From 8bada9fce1acc05990c15e6527f020f7c7a0b821 Mon Sep 17 00:00:00 2001
From: Bryan Roessler <bryanroessler@gmail.com>
Date: Mon, 22 Jul 2024 17:48:27 -0400
Subject: [PATCH] Globalize gtr

---
 workflow/script-run-workflow | 91 ++++++++++++++++++++++--------------
 1 file changed, 55 insertions(+), 36 deletions(-)

diff --git a/workflow/script-run-workflow b/workflow/script-run-workflow
index 314668cf..bed40e59 100755
--- a/workflow/script-run-workflow
+++ b/workflow/script-run-workflow
@@ -385,20 +385,24 @@ gtf() {
   process_dir="GTF/Process"
   function_dir="GTF/Function"
   component_dir="GTF/Component"
+  out_dir="REMcRdy_lm_only"
+
+  py_gtf_dcon "$process_dir" "$out_dir"
 
-  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" "$d"/
+    rsync -a "$process_dir/$out_dir" "$d"/
     out_file="${d##*/}Results.txt" # Use the dirname to create each Results filename
-    pl_gtf "$d" "$out_file" & # parallelize
+    pl_gtf "$d" "$out_dir" & # parallelize
+    py_gtf_concat "$d" "$out_dir" "$out_file"
   done
-
 }
+
+
 # @section Submodules
 # @description Submodules provide functionaility to modules and are reusable between modules
-# Use a submodule when:
+# Use a submodule for:
 #   * Calling external scripts
 #   * Performing repetitive tasks
 #   *
@@ -408,7 +412,7 @@ submodule r_join_interact
 # @description JoinInteractExps3dev.R creates REMcRdy_lm_only.csv and Shift_only.csv
 r_join_interact() {
   debug "Running: ${FUNCNAME[0]}"
-  echo "Rscript JoinInteractExps3dev.R"
+  debug "Rscript JoinInteractExps3dev.R"
   Rscript JoinInteractExps3dev.R
   out_file="REMcRdy_lm_only.csv"
   out_file2="Shift_only.csv"
@@ -436,7 +440,7 @@ java_extract() {
     "ORF_List_Without_DAmPs.txt" 1 true true
   )
 
-  echo "${java_cmd[@]}"
+  debug "${java_cmd[@]}"
   "${java_cmd[@]}"
   [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
 }
@@ -448,7 +452,7 @@ submodule r_add_shift_values
 r_add_shift_values() {
   debug "Running: ${FUNCNAME[0]}"
   out_file="REMcHeatmaps/REMcWithShift.csv"
-  echo "Rscript AddShiftVals2.R"
+  debug "Rscript AddShiftVals2.R"
   Rscript AddShiftVals2.R
   rm -f "REMcHeatmaps/"*.pdf
   [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
@@ -460,10 +464,10 @@ submodule r_heat_maps_zscores
 r_heat_maps_zscores() {
   debug "Running: ${FUNCNAME[0]}"
   out_file="REMcHeatmaps/compiledREMcHeatmaps.pdf"
-  echo "Rscript REMcHeatmaps_zscores.R"
+  debug "Rscript REMcHeatmaps_zscores.R"
   Rscript REMcHeatmaps_zscores.R
   pdfs=(REMcHeatmaps/*.pdf)
-  echo "pdftk ${pdfs[*]} output $out_file"
+  debug "pdftk ${pdfs[*]} output $out_file"
   pdftk "${pdfs[@]}" output "$out_file"
   [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
 }
@@ -477,7 +481,7 @@ r_heat_maps_homology() {
   source_file="REMcHeatmaps/REMcWithShift.csv"
   target_file="$work_dir/REMcWithShift.csv"
   out_file="$work_dir/Homology/compiledREMcHomologyHeatmaps.pdf"
-  echo "rsync --archive $source_file $target_file"
+  debug "rsync --archive $source_file $target_file"
   rsync --archive "$source_file" "$target_file"
 
   # Clean old output
@@ -499,13 +503,14 @@ r_heat_maps_homology() {
 }
 
 
-submodule py_gtf
-# @description Perform python portion of GTF
+submodule py_gtf_dcon
+# @description Perform python dcon portion of GTF
 # @arg $1 string Directory to process
-py_gtf() {
+# @arg $2 string Output directory name
+py_gtf_dcon() {
   debug "Running: ${FUNCNAME[0]}"
   in_file="REMcRdy_lm_only.csv-finalTable.csv"
-  out_file="$1/REMcRdy_lm_only/1-0-0-finaltable.csv"
+  out_file="$1/$2/1-0-0-finaltable.csv"
   debug "$PYTHON DconJG2.py $in_file $1/"
   "$PYTHON" DconJG2.py "$in_file" "$1/"
   [[ -f $out_file ]] || (echo "$out_file does not exist"; return 1)
@@ -513,43 +518,38 @@ py_gtf() {
 
 
 submodule pl_gtf
-# @description Perl module for GTF
+# @description Perl modules for GTF
 # @arg $1 string working directory
-# @arg $2 string output file
+# @arg $2 string output directory name to look for txt files
 pl_gtf() {
   debug "Running: ${FUNCNAME[0]}" "$@"
-  set1="ORF_List_Without_DAmPs.txt"
-  pushd "$1" || return 1
 
+  pushd "$1" || return 1
+  set1="ORF_List_Without_DAmPs.txt"
   shopt -s nullglob
-  set2=(REMcRdy_lm_only/*.txt)
+  set2=("$2"/*.txt) # glob them all
   shopt -u nullglob
 
-  for s in "${set2[@]}"; do
-    debug "pl_analyze $set1 $s"
-    pl_analyze "$set1" "$s"
-    debug "pl_terms2tsv $s"
-    pl_terms2tsv "$s"
+  for s2 in "${set2[@]}"; do
+    debug "pl_analyze $set1 $s2"
+    pl_gtf_analyze "$set1" "$s2"
+    debug "pl_terms2tsv $s2"
+    pl_gtf_terms2tsv "$s2"
   done
 
-  # Concat the process ontology outputs from the /REMcReady_lm_only folder
-  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/ "$2"
-
-  [[ -f $2 ]] || (echo "$2 does not exist"; return 1)
   popd || return 1
 }
 
 
-submodule pl_analyze
+submodule pl_gtf_analyze
 # @description Perl analyze submodule
 # This seems weird to me because we're just overwriting the same data for all set2 members
 # https://metacpan.org/dist/GO-TermFinder/view/examples/analyze.pl
 # Is there a reason you need a custom version and not the original from cpan?
 # @arg $1 string Set 1
 # @arg $2 string Set 2
-pl_analyze() {
+pl_gtf_analyze() {
+  debug "Running: ${FUNCNAME[0]}"
   script="analyze_v2.pl"
   an="gene_association.sgd"
   out_file="gene_ontology_edit.obo"
@@ -558,22 +558,41 @@ pl_analyze() {
 }
 
 
-submodule pl_terms2tsv
+submodule pl_gtf_terms2tsv
 # @description Perl terms2tsv submodule
 # Probably should be translated to shell/python
 # @arg $1 string Set 2
-pl_terms2tsv() {
+pl_gtf_terms2tsv() {
+  debug "Running: ${FUNCNAME[0]}"
   script="terms2tsv_v4.pl"
   debug "$PERL $script $1.terms > $1.tsv"
   "$PERL" "$script" "$1.terms" > "$1.tsv"
 }
 
 
+submodule py_gtf_concat
+# @description Python concat submodule for GTF
+# Concat the process ontology outputs from the /REMcReady_lm_only folder
+# Probably should be translated to bash
+# @arg $1 string working directory
+# @arg $2 string output directory name to look for txt files
+# @arg $3 string output file
+py_gtf_concat() {
+  debug "Running: ${FUNCNAME[0]}"
+  pushd "$1" || return 1
+  script="Concatenate_GTF_results.py"
+  debug "$PYTHON $script $2/ $3"
+  "$PYTHON" "$script" "$2/" "$3"
+  [[ -f $3 ]] || (echo "$3 does not exist"; return 1)
+  popd || return 1
+}
+
+
 submodule r_compile_gtf
 # @description Compile GTF in R
 r_compile_gtf() {
   debug "Running: ${FUNCNAME[0]}"
-  echo "Rscript CompileGTF.R"
+  debug "Rscript CompileGTF.R"
   Rscript CompileGTF.R
 }