Add pubmed info to Drug Central ingest (if present)

kg_covid_19/transform_utils/drug_central/drug_central.py

@@ -48,7 +48,7 @@ def run(self, data_file: Optional[str] = None, species: str = "Homo sapiens") ->
         drug_gene_edge_label = "biolink:interacts_with"
         drug_gene_edge_relation = "RO:0002436"  # molecularly interacts with
         self.edge_header = ['subject', 'edge_label', 'object', 'relation',
-                            'provided_by', 'comment']
+                            'provided_by', 'publication', 'comment']
 
         # unzip tcrd.zip and get tchem and tclin filenames
         tempdir = tempfile.mkdtemp()
@@ -118,11 +118,28 @@ def run(self, data_file: Optional[str] = None, species: str = "Homo sapiens") ->
                                                gene_id,
                                                drug_gene_edge_relation,
                                                self.source_name,
+                                               get_pub_info_from_dict(items_dict),
                                                items_dict['ACT_COMMENT']])
 
         return None
 
 
+def get_pub_info_from_dict(items_dict,
+                           pubmed_prefix="PMID",
+                           uri_match='http://www.ncbi.nlm.nih.gov/pubmed/'
+                           ) -> str:
+    pubs = []
+    if 'ACT_SOURCE_URL' in items_dict and re.match(uri_match,
+                                                   items_dict['ACT_SOURCE_URL']):
+        pubs.append(
+            items_dict['ACT_SOURCE_URL'].replace(uri_match, pubmed_prefix + ":"))
+    if 'MOA_SOURCE_URL' in items_dict and re.match(uri_match,
+                                                   items_dict['MOA_SOURCE_URL']):
+        pubs.append(
+            items_dict['MOA_SOURCE_URL'].replace(uri_match, pubmed_prefix + ":"))
+    return "|".join(pubs)
+
+
 def tsv_to_dict(input_file: str, col_for_key: str) -> dict:
     this_dict: dict = defaultdict(list)
     with open(input_file) as file:

tests/test_drug_central.py

@@ -3,7 +3,8 @@
 import unittest
 
 from kg_covid_19.transform_utils.drug_central.drug_central import \
-    parse_drug_central_line, unzip_and_get_tclin_tchem, tsv_to_dict
+    parse_drug_central_line, unzip_and_get_tclin_tchem, tsv_to_dict, \
+    get_pub_info_from_dict
 from kg_covid_19.utils.transform_utils import parse_header
 from parameterized import parameterized
 
@@ -63,3 +64,28 @@ def test_unzip_and_get_tclin_tchem(self) -> None:
         self.assertEqual(tclin, os.path.join(tempdir, 'tclin_05122020.tsv'))
         self.assertEqual(tchem, os.path.join(tempdir, 'tchem_drugs_05122020.tsv'))
 
+    @parameterized.expand([
+    ('', ''),
+    ({'ACT_SOURCE_URL': '',
+     'MOA_SOURCE_URL': 'https://www.ebi.ac.uk/chembl/compound/inspect/CHEMBL1200749'},
+     ''
+     ),
+    ({'ACT_SOURCE_URL': 'https://www.ebi.ac.uk/chembl/compound/inspect/CHEMBL1200749',
+     'MOA_SOURCE_URL': ''},
+     ''
+     ),
+    ({'ACT_SOURCE_URL': 'https://www.ebi.ac.uk/chembl/compound/inspect/CHEMBL1200749',
+     'MOA_SOURCE_URL': 'https://www.ebi.ac.uk/chembl/compound/inspect/CHEMBL1200749'},
+     ''
+     ),
+    ({'ACT_SOURCE_URL': 'http://www.ncbi.nlm.nih.gov/pubmed/17275317',
+     'MOA_SOURCE_URL': 'https://www.ebi.ac.uk/chembl/compound/inspect/CHEMBL1200749'},
+     'PMID:17275317'
+     ),
+    ({'ACT_SOURCE_URL': 'http://www.ncbi.nlm.nih.gov/pubmed/17275317',
+      'MOA_SOURCE_URL': 'http://www.ncbi.nlm.nih.gov/pubmed/3207986'},
+     'PMID:17275317|PMID:3207986'
+     ),
+    ])
+    def test_get_pub_info_from_dict(self, this_dict, expected_pub_info) -> None:
+        self.assertEqual(expected_pub_info, get_pub_info_from_dict(this_dict))