Merge pull request #363 from microbiomedata/issue-352-proc-inst-enum

processing institution code and data

src/schema/nmdc.yaml

@@ -713,6 +713,28 @@ enums:
         meaning: OBI:0000103
     comments:
       - credit enums come from https://casrai.org/credit/
+  processing_institution_enum:
+    name: processing_institution_enum
+    comments:
+      - This will become the range of processing_institution.omics processing
+      - use ROR meanings like https://ror.org/0168r3w48 for UCSD
+    from_schema: NMDC_enums_roundtrip
+    permissible_values:
+      UCSD:
+        text: UCSD
+        title: University of California, San Diego
+        meaning: https://ror.org/0168r3w48
+      JGI:
+        text: JGI
+        title: Joint Genome Institute
+        meaning: https://ror.org/04xm1d337
+      EMSL:
+        text: EMSL
+        title: Environmental Molecular Sciences Laboratory
+        meaning: https://ror.org/04rc0xn13
+        comments:
+          - replaces Environmental Molecular Science Laboratory
+          - replaces Environmental Molecular Sciences Lab
 
 slots:
   ess dive datasets:

util/fetch_omics_processing_set.py

@@ -0,0 +1,43 @@
+import csv
+import pprint
+
+from pymongo import MongoClient
+
+client = MongoClient(
+    "mongodb://mam:NJAxcszXBt3fu%21q@localhost:27027/?authSource=admin&readPreference=primary&directConnection=true&ssl=false"
+)
+
+id_inst_file ="../target/omics_processing_id_inst.tsv"
+
+# on the verbose side for just retrieving a collection
+result_filter = {}
+result = client["nmdc"]["omics_processing_set"].find(filter=result_filter)
+
+# print(type(result))
+# <class 'pymongo.cursor.Cursor'>
+
+# ['GOLD_sequencing_project_identifiers',
+#  '_id',
+#  'add_date',
+#  'has_input',
+#  'has_output',
+#  'id',
+#  'mod_date',
+#  'name',
+#  'ncbi_project_name',
+#  'omics_type',
+#  'part_of',
+#  'principal_investigator',
+#  'processing_institution',
+#  'type']
+
+id_inst = []
+for i in result:
+    id_inst.append(
+        {"id": i["id"], "processing_institution": i["processing_institution"]}
+    )
+
+with open(id_inst_file, 'w') as f:
+    csv_writer = csv.DictWriter(f, list(id_inst[0].keys()), delimiter="\t")
+    csv_writer.writeheader()
+    csv_writer.writerows(id_inst)