Add scripts to run from study RID

.gitignore

@@ -297,6 +297,8 @@ timeline*.html*
 *.tmp
 *.swp
 *.out
+*_studyRID.json
+*_studyRID.csv
 run*.sh
 
 !.gitkeep

cleanup.sh

@@ -5,3 +5,5 @@ rm timeline*.html*
 rm .nextflow*.log*
 rm -r .nextflow/
 rm -r work/
+rm *_studyRID.json
+rm *_studyRID.csv

workflow/scripts/splitStudy.py

+#!/usr/bin/env python3
+
+import argparse
+import pandas as pd
+import warnings
+warnings.simplefilter(action='ignore', category=FutureWarning)
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-s', '--studyRID',help="The study RID.",required=True)
+    args = parser.parse_args()
+    return args
+
+def main():
+    args = get_args()
+    studyRID=pd.read_json(args.studyRID+"_studyRID.json")
+    if studyRID["RID"].count() > 0:
+        studyRID["RID"].to_csv(args.studyRID+"_studyRID.csv",header=False,index=False)
+    else:
+        raise Exception("No associated replicates found: %s" %
+            studyRID)
+
+if __name__ == '__main__':
+    main()

workflow/scripts/splitStudy.sh

+#!/bin/bash
+
+# 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/splitStudy.py -s $1
+
+# 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}; done < "$1_studyRID.csv" | xargs -P 5 -I {} nextflow run workflow/rna-seq.nf --repRID {}
+
+# cleanup study RID files
+rm $1_studyRID.json
+rm $1_studyRID.csv

[Gervaise Henry]

Run in repo root dir: sh workflow/scripts/splitStudy.sh [studyRID]

It will run in parallel in batches of 5 replicatesRID (this can be changed in splitStudy.sh: xargs -P flag)