Merge pull request #231 from Knowledge-Graph-Hub/fix_sars_cov2_names_…

…symbols

Fix names and symbols for SARS-CoV-2 gene annotation ingest

kg_covid_19/transform_utils/sars_cov_2_gene_annot/sars_cov_2_gene_annot.py

@@ -21,7 +21,8 @@ def __init__(self, input_dir: Optional[str] = None, output_dir: str = None):
         source_name = "sars_cov_2_gene_annot"
         super().__init__(source_name, input_dir, output_dir)
 
-        self.node_header = ['id', 'name', 'category', 'synonym', 'in_taxon', 'provided_by']
+        self.node_header = ['id', 'name', 'category', 'full_name', 'synonym',
+                            'in_taxon', 'provided_by']
         self.edge_header = ['subject', 'edge_label', 'object', 'relation',
                             'provided_by', 'DB_References', 'ECO_code', 'With',
                             'Interacting_taxon_ID',
@@ -111,26 +112,41 @@ def gpi_to_gene_node_data(self, rec: dict) -> list:
         :param rec: record from gpi iterator
         :return: list of node items, one for each thing in self.node_header
         """
-        # ['id', 'name', 'category', 'synonym', 'in_taxon']
+        # ['id', 'name', 'category', 'full_name', 'synonym', 'in_taxon', 'provided_by']
         id: str = self._rec_to_id(rec)
 
         try:
             name_list = get_item_by_priority(rec, ['DB_Object_Name'])
             if name_list is not None and len(name_list) > 0:
-                name = name_list[0]
+                full_name = name_list[0]
+                if len(name_list) > 1:
+                    logging.warning(
+                        "Found >1 DB_Object_Name in rec, using the first one")
+            else:
+                full_name = ''
+        except (IndexError, ItemInDictNotFound):
+            full_name = ''
+
+        try:
+            symbol_list = get_item_by_priority(rec, ['DB_Object_Symbol'])
+            if symbol_list is not None and len(symbol_list) > 0:
+                name = symbol_list[0]
+                if len(symbol_list) > 1:
+                    logging.warning(
+                        "Found >1 DB_Object_Symbol in rec, using the first one")
             else:
                 name = ''
         except (IndexError, ItemInDictNotFound):
-            name = ''
+            full_name = ''
 
         category = self.protein_node_type
         try:
-            synonym = get_item_by_priority(rec, ['DB_Object_Synonym'])[0]
+            synonym = get_item_by_priority(rec, ['DB_Object_Synonym'])
         except (IndexError, ItemInDictNotFound):
             synonym = ''
         taxon = get_item_by_priority(rec, ['Taxon'])
         taxon = ":".join([self.ncbi_taxon_prefix, taxon.split(":")[1]])
-        return [id, name, category, synonym, taxon, self.source_name]
+        return [id, name, category, full_name, synonym, taxon, self.source_name]
 
 
 def _gpi12iterator(handle: TextIO) -> Generator:

kg_covid_19/utils/transform_utils.py

@@ -6,6 +6,7 @@
 from typing import Any, Dict, List, Union, TextIO
 from tqdm import tqdm  # type: ignore
 
+
 class TransformError(Exception):
     """Base class for other exceptions"""
     pass
@@ -102,6 +103,7 @@ def get_item_by_priority(items_dict: dict, keys_by_priority: list) -> str:
         raise ItemInDictNotFound("Can't find item in items_dict {}".format(items_dict))
     return value
 
+
 def data_to_dict(these_keys, these_values) -> dict:
     """Zip up two lists to make a dict
 
@@ -111,6 +113,7 @@ def data_to_dict(these_keys, these_values) -> dict:
     """
     return dict(zip(these_keys, these_values))
 
+
 def uniprot_make_name_to_id_mapping(dat_gz_file: str) -> dict:
     """Given a Uniprot dat.gz file, like this:
     ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/HUMAN_9606_idmapping.dat.gz

tests/test_sars_cov_2_gene_annot.py

@@ -9,8 +9,8 @@
     _gpi12iterator, _gpa11iterator
 
 
-class TestPharmGKB(TestCase):
-    """Tests the ttd transform"""
+class TestSarsGeneAnnot(TestCase):
+    """Tests the SARS-CoV-2 gene annotation transform"""
 
     def setUp(self) -> None:
         self.sc2ga = SARSCoV2GeneAnnot()
@@ -43,8 +43,13 @@ def test_gpi_to_gene_node(self):
         item = next(gpi_iter)
         node = self.sc2ga.gpi_to_gene_node_data(item)
         self.assertEqual(len(self.sc2ga.node_header), len(node))
-        self.assertEqual(node,
-                         ['UniProtKB:P0DTD2', 'Protein 9b', 'biolink:Protein', '', 'NCBITaxon:2697049', 'sars_cov_2_gene_annot'])
+        self.assertEqual(node, ['UniProtKB:P0DTD2',
+                                'P0DTD2',
+                                'biolink:Protein',
+                                'Protein 9b',
+                                '',
+                                'NCBITaxon:2697049',
+                                'sars_cov_2_gene_annot'])
 
     def test_gpa_to_edge_data(self):
         gpa_iter = _gpa11iterator(self.gpa_fh)