Break up GTR into module and submodules

workflow/script-run-workflow

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 # Copyright 2024 Bryan C. Roessler
 #
-# This is a code scratchpad for organizing the Hartman Lab Server workflow
+# This is a flexible yet opinionated analysis workflow for the Hartman Lab
 # It contains a mixture of code/pseudocode and shouldn't be run until this message is removed
 #
 # Allow indirect functions
@@ -14,6 +14,7 @@
 # @option -p<value> | --project=<value> Include one or more projects in the analysis
 # @option -i<value> | --include=<value> Include one or more modules in the analysis (default: all modules)
 # @option -x<value> | --exclude=<value> Exclude one or more modules in the analysis
+# @option -m | --markdown Generate the shdoc markdown file for this program
 # @option -y | --yes | --auto Assume yes answer to all questions (non-interactive mode)
 # @option -d | --debug Turn on extra debugging output
 # @option -h | --help Print help message and exit (overrides other options)
@@ -49,6 +50,8 @@ print_help() {
 		    If no --include is specified, all modules are run
 		  --exclude, -x MODULE
 		    See MODULES section below for list of modules to exclude
+		  --markdown, -m
+		    Generate the shdoc markdown file for this program
 		  --yes, -y, --auto
 		    Always answer yes to questions (non-interactive mode)
 		  --debug, -d
@@ -86,8 +89,8 @@ print_help() {
 parse_input() {
   debug "Running: ${FUNCNAME[0]}" "$@"
 
-  long_opts="project:,include:,exclude:,yes,auto,debug,help"
+  long_opts="project:,include:,exclude:,markdown,yes,auto,debug,help"
-  short_opts="+p:i:x:yhd"
+  short_opts="+p:i:x:mydh"
 
   if input=$(getopt -o $short_opts -l $long_opts -- "$@"); then
     eval set -- "$input"
@@ -117,6 +120,9 @@ parse_input() {
             EXCLUDE_MODULES+=("$1")
           fi
           ;;
+        --markdown|-m)
+          documentation
+          ;;
         --yes|-y|--auto)
           declare -g YES=1
           ;;
@@ -176,8 +182,9 @@ debug() { (( DEBUG )) && echo "Debug: $*"; }
 # @section Modules
 # @description A module contains a cohesive set of actions/experiments to run on a project
 # Use a module when:
-#   * Building a new type of analysis
+#   * Building a new type of analysis from scratch
-#   * Combining submodules
+#   * Generates project directories
+#   * Can combine other modules and submodules
 #
 #
 
@@ -327,13 +334,13 @@ qhtcp() {
 
   # Our list of submodules (functions) to run for this module
   # Put these in the appropriate order of operations
-  submodules=(
+  modules=(
     r_join_interact
     java_extract
     r_add_shift_values
     r_heat_maps_zscores
     r_heat_maps_homology
-    py_gtf
+    gtf
     r_compile_gtf
   )
   
@@ -364,12 +371,31 @@ qhtcp() {
   pushd "$QHTCP_DIR/REMc" || return 1
 
   # Run each submodule
-  for s in "${submodules[@]}"; do "$s"; done
+  for s in "${modules[@]}"; do "$s"; done
 
   popd || return 1
 }
 
 
+module gtf
+# @section GTF
+# @description GTF module for QHTCP
+gtf() {
+  debug "Running: ${FUNCNAME[0]}"
+  process_dir="GTF/Process"
+  function_dir="GTF/Function"
+  component_dir="GTF/Component"
+
+  py_gtf "$process_dir"
+
+  # Perform operations in each directory in parallel
+  for d in "$process_dir" "$function_dir" "$component_dir"; do
+    rsync -a "$process_dir/REMcRdy_lm_only" "$d"/
+    out_file="${d##*/}Results.txt" # Use the dirname to create each Results filename
+    pl_gtf "$d" "$out_file" & # parallelize
+  done
+
+}
 # @section Submodules
 # @description Submodules provide functionaility to modules and are reusable between modules
 # Use a submodule when:
@@ -474,25 +500,25 @@ r_heat_maps_homology() {
 
 
 submodule py_gtf
-# @description Perform GTF
+# @description Perform python portion of GTF
+# @arg $1 string Directory to process
 py_gtf() {
   debug "Running: ${FUNCNAME[0]}"
-  process_dir="GTF/Process"
-  function_dir="GTF/Function"
-  component_dir="GTF/Component"
   in_file="REMcRdy_lm_only.csv-finalTable.csv"
-  out_file="$process_dir/REMcRdy_lm_only/1-0-0-finaltable.csv"
+  out_file="$1/REMcRdy_lm_only/1-0-0-finaltable.csv"
-  echo "$PYTHON DconJG2.py $in_file $process_dir/"
+  debug "$PYTHON DconJG2.py $in_file $1/"
-  "$PYTHON" DconJG2.py "$in_file" "$process_dir/"
+  "$PYTHON" DconJG2.py "$in_file" "$1/"
   [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
-  unset out_file
+}
-  rsync -a "$process_dir/REMcRdy_lm_only" GTF/Function/
-  rsync -a "$process_dir/REMcRdy_lm_only" GTF/Component/
 
-  # @description Not sure what to name this
+
-  # @arg $1 string directory name
+submodule pl_gtf
-  _process() {
+# @description Perl module for GTF
+# @arg $1 string working directory
+# @arg $2 string output file
+pl_gtf() {
   debug "Running: ${FUNCNAME[0]}" "$@"
+  set1="ORF_List_Without_DAmPs.txt"
   pushd "$1" || return 1
 
   shopt -s nullglob
@@ -500,28 +526,21 @@ py_gtf() {
   shopt -u nullglob
 
   for s in "${set2[@]}"; do
+    debug "pl_analyze $set1 $s"
     pl_analyze "$set1" "$s"
+    debug "pl_terms2tsv $s"
     pl_terms2tsv "$s"
-		  "$PERL" terms2tsv_v4.pl "$s.terms" > "$s.tsv"
   done
 
   # Concat the process ontology outputs from the /REMcReady_lm_only folder
-    echo "$PYTHON Concatenate_GTF_results.py REMcRdy_lm_only/ $out_file"
+  echo "$PYTHON Concatenate_GTF_results.py REMcRdy_lm_only/ $2"
   echo "TODO: Concatenate_GTF_results.py should be translated to bash"
-    "$PYTHON" Concatenate_GTF_results.py REMcRdy_lm_only/ "$out_file"
+  "$PYTHON" Concatenate_GTF_results.py REMcRdy_lm_only/ "$2"
 
-    [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
+  [[ -f $2 ]] || (echo "$2 does not exist"; return 1)
   popd || return 1
 }
 
-  # Perform operations in each directory
-  for d in "$process_dir" "$function_dir" "$component_dir"; do 
-    set1="ORF_List_Without_DAmPs.txt"
-    out_file="${d##*/}Results.txt" # Use the dirname to create each Results filename
-    _process "$d" & # parallelize
-  done
-}
-
 
 submodule pl_analyze
 # @description Perl analyze submodule
@@ -550,23 +569,7 @@ pl_terms2tsv() {
 }
 
 
-submodule documentation
+submodule r_compile_gtf
-# @section Documentation
-# @description Generates markdown documentation from this script using shdoc
-documentation() {
-  debug "Running: ${FUNCNAME[0]}"
-
-  # Print markdown to stdout
-  shdoc < "$SCRIPT"
-
-  # Create markdown file
-  shdoc < "$SCRIPT" > documentation.md
-  
-}
-
-
-
-
 # @description Compile GTF in R
 r_compile_gtf() {
   debug "Running: ${FUNCNAME[0]}"
@@ -575,6 +578,18 @@ r_compile_gtf() {
 }
 
 
+submodule documentation
+# @section Documentation
+# @description Generates markdown documentation from this script using shdoc
+documentation() {
+  debug "Running: ${FUNCNAME[0]}"
+  # Print markdown to stdout
+  ((DEBUG)) && shdoc < "$SCRIPT"
+  # Create markdown file
+  shdoc < "$SCRIPT" > documentation.md
+}
+
+
 # @description The main loop of script-run-workflow
 # May eventually need to add git ops
 # Passes on arguments