Update split study.

scripts/split_study.sh

@@ -4,18 +4,71 @@
 #SBATCH --job-name GUDMAP-RBK_Study
 #SBATCH -t 7-0:0:0
 
-# query GUDMAP/RBK for study RID
-echo "curl --location --request GET 'https://www.gudmap.org/ermrest/catalog/2/entity/RNASeq:Replicate/Study_RID="${1}"'" | bash > $1_studyRID.json
 
-# extract replicate RIDs
-module load python/3.6.4-anaconda
-python3 ./workflow/scripts/split_study.py -s $1
+script_name="split_study.sh"
 
-# run pipeline on replicate RIDs in parallel
-module load nextflow/20.01.0
-module load singularity/3.5.3
-while read repRID; do echo ${repRID}; sleep 30; done < "$1_studyRID.csv" | xargs -P 5 -I {} nextflow -q run workflow/rna-seq.nf --repRID {} --source production --deriva /project/BICF/BICF_Core/shared/gudmap/test_data/auth/credential.json --bdbag /project/BICF/BICF_Core/shared/gudmap/test_data/auth/cookies.txt --dev false --upload true --email gervaise.henry@utsouthwestern.edu -with-report ./output/{}_report.html -with-timeline ./output/{}_timeline.html
+#Help function
+usage() {
+  echo "-h  --Help documentation for $script_name"
+  echo "-r  --Study_RID."
+  echo "-t  --Tag of pipelne"
+  echo "Example: $script_name -r 16-1ZP0 -t 0.1.0"
+  exit 1
+}
 
-# cleanup study RID files
-rm $1_studyRID.json
-#rm $1_studyRID.csv
+main(){
+
+    # Load required modules
+    module load python/3.6.4-anaconda
+    module load nextflow/20.01.0
+    module load singularity/3.5.3
+
+    # Parsing options
+    OPTIND=1 # Reset OPTIND
+    while getopts :r:t:h opt
+        do
+            case $opt in
+                r) rid=$OPTARG;;
+                t) tag=$OPTARG;;
+                h) usage;;
+            esac
+        done
+
+    shift $(($OPTIND -1))
+
+    # Check for mandatory options
+    if [[ -z $rid ]] || [[ -z $tag ]]; then
+        usage
+    fi
+
+    # query GUDMAP/RBK for study RID
+    echo "curl --location --request GET 'https://www.gudmap.org/ermrest/catalog/2/entity/RNASeq:Replicate/Study_RID="${rid}"'" | bash > $rid\_studyRID.json
+
+  # extract replicate RIDs
+
+  python3 ./scripts/split_study.py -s $rid
+
+  # cleanup study RID files
+  rm $rid\_studyRID.json
+
+  # make dir for study
+  mkdir $rid
+  mv $rid\_studyRID.csv $rid
+  cd $rid
+
+  # download version of RNA-seq pipelne
+  existed_in_remote=$( git ls-remote --tags git@git.biohpc.swmed.edu:gudmap_rbk/rna-seq.git ${tag})
+
+  if [[ -z ${existed_in_remote} ]]; then
+      echo "The tag ${tag} doesn't exist."
+      exit 1
+  fi
+
+  git clone -b $tag --depth 1 git@git.biohpc.swmed.edu:gudmap_rbk/rna-seq.git
+  cd rna-seq
+
+  # run pipeline on replicate RIDs in parallel
+  while read repRID; do echo ${repRID}; sleep 30; done < "../${rid}_studyRID.csv" | xargs -P 5 -I {} nextflow -q run workflow/rna-seq.nf --repRID {} --source production --deriva /project/BICF/BICF_Core/shared/gudmap/test_data/auth/credential.json --bdbag /project/BICF/BICF_Core/shared/gudmap/test_data/auth/cookies.txt --dev false --upload true --email gervaise.henry@utsouthwestern.edu -with-report ./output/{}_report.html -with-timeline ./output/{}_timeline.html
+}
+
+main "$@"