Merge pull request #23 from opentargets/1808-tskir-minor-improvements

Minor improvements from issue 1808

VERSION

@@ -1 +1 @@
-v1.0.2
+v1.0.3

docs/development.rst

@@ -27,6 +27,16 @@ Install development packages
 
 
 
+Installing locally and running the tests
+----------------------------------------
+
+.. code-block:: bash
+
+    pip install -e .
+    pytest
+
+
+
 Adding a dependency
 -------------------
 Installation dependencies are stored in the ``setup.py`` file, in the ``install_requires`` section.

ontoma/cli.py

@@ -1,5 +1,6 @@
 import csv
 import logging
+from sys import stderr
 
 import click
 
@@ -9,6 +10,10 @@
 logger = logging.getLogger(__name__)
 
 
+def get_version():
+    return open('../VERSION').read().strip()
+
+
 @click.command()
 @click.option(
     '--infile',
@@ -50,8 +55,17 @@
     help=f'EFO release to use. This must be be either “latest”, or match the specific tag name in their GitHub '
          f'releases, for example v3.31.0. By default, {EFO_DEFAULT_VERSION!r} is used.'
 )
-def ontoma(infile, outfile, input_type, cache_dir, columns, efo_release):
+@click.option(
+    '--version',
+    help='Print version number and exit.',
+    is_flag=True
+)
+def ontoma(infile, outfile, input_type, cache_dir, columns, efo_release, version):
     """Maps ontology identifiers and strings to EFO, the ontology used by the Open Targets Platform."""
+    if version:
+        stderr.write(f'OnToma version {get_version()}.')
+        return
+
     if infile.name == '/dev/stdin':
         logger.warning('Reading input from STDIN. If this is not what you wanted, re-run with --help to see usage.')
 

ontoma/ontology.py

@@ -69,14 +69,15 @@ def convert_to_ot_schema(normalised_identifier: str) -> Optional[str]:
 
 
 URI_MAPPING = {
-    'NCIT':  'http://purl.obolibrary.org/obo/NCIT_{}',
-    'ORDO':  'http://www.orpha.net/ORDO/Orphanet_{}',
+    'CHEBI': 'http://purl.obolibrary.org/obo/CHEBI_{}',
+    'DOID':  'http://purl.obolibrary.org/obo/DOID_{}',
+    'EFO':   'http://www.ebi.ac.uk/efo/EFO_{}',
     'GO':    'http://purl.obolibrary.org/obo/GO_{}',
     'HP':    'http://purl.obolibrary.org/obo/HP_{}',
-    'EFO':   'http://www.ebi.ac.uk/efo/EFO_{}',
     'MONDO': 'http://purl.obolibrary.org/obo/MONDO_{}',
-    'DOID':  'http://purl.obolibrary.org/obo/DOID_{}',
     'MP':    'http://purl.obolibrary.org/obo/MP_{}',
+    'NCIT':  'http://purl.obolibrary.org/obo/NCIT_{}',
+    'ORDO':  'http://www.orpha.net/ORDO/Orphanet_{}',
 }
 
 

tests/test_cli.py

@@ -19,5 +19,5 @@ def test_file_batch_input(rootdir):
     ])
     assert result.exit_code == 0
     output = open('/tmp/ontoma-1.txt').read()
-    assert 'EFO_0000270' in output
+    assert 'MONDO_0004979' in output
     # assert 'MONDO_0002279' in output  # Related synonyms are not processed by this version.

tests/test_ontoma.py

@@ -4,21 +4,18 @@
 def test_find_term_asthma(ontclient):
     assert_result_ot_label(
         ontclient.find_term('asthma'),
-        ['EFO_0000270']
+        ['MONDO_0004979']
     )
 
 
 def test_is_included(ontclient):
-    assert ontclient.filter_identifiers_by_efo_current(['ORDO:354']) == ['ORDO:354']
-    # FIXME: This represents a term which is in EFO, but perhaps should not be considered by OnToma, because this is
-    # FIXME: a body part rather than a disease/drug response/etc.
-    assert ontclient.filter_identifiers_by_efo_current(['UBERON:0000310']) == ['UBERON:0000310']
+    assert ontclient.filter_identifiers_by_efo_current(['MONDO:0018149']) == ['MONDO:0018149']
 
 
 def test_suggest_hp_term_not_excluded(ontclient):
     assert_result_ot_label(
         ontclient.find_term('hypogammaglobulinemia'),
-        ['Orphanet_183669']
+        ['MONDO_0015977']
     )
 
 
@@ -29,7 +26,7 @@ def test_catch_ordo(ontclient):
     )
     assert_result_ot_label(
         ontclient.find_term('OMIM:208250', code=True),
-        {'EFO_0009028', 'MONDO_0008828'}
+        {'EFO_0009028'}
     )
 
 
@@ -42,5 +39,5 @@ def test_query_comma(ontclient):
 def test_find_term_alzheimer(ontclient):
     assert_result_ot_label(
         ontclient.find_term('alzheimer\'s disease'),
-        ['EFO_0000249']
+        ['MONDO_0004975']
     )

tests/test_phewascat.py

@@ -4,14 +4,14 @@
 def test_find_term_asthma(ontclient):
     assert_result_ot_label(
         ontclient.find_term('asthma'),
-        ['EFO_0000270']
+        ['MONDO_0004979']
     )
 
 
 def test_efo_direct_match(ontclient):
-    # The test deliberately expects no results, since a match from “Dementias” to “EFO_0004718” is a fuzzy one and
-    # cannot be assumed of high quality.
-    assert not ontclient.find_term('Dementias')
+    # The test deliberately expects no results, since a match from “Xeroderma Pigmentosa” to “MONDO_0019600” is a fuzzy
+    # one and cannot be assumed of high quality.
+    assert not ontclient.find_term('Xeroderma Pigmentosa')
 
 
 def test_otzooma_mappings_whitespace(ontclient):
@@ -24,7 +24,7 @@ def test_otzooma_mappings_whitespace(ontclient):
 def test_efo_match_with_apostrophe(ontclient):
     assert_result_ot_label(
         ontclient.find_term('Alzheimer\'s disease'),
-        ['EFO_0000249']
+        ['MONDO_0004975']
     )