diff --git a/CHANGELOG.md b/CHANGELOG.md index efee95f..4f60bc1 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,10 @@ # Changelog +## Unreleased + +### Manual curation +- argannot_curation: (Tet)tetH:EF460464:6286-7839:1554 was incorrectly annotated as ARO:3004797 which is a beta-lactamase due to a loose RGI hit. This was manually curated to ARO:3000175. + ## 0.4.0 - 10 June - Bundle a specific version of ARO with the package instead of downloading it from the internet (ensures reproducibility) diff --git a/argnorm/data/manual_curation/argannot_curation.tsv b/argnorm/data/manual_curation/argannot_curation.tsv index 2ccf34c..ad11ac5 100644 --- a/argnorm/data/manual_curation/argannot_curation.tsv +++ b/argnorm/data/manual_curation/argannot_curation.tsv @@ -1,2 +1,3 @@ Original ID ARO Gene Name in CARD Description (Phe)cpt_strepv:U09991:AAB36569:1412-1948:537 3000249 chloramphenicol phosphotransferase Parent ARO mapping +(Tet)tetH:EF460464:6286-7839:1554 3000175 tet(H) Loose RGI mapping. Mapped incorrectly to ARO:3004797. diff --git a/tests/test_database.py b/tests/test_database.py index a9c8a2e..e21fd31 100644 --- a/tests/test_database.py +++ b/tests/test_database.py @@ -2,10 +2,10 @@ from argnorm import lib from argnorm import drug_categorization +ARO = lib.get_aro_ontology() + @pytest.mark.parametrize('database', lib.DATABASES) def test_database(database): - ARO = lib.get_aro_ontology() - determinant_of_ab_resistance = ARO['ARO:3000000'] antibiotic_molecule = ARO['ARO:1000003'] assert determinant_of_ab_resistance.name == 'determinant of antibiotic resistance' @@ -23,3 +23,5 @@ def test_database(database): assert dc in ARO, f'ARO not found in the ontology: {dc}' assert antibiotic_molecule in ARO[dc].superclasses(1), f'ARO term not an immediate child of antibiotic molecule: {dc}' +def test_misannotated_genes(): + assert lib.map_to_aro('(Tet)tetH:EF460464:6286-7839:1554', 'argannot') == ARO['ARO:3000175'] \ No newline at end of file