Run pipeline once

RIVM-bioinformatics · Jul 11, 2022 · 35c69ef · 35c69ef
1 parent 61b30ae
commit 35c69ef
Show file tree

Hide file tree

Showing 2 changed files with 44 additions and 37 deletions.
diff --git a/bin/chewbbaca_per_genus.sh b/bin/chewbbaca_per_genus.sh
@@ -10,15 +10,15 @@ genus="$5"
 
 # Make new variables
 downloaded_scheme="${db_dir}/downloaded_schemes/${genus}"
-prepared_scheme="${db_dir}/prepared_schemes/${genus}/scheme"
+prepared_scheme="${db_dir}/prepared_schemes/${genus}"
 script_path="$( cd -- "$(dirname "$0")" >/dev/null 2>&1 ; pwd -P )"
-prodigal_training_file="$script_path/../files/prodigal_training_files/${genus}.trn"
+prodigal_training_file=$(realpath "$script_path/../files/prodigal_training_files/${genus}.trn")
 
 echo "Deleting any previous results from old ChewBBACA runs if existing in ${output_dir}...\n"
 rm -rf "results_*"  
 
-if [ ! -f "${prepared_scheme}_summary_stats.txt" ]; then
-    echo "\nPreparing scheme for running it with ChewBBACA...\n"
+if [ ! -f "$db_dir/prepared_schemes/${genus}_summary_stats.txt" ]; then
+    echo "Preparing scheme for running it with ChewBBACA..."
     chewBBACA.py PrepExternalSchema -i "$downloaded_scheme" \
         --output-directory "$prepared_scheme" \
         --cpu $threads \
@@ -35,7 +35,7 @@ chewBBACA.py AlleleCall --cpu ${threads} \
                 -i "${input_files}" \
                 -g "${prepared_scheme}" \
                 -o "." \
-                --ptf "$prodigal_training_file"
+                --ptf "$prodigal_training_file" \
                 --fr
 
 find "." -type f -name "results_alleles.tsv" -exec cp {} "." \;

diff --git a/run_pipeline.sh b/run_pipeline.sh
@@ -24,30 +24,6 @@ fi
 #   input_fastq="${input_dir}/clean_fastq"
 # fi
 
-case $PROJECT_NAME in
-
-  svstec)
-    GENUS_ALL="escherichia shigella stec"
-    ;;
-  svshig)
-    GENUS_ALL="escherichia shigella"
-    ;;
-  salm)
-    GENUS_ALL="salmonella"
-    ;;
-  campy)
-    GENUS_ALL="campylobacter"
-    ;;
-  svlismon)
-    GENUS_ALL="listeria listeria_optional"
-    ;;
-  yers)
-    GENUS_ALL="yersinia"
-    ;;
-  *)
-    GENUS_ALL="other"
-    ;;
-esac
 
 
 #----------------------------------------------#
@@ -80,15 +56,46 @@ else
     QUEUE="bio"
 fi
 
-for GENUS in $GENUS_ALL
-do
+case $PROJECT_NAME in
+  svstec)
+    GENUS_ALL="escherichia shigella stec"
+    GENUS="stec"
+    ;;
+  svshig)
+    GENUS_ALL="escherichia shigella"
+    GENUS="shigella"
+    ;;
+  salm)
+    GENUS_ALL="salmonella"
+    GENUS="salmonella"
+    ;;
+  campy)
+    GENUS_ALL="campylobacter"
+    GENUS="campylobacter"
+    ;;
+  svlismon)
+    GENUS_ALL="listeria listeria_optional"
+    GENUS="listeria"
+    ;;
+  yers)
+    GENUS_ALL="yersinia"
+    GENUS="yersinia"
+    ;;
+  *)
+    GENUS_ALL="other"
+    ;;
+esac
+
 #----------------------------------------------#
 # Copying database directory if it exists
-
-echo -e "\nCopying the cgMLST schema from $GENUS..."
 DB_DIR="schemes"
-mkdir -p "$DB_DIR/prepared_schemes"
-cp -r "/mnt/db/juno/cgmlst/prepared_schemes/$GENUS" "$DB_DIR/prepared_schemes/$GENUS"
+for G in $GENUS_ALL
+do
+  echo -e "\nCopying the cgMLST schema from /mnt/db/juno/cgmlst/prepared_schemes/$G..."
+  mkdir -p "$DB_DIR/prepared_schemes"
+  cp -r --no-preserve=mode,ownership "/mnt/db/juno/cgmlst/prepared_schemes/$G" "$DB_DIR/prepared_schemes/$G"
+  cp --no-preserve=mode,ownership /mnt/db/juno/cgmlst/prepared_schemes/${G}_{sum,inv}*.txt "$DB_DIR/prepared_schemes/"
+done
 
 #----------------------------------------------#
 # Run the pipeline
@@ -100,8 +107,8 @@ python juno_cgmlst.py \
     -o "$output_dir" \
     -g "$GENUS" \
     -d "$DB_DIR"
-result=$((result > $? ? result : $?)) # Maximum of previous return value and result https://unix.stackexchange.com/a/186703
-done
+
+result=$?
 
 #----------------------------------------------#
 # Propagate metadata