diff galaxy-tools/biobank/tools/enrollments_by_platewells.py @ 0:ba6cf6ede027 draft default tip

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/galaxy-tools/biobank/tools/enrollments_by_platewells.py	Wed Sep 28 06:03:30 2016 -0400
@@ -0,0 +1,77 @@
+"""
+From a list of platewells retrieves the enrollments code of the connected individual
+"""
+import argparse
+import csv
+import sys
+
+from bl.vl.kb import KnowledgeBase as KB
+import bl.vl.utils.ome_utils as vlu
+from bl.vl.utils import LOG_LEVELS, get_logger
+
+def make_parser():
+  parser = argparse.ArgumentParser(description='From platewells 2 enrollments code')
+  parser.add_argument('--logfile', type=str, help='log file (default=stderr)')
+  parser.add_argument('--loglevel', type=str, choices = LOG_LEVELS,
+                      help='logging level', default='INFO')
+  parser.add_argument('-H', '--host', type=str, help='omero hostname')
+  parser.add_argument('-U', '--user', type=str, help='omero user')
+  parser.add_argument('-P', '--passwd', type=str, help='omero password')
+  parser.add_argument('-S', '--study', type=str, required=True,
+                      help='a study used to retrieve individuals')
+  parser.add_argument('--ifile', type=str, required=True,
+                      help='list of platewells used to fetch data')
+  parser.add_argument('--ofile', type=str, help='output file path',
+                      required=True)
+  return parser
+
+
+def main(argv):
+  parser = make_parser()
+  args = parser.parse_args(argv)
+
+  logger = get_logger('pws2enrolls', level=args.loglevel,
+                      filename=args.logfile)
+  try:
+    host = args.host or vlu.ome_host()
+    user = args.user or vlu.ome_user()
+    passwd = args.passwd or vlu.ome_passwd()
+  except ValueError, ve:
+    logger.critical(ve)
+    sys.exit(ve)
+
+  kb = KB(driver='omero')(host, user, passwd)
+  study = kb.get_study(args.study)
+  enrolled_map = {e.individual.id:e  for e in kb.get_enrolled(study)}
+  logger.info('Loaded {} enrolled individuals for study {}'.format(len(enrolled_map), study.label))
+  plates = kb.get_objects(kb.TiterPlate)
+  logger.info('Loaded {} plates'.format(len(plates)))
+  pws_map = {':'.join([w.container.barcode, w.label]):w for w in kb.get_objects(kb.PlateWell) 
+             if w.container.barcode}
+  logger.info('Loaded {} platewells'.format(len(pws_map)))
+  #records = []
+  of=open(args.ofile, 'w')
+  writer=csv.DictWriter(of, ['platewell', 'status', 'enrollment'], 
+                        delimiter='\t', quotechar='"', restval='None')
+  writer.writeheader()
+  with open(args.ifile, 'r') as f:
+    reader=csv.DictReader(f, delimiter='\t')
+    logger.info('Searching individuals connected to the platewells')
+    for r in reader:
+      ind=kb.dt.get_connected(pws_map[r['platewell']], kb.Individual, 
+                              kb.dt.DIRECTION_INCOMING)
+      try:          
+        record = {'platewell': r['platewell'],
+                  'status': pws_map[r['platewell']].status.enum_label(),
+                  'enrollment': ':'.join([study.label,enrolled_map[ind[0].id].studyCode])}
+      except KeyError as e:
+        logger.warning('not enrolled {}'.format(r['platewell']))
+        record = {'platewell': r['platewell'],
+                  'status': pws_map[r['platewell']].status.enum_label(),
+                  'enrollment': ':'.join([study.label,'not_enrolled'])}
+      writer.writerow(record)
+  of.close()
+
+          
+if __name__ == "__main__":
+  main(sys.argv[1:])