
 
-    echo echo 'R markdown rendering started.' &&
-
     Rscript '${__tool_directory__}/htseq_count_render.R'
 
 			-o $report
@@ -45,9 +43,7 @@
 			-i $idattr
 			-m $mode
 			-c $count
-			-O $count_rdata &&
-
-	echo 'R markdown rendering finished.'
+			-O $count_rdata
 
     ]]></command>
     <inputs>
--- a/htseq_count_render.R	Wed Apr 18 13:17:28 2018 -0400
+++ b/htseq_count_render.R	Wed Apr 18 15:59:38 2018 -0400
@@ -11,6 +11,8 @@
 library(getopt)
 library(rmarkdown)
 library(htmltools)
+library(kableExtra)
+library(magrittr)
 # load helper functions
 source(paste0(Sys.getenv('TOOL_INSTALL_DIR'), '/helper.R'))
 # import getopt specification matrix from a csv file
--- a/run_htseq-count.sh	Wed Apr 18 13:17:28 2018 -0400
+++ b/run_htseq-count.sh	Wed Apr 18 15:59:38 2018 -0400
@@ -10,9 +10,11 @@
     -a ${X_a} \\
     -t ${X_T} \\
     -i ${X_i} \\
-    -m ${X_m} > counts.txt
+    -m ${X_m} > htseq-counts-raw.txt 
     
-  grep -v '__no_feature\|__ambiguous\|__too_low_aQual\|__not_aligned\|__alignment_not_unique' counts.txt > ${X_c}
+  grep -v '__no_feature\|__ambiguous\|__too_low_aQual\|__not_aligned\|__alignment_not_unique' htseq-counts-raw.txt > counts.txt
+  
+  cp counts.txt ${X_c}
 EOF
 
 sh htseq-count.sh
\ No newline at end of file