Feature: Basic slurp pipeline

- Update: Basic pseudo code in Python updated
- Update: Makfile: Updating formatting.

src/ontology/mondo-ingest.Makefile

@@ -160,7 +160,12 @@ mappings: sssom $(ALL_MAPPINGS)
 #################
 # Utils #########
 #################
-# Documentation for this commands in this section is in: `docs/developer/ordo.md`
+# Documentation for `report-mapping-annotations` and `update-jinja-sparql-queries`: `docs/developer/ordo.md`
+# TODO: When https://github.com/monarch-initiative/mondo-ingest/issues/43 is fixed, can change back to `requirements.txt`
+python-install-dependencies:
+	python3 -m pip install --upgrade pip
+	python3 -m pip install -r $(RELEASEDIR)/requirements-unlocked.txt
+
 
 report-mapping-annotations:
 	python3 $(SCRIPTSDIR)/ordo_mapping_annotations/report_mapping_annotations.py
@@ -254,10 +259,16 @@ signature_reports: $(ALL_MIRROR_SIGNTAURE_REPORTS) $(ALL_COMPONENT_SIGNTAURE_REP
 slurp/:
 	mkdir -p $@
 
+# Feel free to change the signature. Min ID is the next available Mondo ID.
 slurp/%.tsv: components/%.owl tmp/mondo.sssom.tsv reports/mirror-signature-mondo.tsv | slurp/
-	python $(SCRIPTSDIR)/migrate.py -i $< --mapping-file tmp/mondo.sssom.tsv --min-id 123000 --mondo-terms reports/mirror-signature-mondo.tsv --output $@
-	# Feel free to change the signature. Min ID is the next available Mondo ID.
+	python $(SCRIPTSDIR)/migrate.py \
+	-i $< \
+	--mapping-file tmp/mondo.sssom.tsv \
+	--min-id 123000 \
+	--mondo-terms reports/mirror-signature-mondo.tsv \
+	--output $@
 
 slurp-%: slurp/%.tsv
 
+# TODO: add more ontologies, e.g.: doid, icd10cm, icd10who, ncit, ordo
 slurp: slurp-omim

src/scripts/migrate.py

@@ -1,37 +1,54 @@
-# Migration pipeline
+"""Migration pipeline
 
 #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING
 #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING
 #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING
 #### THIS IS PSEUDO CODE NOT PYTHON OR ANYTHING
 
+TODOs:
+  - add CLI: look to makefile for what to include
+"""
+import oakliblib
+import pandas
+
+
 #Inputs:
-source_ontology #e.g. omim
-sssom_map # e.g. mondo.sssom.tsv
-min_id
-termlist_mondo
-
-#Outputs:
-data = []
-
-for t in source_ontology:
-    if t not in sssom_map['object_id']:
-        parents = []
-        migrate = True
-        for p in oak.get_direct_parents(t):
-            if p not in sssom_map['object_id']:
-                migrate = False
-                break
-            elif sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:exactMatch' \
-                or sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:narrowMatch':
-                # In other words, if the parent is mapped, and the mapping is either exact or narrower
-                parents.append(sssom_map[sssom_map['object_id']==p]['subject_id'])
-            else:
-                # Its fine, just continue looking for other parents in this case
-        if migrate and parents:
-            next_mondo_id = determine_next_available_mondo_id(min_id, termlist_mondo) # satrting from min_id, then counting up and checking if it does not already exist.
-            label = oak.get_label(t)
-            definition = oak.get_definition(t)
-            data.append({'mondo_id':next_mondo_id, 'xref': t, 'label': label, 'definition': definition})
-
-pandas.DataFrame(data).to_csv(fn, sep="\t")
+source_ontology = ''  #e.g. omim
+sssom_map = ''  # e.g. mondo.sssom.tsv
+min_id = ''
+termlist_mondo = ''
+
+
+def run(source_ontology = '', sssom_map = '', min_id = '', termlist_mondo = ''):
+    """source_ontology = ''  #e.g. omim
+    sssom_map = ''  # e.g. mondo.sssom.tsv
+    min_id = ''
+    termlist_mondo = ''"""
+    #Outputs:
+    data = []
+
+    for t in source_ontology:
+        if t not in sssom_map['object_id']:
+            parents = []
+            migrate = True
+            for p in oaklib.get_direct_parents(t):
+                if p not in sssom_map['object_id']:
+                    migrate = False
+                    break
+                elif sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:exactMatch' \
+                    or sssom_map[sssom_map['object_id']==p]['predicate_id'] = 'skos:narrowMatch':
+                    # In other words, if the parent is mapped, and the mapping is either exact or narrower
+                    parents.append(sssom_map[sssom_map['object_id']==p]['subject_id'])
+                else:
+                    # Its fine, just continue looking for other parents in this case
+            if migrate and parents:
+                next_mondo_id = determine_next_available_mondo_id(min_id, termlist_mondo) # satrting from min_id, then counting up and checking if it does not already exist.
+                label = oaklib.get_label(t)
+                definition = oaklib.get_definition(t)
+                data.append({'mondo_id':next_mondo_id, 'xref': t, 'label': label, 'definition': definition})
+
+    pandas.DataFrame(data).to_csv(fn, sep="\t")
+
+
+if __name__ == '__main__':
+    run()