Use the NCBITaxon prefix instead of NCBI_TAXON in examples and tests (#1520)

NCBITaxon is the canonical CURIE prefix for the NCBI Taxonomy ontology. The
back-compat test and its 1.8.0 reproduction script keep NCBI_TAXON because they
read/regenerate historical data, and the hdmf-common-schema submodule is left
untouched.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Oliver Ruebel <oruebel@users.noreply.github.com>

Author: 3 people

docs/gallery/example_term_set.yaml

@@ -2,7 +2,7 @@ id: termset/species_example
 name: Species
 version: 0.0.1
 prefixes:
-  NCBI_TAXON: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
+  NCBITaxon: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
 imports:
   - linkml:types
 default_range: string
@@ -12,13 +12,13 @@ enums:
     permissible_values:
       Homo sapiens:
         description: the species is human
-        meaning: NCBI_TAXON:9606
+        meaning: NCBITaxon:9606
       Mus musculus:
         description: the species is a house mouse
-        meaning: NCBI_TAXON:10090
+        meaning: NCBITaxon:10090
       Ursus arctos horribilis:
         description: the species is a grizzly bear
-        meaning: NCBI_TAXON:116960
+        meaning: NCBITaxon:116960
       Myrmecophaga tridactyla:
         description: the species is an anteater
-        meaning: NCBI_TAXON:71006
+        meaning: NCBITaxon:71006

docs/gallery/plot_external_resources.py

@@ -139,14 +139,14 @@ def __init__(self, **kwargs):
 herd.add_ref(
     container=data,
     key='Homo sapiens',
-    entity_id='NCBI_TAXON:9606',
+    entity_id='NCBITaxon:9606',
     entity_uri='https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606'
 )
 
 herd.add_ref(
     container=data,
     key='Mus musculus',
-    entity_id='NCBI_TAXON:10090',
+    entity_id='NCBITaxon:10090',
     entity_uri='https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=10090'
 )
 
@@ -208,7 +208,7 @@ def __init__(self, **kwargs):
     container=species,
     attribute='Species_Data',
     key='Ursus arctos horribilis',
-    entity_id='NCBI_TAXON:116960',
+    entity_id='NCBITaxon:116960',
     entity_uri='https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id'
 )
 
@@ -316,7 +316,7 @@ def __init__(self, **kwargs):
     container=data,
     field='species',
     key='Mus musculus',
-    entity_id='NCBI_TAXON:txid10090',
+    entity_id='NCBITaxon:txid10090',
     entity_uri='https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=10090'
 )
 

docs/gallery/plot_term_set.py

@@ -42,7 +42,7 @@
 1. The name of the schema is up to the user, e.g., the name could be "Species" if the term set will
    contain species terms.
 2. The prefixes will be the standardized prefix of your source, followed by the URI to the terms.
-   For example, the NCBI Taxonomy is abbreviated as NCBI_TAXON, and Ensemble is simply Ensemble.
+   For example, the NCBI Taxonomy is abbreviated as NCBITaxon, and Ensemble is simply Ensemble.
    As mentioned prior, the URI needs to be to the terms; this is to allow the URI to later be coupled
    with the source id for the term to create a valid link to the term source page.
 3. The schema uses LinkML enumerations to list all the possible terms. To define the all the permissible

tests/unit/common/test_resources.py

@@ -145,13 +145,13 @@ def test_repr_populated(self):
         container.parent = file
         er.add_ref(container=container,
                    key='Mus musculus',
-                   entity_id='NCBI_TAXON:10090',
+                   entity_id='NCBITaxon:10090',
                    entity_uri='http://x')
         text = repr(er)
         self.assertIn('1 key(s), 1 entity(ies), 1 object(s), 1 file(s)', text)
         # the HTML repr surfaces the flattened table content
         html = er._repr_html_()
-        self.assertIn('NCBI_TAXON:10090', html)
+        self.assertIn('NCBITaxon:10090', html)
         self.assertIn('http://x', html)
 
     def test_assert_external_resources_equal(self):
@@ -390,7 +390,7 @@ def test_add_ref_container_data(self):
 
         er.add_ref_container(root_container=em)
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', '', '')])
 
@@ -413,7 +413,7 @@ def test_add_ref_container_attr(self):
 
         er.add_ref_container(root_container=em)
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', 'description', '')])
 
@@ -437,7 +437,7 @@ def test_add_ref_termset(self):
                     termset=terms
                    )
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', '', '')])
 
@@ -475,7 +475,7 @@ def test_add_ref_termset_attribute_none(self):
                     termset=terms
                    )
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', '', '')])
 
@@ -498,7 +498,7 @@ def test_add_ref_termset_data_object_list(self):
                     termset=terms
                    )
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, species.object_id, 'DynamicTable', 'colnames', '')])
 
@@ -521,9 +521,9 @@ def test_add_ref_termset_bulk(self):
                     termset=terms
                    )
         self.assertEqual(er.keys.data, [('Homo sapiens',), ('Mus musculus',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606'),
-        ('NCBI_TAXON:10090',
+        ('NCBITaxon:10090',
          'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=10090')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', '', '')])
 
@@ -546,7 +546,7 @@ def test_add_ref_termset_missing_terms(self):
                                             termset=terms
                                            )
         self.assertEqual(er.keys.data, [('Homo sapiens',)])
-        self.assertEqual(er.entities.data, [('NCBI_TAXON:9606',
+        self.assertEqual(er.entities.data, [('NCBITaxon:9606',
         'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606')])
         self.assertEqual(er.objects.data, [(0, col1.object_id, 'VectorData', '', '')])
         self.assertEqual(missing_terms, {'missing_terms': ['missing_term']})
@@ -792,7 +792,7 @@ def test_get_obj_entities_hdf5_roundtrip(self):
         data.parent = file
         er.add_ref(container=data,
                    key='Homo sapiens',
-                   entity_id='NCBI_TAXON:9606',
+                   entity_id='NCBITaxon:9606',
                    entity_uri='http://x')
 
         path = 'test_HERD_hdf5_roundtrip.h5'
@@ -809,7 +809,7 @@ def test_get_obj_entities_hdf5_roundtrip(self):
             remove_test_file(path)
 
         expected_df = pd.DataFrame.from_dict(
-            {'entity_id': {0: 'NCBI_TAXON:9606'},
+            {'entity_id': {0: 'NCBITaxon:9606'},
              'entity_uri': {0: 'http://x'}}
         )
         pd.testing.assert_frame_equal(df, expected_df)

tests/unit/example_test_term_set.yaml

@@ -2,7 +2,7 @@ id: termset/species_example
 name: Species
 version: 0.0.1
 prefixes:
-  NCBI_TAXON: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
+  NCBITaxon: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
 imports:
   - linkml:types
 default_range: string
@@ -12,16 +12,16 @@ enums:
     permissible_values:
       Homo sapiens:
         description: the species is human
-        meaning: NCBI_TAXON:9606
+        meaning: NCBITaxon:9606
       Mus musculus:
         description: the species is a house mouse
-        meaning: NCBI_TAXON:10090
+        meaning: NCBITaxon:10090
       Ursus arctos horribilis:
         description: the species is a grizzly bear
-        meaning: NCBI_TAXON:116960
+        meaning: NCBITaxon:116960
       Myrmecophaga tridactyla:
         description: the species is an anteater
-        meaning: NCBI_TAXON:71006
+        meaning: NCBITaxon:71006
       Ailuropoda melanoleuca:
         description: the species is a panda
-        meaning: NCBI_TAXON:9646
+        meaning: NCBITaxon:9646

tests/unit/example_test_term_set2.yaml

@@ -2,7 +2,7 @@ id: termset/species_example2
 name: Species
 version: 0.0.1
 prefixes:
-  NCBI_TAXON: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
+  NCBITaxon: https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=
 imports:
   - linkml:types
 default_range: string
@@ -12,10 +12,10 @@ enums:
     permissible_values:
       Homo sapiens:
         description: the species is human
-        meaning: NCBI_TAXON:9606
+        meaning: NCBITaxon:9606
       Mus musculus:
         description: the species is a house mouse
-        meaning: NCBI_TAXON:10090
+        meaning: NCBITaxon:10090
       Ursus arctos horribilis:
         description: the species is a grizzly bear
-        meaning: NCBI_TAXON:116960
+        meaning: NCBITaxon:116960

tests/unit/test_io_hdf5_h5tools.py

@@ -1237,7 +1237,7 @@ def test_io_write_extend_herd(self):
 
             self.assertEqual(read_herd.keys.data, [('special',), ('Homo sapiens',)])
             self.assertEqual(read_herd.entities.data[0], ('id11', 'url11'))
-            self.assertEqual(read_herd.entities.data[1], ('NCBI_TAXON:9606',
+            self.assertEqual(read_herd.entities.data[1], ('NCBITaxon:9606',
             'https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?mode=Info&id=9606'))
             self.assertEqual(read_herd.objects.data[0],
             (0, read_foofile.object_id, 'FooFile', '', ''))

tests/unit/test_term_set.py

@@ -36,32 +36,32 @@ def tearDown(self):
     def test_termset_setup(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set.yaml')
         self.assertEqual(termset.name, 'Species')
-        self.assertEqual(list(termset.sources), ['NCBI_TAXON'])
+        self.assertEqual(list(termset.sources), ['NCBITaxon'])
 
     def test_repr_short(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set2.yaml')
-        output = ('Schema Path: tests/unit/example_test_term_set2.yaml\nSources: NCBI_TAXON\nTerms: \n'
+        output = ('Schema Path: tests/unit/example_test_term_set2.yaml\nSources: NCBITaxon\nTerms: \n'
                   '   - Homo sapiens\n   - Mus musculus\n   - Ursus arctos horribilis\nNumber of terms: 3')
         self.assertEqual(repr(termset), output)
 
     def test_repr_html_short(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set2.yaml')
         output = ('<b>Schema Path: </b>tests/unit/example_test_term_set2.yaml<br><b>Sources:'
-                  ' </b>NCBI_TAXON<br><b> Terms: </b><li> Homo sapiens </li><li> Mus musculus'
+                  ' </b>NCBITaxon<br><b> Terms: </b><li> Homo sapiens </li><li> Mus musculus'
                   ' </li><li> Ursus arctos horribilis </li><i> Number of terms:</i> 3')
         self.assertEqual(termset._repr_html_(), output)
 
     def test_repr_long(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set.yaml')
-        output = ('Schema Path: tests/unit/example_test_term_set.yaml\nSources: NCBI_TAXON\nTerms: \n'
+        output = ('Schema Path: tests/unit/example_test_term_set.yaml\nSources: NCBITaxon\nTerms: \n'
                   '   - Homo sapiens\n   - Mus musculus\n   - Ursus arctos horribilis\n   ... ... \n'
                   '   - Ailuropoda melanoleuca\nNumber of terms: 5')
         self.assertEqual(repr(termset), output)
 
     def test_repr_html_long(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set.yaml')
         output = ('<b>Schema Path: </b>tests/unit/example_test_term_set.yaml<br><b>Sources:'
-                  ' </b>NCBI_TAXON<br><b> Terms: </b><li> Homo sapiens </li><li> Mus musculus'
+                  ' </b>NCBITaxon<br><b> Terms: </b><li> Homo sapiens </li><li> Mus musculus'
                   ' </li><li> Ursus arctos horribilis </li>... ...<li> Ailuropoda melanoleuca'
                   ' </li><i> Number of terms:</i> 5')
         self.assertEqual(termset._repr_html_(), output)
@@ -83,7 +83,7 @@ def test_termset_validate_false(self):
 
     def test_get_item(self):
         termset = TermSet(term_schema_path='tests/unit/example_test_term_set.yaml')
-        self.assertEqual(termset['Homo sapiens'].id, 'NCBI_TAXON:9606')
+        self.assertEqual(termset['Homo sapiens'].id, 'NCBITaxon:9606')
         self.assertEqual(termset['Homo sapiens'].description, 'the species is human')
         self.assertEqual(
             termset['Homo sapiens'].meaning,