Mercurial > repos > mingchen0919 > aurora_htseq

changeset 9:578a96df8690 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 1cb2dd80dcb431563edbe1e763b3dde3a1adb2ae-dirty
author mingchen0919
date Wed, 25 Apr 2018 14:22:32 -0400
parents 1696f5ee0fe7
children ec906e72784d
files expose-outputs.sh helper.R htseq_count.Rmd htseq_count_render.R run_htseq-count.sh shell-script-template.sh
diffstat 6 files changed, 84 insertions(+), 66 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/expose-outputs.sh	Wed Apr 25 14:22:32 2018 -0400
@@ -0,0 +1,7 @@
+# change directory to tool outputs directory
+cd ${REPORT_FILES_PATH}
+
+# copy files to corresponding tool output paths.
+cp htseq_count.html ${REPORT}
+cp counts.RData ${X_O}
+cp counts.txt ${X_c}
\ No newline at end of file
--- a/helper.R	Wed Apr 18 17:12:06 2018 -0400
+++ b/helper.R	Wed Apr 25 14:22:32 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/htseq_count.Rmd	Wed Apr 18 17:12:06 2018 -0400
+++ b/htseq_count.Rmd	Wed Apr 25 14:22:32 2018 -0400
@@ -47,7 +47,7 @@
 * htseq-count analysis: [htseq-count.sh](htseq-count.sh)
 
 ```{bash, echo=FALSE}
-sh ${TOOL_INSTALL_DIR}/run_htseq-count.sh
+sh ${TOOL_INSTALL_DIR}/shell-script-template.sh
 ```
 
 
@@ -62,12 +62,7 @@
 
 ```{r, echo=FALSE}
 # save count data as an R object
-save(count_data, file = paste0(opt$X_d, '/counts.RData'))
-```
-
-```{bash, echo=FALSE}
-# expose counts.RData to galaxy history
-cp ${X_d}/counts.RData ${X_O}
+save(count_data, file = paste0(Sys.getenv('REPORT_FILES_PATH'), '/counts.RData'))
 ```
 
 -----------------------------------------
--- a/htseq_count_render.R	Wed Apr 18 17:12:06 2018 -0400
+++ b/htseq_count_render.R	Wed Apr 25 14:22:32 2018 -0400
@@ -38,10 +38,8 @@
 #------------------------------------------
 
 
-#---------------- copy the output html to REPORT ----
-system(command = 'cp ${REPORT_FILES_PATH}/htseq_count.html ${REPORT}')
-# add more lines below if there are more output html files
-
+#--------- expose outputs to galaxy history ----
+system(command = 'sh ${TOOL_INSTALL_DIR}/expose-outputs.sh')
 #==============the end==============
 
 
--- a/run_htseq-count.sh	Wed Apr 18 17:12:06 2018 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,20 +0,0 @@
-cd ${X_d}
-
-cat >htseq-count.sh <<EOF
-  htseq-count \\
-    $(echo ${X_A} | sed 's/,/ /g') \\
-    ${X_G} \\
-    -f ${X_f} \\
-    -r ${X_r} \\
-    -s ${X_S} \\
-    -a ${X_a} \\
-    -t ${X_T} \\
-    -i ${X_i} \\
-    -m ${X_m} > htseq-counts-raw.txt 
-    
-  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
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/shell-script-template.sh	Wed Apr 25 14:22:32 2018 -0400
@@ -0,0 +1,28 @@
+# SHELL_SCRIPT file name
+SHELL_SCRIPT='htseq-count.sh'
+
+# run SHELL_SCRIPT within tool outputs directory
+cd ${REPORT_FILES_PATH}
+
+# build job-script.sh
+cat >${SHELL_SCRIPT} <<EOF
+#------------ BELOW IS WHERE YOU WRITE YOUR OWN SHELL SCRIPT --------------
+
+  htseq-count \\
+    $(echo ${X_A} | sed 's/,/ /g') \\
+    ${X_G} \\
+    -f ${X_f} \\
+    -r ${X_r} \\
+    -s ${X_S} \\
+    -a ${X_a} \\
+    -t ${X_T} \\
+    -i ${X_i} \\
+    -m ${X_m} > htseq-counts-raw.txt 
+    
+  grep -v '__no_feature\|__ambiguous\|__too_low_aQual\|__not_aligned\|__alignment_not_unique' htseq-counts-raw.txt > counts.txt
+
+#------------ END OF SHELL SCRIPT ------------------------------------------  
+EOF
+
+# run SHELL_SCRIPT
+sh ${SHELL_SCRIPT}
\ No newline at end of file