diff --git a/ingest/validation/ontologies/cl.min.tsv.gz b/ingest/validation/ontologies/cl.min.tsv.gz index cd6e0cef..e95ae3d8 100644 Binary files a/ingest/validation/ontologies/cl.min.tsv.gz and b/ingest/validation/ontologies/cl.min.tsv.gz differ diff --git a/ingest/validation/ontologies/mondo.min.tsv.gz b/ingest/validation/ontologies/mondo.min.tsv.gz index 58540283..e245263d 100644 Binary files a/ingest/validation/ontologies/mondo.min.tsv.gz and b/ingest/validation/ontologies/mondo.min.tsv.gz differ diff --git a/ingest/validation/ontologies/version.txt b/ingest/validation/ontologies/version.txt index 477a6d06..88b13a2a 100644 --- a/ingest/validation/ontologies/version.txt +++ b/ingest/validation/ontologies/version.txt @@ -1,2 +1 @@ -1738072997 # validation cache key - +1741807191 # validation cache key diff --git a/tests/data/annotation/metadata/convention/valid_array_v2.1.2.txt b/tests/data/annotation/metadata/convention/valid_array_v2.1.2.txt index 1ec6fc24..f3bac639 100644 --- a/tests/data/annotation/metadata/convention/valid_array_v2.1.2.txt +++ b/tests/data/annotation/metadata/convention/valid_array_v2.1.2.txt @@ -1,7 +1,7 @@ NAME disease__time_since_onset disease__time_since_onset__unit organ_region organ_region__ontology_label donor disease__treated species species__ontology_label geographical_region geographical_region__ontology_label library_preparation_protocol library_preparation_protocol__ontology_label organ organ__ontology_label sex is_living organism_age__unit organism_age__unit_label ethnicity__ontology_label ethnicity organism_age disease disease__ontology_label cell_type cell_type__ontology_label donor_id biosample_id biosample_type preservation_method TYPE numeric group group group group group group group group group group group group group group group group group group group numeric group group group group group group group group -BM01_16dpp_AAGCAGTGGTAT 12|2 UO_0000035 MBA:000000944 Folium-tuber vermis (VII) BM01 False|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 31 MONDO_0005015|MONDO_0006849 diabetes mellitus|mastitis CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_TAAGCAGTGGTA 1 UO_0000035 MBA:000000302|MBA:000000294|MBA:000000795 Superior colliculus, sensory related|Superior colliculus, motor related|Periaqueductal gray BM01 FALSE NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 31 MONDO_0005709 common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CTAAGCAGTGGT 24|2 UO_0000035 MBA:000000714|MBA:000000972 BM01 True|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European|British HANCESTRO_0005|HANCESTRO_0462 31 MONDO_0005015|MONDO_0005709 diabetes mellitus|common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_AAGCAGTGGTAT 12|2 UO_0000035 MBA:000000944 Folium-tuber vermis (VII) BM01 False|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 31 MONDO_0005015|MONDO_0006849 diabetes mellitus|mastitis CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_TAAGCAGTGGTA 1 UO_0000035 MBA:000000302|MBA:000000294|MBA:000000795 Superior colliculus, sensory related|Superior colliculus, motor related|Periaqueductal gray BM01 FALSE NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 31 MONDO_0005709 common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CTAAGCAGTGGT 24|2 UO_0000035 MBA:000000714|MBA:000000972 BM01 True|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry|British HANCESTRO_0005|HANCESTRO_0462 31 MONDO_0005015|MONDO_0005709 diabetes mellitus|common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh BM01_16dpp_CGGTAAACCATT 36|3|1 UO_0000035 MBA:000001041 Paraflocculus BM01 True|False|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year HANCESTRO_0005|HANCESTRO_0462 31 MONDO_0005015|MONDO_0006849|MONDO_0005709 diabetes mellitus|mastitis|common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CCGAATTCACCG 0 UO_0000035 MBA:000000909|MBA:000000502 Entorhinal area|Subiculum BM01 FALSE NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 31 MONDO_0000001 disease CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CCGAATTCACCG 0 UO_0000035 MBA:000000909|MBA:000000502 Entorhinal area|Subiculum BM01 FALSE NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 31 MONDO_0000001 disease CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh diff --git a/tests/data/annotation/metadata/convention/valid_cell_type__custom_v2.2.1.txt b/tests/data/annotation/metadata/convention/valid_cell_type__custom_v2.2.1.txt index f13326a4..a8485313 100644 --- a/tests/data/annotation/metadata/convention/valid_cell_type__custom_v2.2.1.txt +++ b/tests/data/annotation/metadata/convention/valid_cell_type__custom_v2.2.1.txt @@ -1,6 +1,6 @@ NAME disease__time_since_onset disease__time_since_onset__unit organ_region organ_region__ontology_label donor disease__treated species species__ontology_label geographical_region geographical_region__ontology_label library_preparation_protocol library_preparation_protocol__ontology_label organ organ__ontology_label sex is_living organism_age__unit organism_age__unit_label ethnicity__ontology_label ethnicity organism_age disease disease__ontology_label cell_type cell_type__ontology_label donor_id biosample_id biosample_type preservation_method cell_type__custom TYPE numeric group group group group group group group group group group group group group group group group group group group numeric group group group group group group group group group -BM01_16dpp_AAGCAGTGGTAT 12|2 UO_0000035 MBA:000000944 Folium-tuber vermis (VII) BM01 False|False NCBITaxon_9606 human GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 31 MONDO_0005015|MONDO_0006849 diabetes|mastitis CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh epithelial +BM01_16dpp_AAGCAGTGGTAT 12|2 UO_0000035 MBA:000000944 Folium-tuber vermis (VII) BM01 False|False NCBITaxon_9606 human GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 31 MONDO_0005015|MONDO_0006849 diabetes|mastitis CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh epithelial BM01_16dpp_TAAGCAGTGGTA 1 UO_0000035 MBA:000000302|MBA:000000294|MBA:000000795 "Superior colliculus, sensory related|Superior colliculus, motor related|Periaqueductal gray" BM01 FALSE NCBITaxon_9606 Homo Sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year white HANCESTRO_0005 31 MONDO_0005709 common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh epithelial BM01_16dpp_CTAAGCAGTGGT 24|2 UO_0000035 MBA:000000714|MBA:000000972 BM01 True|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year British HANCESTRO_0462 31 MONDO_0005015|MONDO_0005709 diabetes mellitus|common cold CL_0000066 epithelial cell BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh epithelial BM01_16dpp_CGGTAAACCATT 36|3|1 UO_0000035 MBA:000001041 Paraflocculus BM01 True|False|False NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year HANCESTRO_0462 31 MONDO_0005015|MONDO_0006849|MONDO_0005709 diabetes|breast infection|common cold BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh sub-epithelial diff --git a/tests/data/annotation/metadata/convention/valid_no_array_synonyms_v2.0.0.txt b/tests/data/annotation/metadata/convention/valid_no_array_synonyms_v2.0.0.txt index 1fd6ffae..247c712f 100644 --- a/tests/data/annotation/metadata/convention/valid_no_array_synonyms_v2.0.0.txt +++ b/tests/data/annotation/metadata/convention/valid_no_array_synonyms_v2.0.0.txt @@ -1,7 +1,7 @@ NAME cell_type cell_type__ontology_label organism_age disease disease__ontology_label species species__ontology_label geographical_region geographical_region__ontology_label library_preparation_protocol library_preparation_protocol__ontology_label organ organ__ontology_label sex is_living organism_age__unit organism_age__unit_label ethnicity__ontology_label ethnicity race race__ontology_label donor_id biosample_id biosample_type preservation_method TYPE group group numeric group group group group group group group group group group group group group group group group group group group group group group -BM01_16dpp_AAGCAGTGGTAT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10x 3' v2 UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_TAAGCAGTGGTA CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10x 3' v2 UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CTAAGCAGTGGT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10X 3' v2 UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CGGTAAACCATT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10X 3' v2 sequencing UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CCGAATTCACCG CL_0000066 epithelial cell 31 PATO_0000001 quality NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_AAGCAGTGGTAT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10x 3' v2 UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_TAAGCAGTGGTA CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10x 3' v2 UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CTAAGCAGTGGT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10X 3' v2 UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CGGTAAACCATT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0009899 10X 3' v2 sequencing UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CCGAATTCACCG CL_0000066 epithelial cell 31 PATO_0000001 quality NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh diff --git a/tests/data/annotation/metadata/convention/valid_no_array_v2.0.0.txt b/tests/data/annotation/metadata/convention/valid_no_array_v2.0.0.txt index 011e33bb..ac3dff39 100644 --- a/tests/data/annotation/metadata/convention/valid_no_array_v2.0.0.txt +++ b/tests/data/annotation/metadata/convention/valid_no_array_v2.0.0.txt @@ -1,7 +1,7 @@ NAME cell_type cell_type__ontology_label organism_age disease disease__ontology_label species species__ontology_label geographical_region geographical_region__ontology_label library_preparation_protocol library_preparation_protocol__ontology_label organ organ__ontology_label sex is_living organism_age__unit organism_age__unit_label ethnicity__ontology_label ethnicity race race__ontology_label donor_id biosample_id biosample_type preservation_method TYPE group group numeric group group group group group group group group group group group group group group group group group group group group group group -BM01_16dpp_AAGCAGTGGTAT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_TAAGCAGTGGTA CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CTAAGCAGTGGT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CGGTAAACCATT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh -BM01_16dpp_CCGAATTCACCG CL_0000066 epithelial cell 31 PATO_0000001 quality NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_AAGCAGTGGTAT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_TAAGCAGTGGTA CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C43862 Norwegian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CTAAGCAGTGGT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CGGTAAACCATT CL_0000066 epithelial cell 31 MONDO_0000001 disease NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh +BM01_16dpp_CCGAATTCACCG CL_0000066 epithelial cell 31 PATO_0000001 quality NCBITaxon_9606 Homo sapiens GAZ_00003181 Boston EFO_0008919 Seq-Well UBERON_0001913 milk female yes UO_0000036 year European ancestry HANCESTRO_0005 NCIT_C126538 Scandinavian BM01 BM01_16dpp_r3 PrimaryBioSample_BodyFluid Fresh diff --git a/tests/data/bq_test.json b/tests/data/bq_test.json index 6660fa44..2c13cc7d 100644 --- a/tests/data/bq_test.json +++ b/tests/data/bq_test.json @@ -1,5 +1,5 @@ -{"CellID": "BM01_16dpp_AAGCAGTGGTAT", "disease__time_since_onset": [12.0, 2.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000944"], "organ_region__ontology_label": ["Folium-tuber vermis (VII)"], "disease__treated": [false, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0006849"], "disease__ontology_label": ["diabetes mellitus", "mastitis"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} -{"CellID": "BM01_16dpp_TAAGCAGTGGTA", "disease__time_since_onset": [1.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000302", "MBA_000000294", "MBA_000000795"], "organ_region__ontology_label": ["Superior colliculus, sensory related", "Superior colliculus, motor related", "Periaqueductal gray"], "disease__treated": [false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0005709"], "disease__ontology_label": ["common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} -{"CellID": "BM01_16dpp_CTAAGCAGTGGT", "disease__time_since_onset": [24.0, 2.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000714", "MBA_000000972"], "disease__treated": [true, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European", "British"], "ethnicity": ["HANCESTRO_0005", "HANCESTRO_0462"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0005709"], "disease__ontology_label": ["diabetes mellitus", "common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "organ_region__ontology_label": ["Orbital area", "Prelimbic area"], "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} -{"CellID": "BM01_16dpp_CGGTAAACCATT", "disease__time_since_onset": [36.0, 3.0, 1.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000001041"], "organ_region__ontology_label": ["Paraflocculus"], "disease__treated": [true, false, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity": ["HANCESTRO_0005", "HANCESTRO_0462"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0006849", "MONDO_0005709"], "disease__ontology_label": ["diabetes mellitus", "mastitis", "common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "ethnicity__ontology_label": ["European", "British"], "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} -{"CellID": "BM01_16dpp_CCGAATTCACCG", "disease__time_since_onset": [0.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000909", "MBA_000000502"], "organ_region__ontology_label": ["Entorhinal area", "Subiculum"], "disease__treated": [false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0000001"], "disease__ontology_label": ["disease"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} +{"CellID": "BM01_16dpp_AAGCAGTGGTAT", "disease__time_since_onset": [12.0, 2.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000944"], "organ_region__ontology_label": ["Folium-tuber vermis (VII)"], "disease__treated": [false, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European ancestry"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0006849"], "disease__ontology_label": ["diabetes mellitus", "mastitis"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} +{"CellID": "BM01_16dpp_TAAGCAGTGGTA", "disease__time_since_onset": [1.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000302", "MBA_000000294", "MBA_000000795"], "organ_region__ontology_label": ["Superior colliculus, sensory related", "Superior colliculus, motor related", "Periaqueductal gray"], "disease__treated": [false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European ancestry"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0005709"], "disease__ontology_label": ["common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} +{"CellID": "BM01_16dpp_CTAAGCAGTGGT", "disease__time_since_onset": [24.0, 2.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000714", "MBA_000000972"], "disease__treated": [true, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European ancestry", "British"], "ethnicity": ["HANCESTRO_0005", "HANCESTRO_0462"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0005709"], "disease__ontology_label": ["diabetes mellitus", "common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "organ_region__ontology_label": ["Orbital area", "Prelimbic area"], "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} +{"CellID": "BM01_16dpp_CGGTAAACCATT", "disease__time_since_onset": [36.0, 3.0, 1.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000001041"], "organ_region__ontology_label": ["Paraflocculus"], "disease__treated": [true, false, false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity": ["HANCESTRO_0005", "HANCESTRO_0462"], "organism_age": 31.0, "disease": ["MONDO_0005015", "MONDO_0006849", "MONDO_0005709"], "disease__ontology_label": ["diabetes mellitus", "mastitis", "common cold"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "ethnicity__ontology_label": ["European ancestry", "British"], "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} +{"CellID": "BM01_16dpp_CCGAATTCACCG", "disease__time_since_onset": [0.0], "disease__time_since_onset__unit": "UO_0000035", "organ_region": ["MBA_000000909", "MBA_000000502"], "organ_region__ontology_label": ["Entorhinal area", "Subiculum"], "disease__treated": [false], "species": "NCBITaxon_9606", "species__ontology_label": "Homo sapiens", "geographical_region": "GAZ_00003181", "geographical_region__ontology_label": "Boston", "library_preparation_protocol": "EFO_0008919", "library_preparation_protocol__ontology_label": "Seq-Well", "organ": "UBERON_0001913", "organ__ontology_label": "milk", "sex": "female", "is_living": "yes", "organism_age__unit": "UO_0000036", "organism_age__unit_label": "year", "ethnicity__ontology_label": ["European ancestry"], "ethnicity": ["HANCESTRO_0005"], "organism_age": 31.0, "disease": ["MONDO_0000001"], "disease__ontology_label": ["disease"], "cell_type": "CL_0000066", "cell_type__ontology_label": "epithelial cell", "donor_id": "BM01", "biosample_id": "BM01_16dpp_r3", "biosample_type": "PrimaryBioSample_BodyFluid", "preservation_method": "Fresh", "disease__time_since_onset__unit_label": "month", "study_accession": "SCPtest", "file_id": "addedfeed000000000000000", "metadata_convention_version": "2.3.0", "organism_age__seconds": 978285600.0} diff --git a/tests/mock_data/annotation/metadata/convention/valid_array_v2_1_2.py b/tests/mock_data/annotation/metadata/convention/valid_array_v2_1_2.py index 0bff30f7..1318a6b4 100644 --- a/tests/mock_data/annotation/metadata/convention/valid_array_v2_1_2.py +++ b/tests/mock_data/annotation/metadata/convention/valid_array_v2_1_2.py @@ -185,7 +185,7 @@ "ethnicity__ontology_label": { "name": "ethnicity__ontology_label", "annotation_type": "group", - "values": ["European", "European|British", ""], + "values": ["European ancestry", "European ancestry|British", ""], "study_file_id": ObjectId("600f42bdb067340e777b1385"), "study_id": ObjectId("5ea08bb17b2f150f29f4d952"), }, @@ -604,7 +604,13 @@ "cluster_name": "valid_array_v2.1.2.csv", "array_type": "annotations", "array_index": 0, - "values": ["European", "European", "European|British", "", "European"], + "values": [ + "European ancestry", + "European ancestry", + "European ancestry|British", + "", + "European ancestry", + ], "subsample_threshold": None, "subsample_annotation": None, "linear_data_type": "CellMetadatum", diff --git a/tests/test_validate_metadata.py b/tests/test_validate_metadata.py index fa1f66a6..869de7c1 100644 --- a/tests/test_validate_metadata.py +++ b/tests/test_validate_metadata.py @@ -291,7 +291,7 @@ def test_auto_filling_missing_labels(self): { "CellID": "test1", "ethnicity": ["HANCESTRO_0005"], - "ethnicity__ontology_label": ["European"], + "ethnicity__ontology_label": ["European ancestry"], }, updated_row, "Row should be updated to inject missing ontology label as array", @@ -299,7 +299,7 @@ def test_auto_filling_missing_labels(self): self.assertEqual( metadata.issues["warn"]["ontology"], { - 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European" per EBI OLS lookup': [ + 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European ancestry" per EBI OLS lookup': [ "test1" ] }, @@ -316,7 +316,7 @@ def test_auto_filling_missing_labels(self): { "CellID": "test1", "ethnicity": ["HANCESTRO_0005"], - "ethnicity__ontology_label": ["European"], + "ethnicity__ontology_label": ["European ancestry"], }, updated_row, "Row should be updated to inject missing ontology label as array", @@ -324,7 +324,7 @@ def test_auto_filling_missing_labels(self): self.assertEqual( metadata.issues["warn"]["ontology"], { - 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European" per EBI OLS lookup': [ + 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European ancestry" per EBI OLS lookup': [ "test1" ] }, @@ -345,7 +345,7 @@ def test_auto_filling_missing_labels(self): { "CellID": "test1", "ethnicity": ["HANCESTRO_0005"], - "ethnicity__ontology_label": ["European"], + "ethnicity__ontology_label": ["European ancestry"], }, updated_row, "Row should be updated to inject missing ontology label as array", @@ -353,7 +353,7 @@ def test_auto_filling_missing_labels(self): self.assertEqual( metadata.issues["warn"]["ontology"], { - 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European" per EBI OLS lookup': [ + 'ethnicity: missing ontology label "HANCESTRO_0005" - using "European ancestry" per EBI OLS lookup': [ "test1" ] }, @@ -567,7 +567,8 @@ def test_valid_multiple_ontologies_content(self): ) validate_input_metadata(metadata, convention) self.assertFalse( - report_issues(metadata), "Valid multiple ontologies content should not elicit error" + report_issues(metadata), + "Valid multiple ontologies content should not elicit error", ) self.teardown_metadata(metadata) @@ -661,7 +662,8 @@ def set_up_test(test_file_name, bq=None): metadata.validate_format(), "Valid metadata headers should not elicit error" ) self.assertFalse( - report_issues(metadata), "Valid array-based ontology content should not elicit error" + report_issues(metadata), + "Valid array-based ontology content should not elicit error", ) self.teardown_metadata(metadata) @@ -671,7 +673,8 @@ def set_up_test(test_file_name, bq=None): metadata.validate_format(), "Valid metadata headers should not elicit error" ) self.assertFalse( - report_issues(metadata), "Valid cell type custom content should not elicit error" + report_issues(metadata), + "Valid cell type custom content should not elicit error", ) self.teardown_metadata(metadata) @@ -878,7 +881,6 @@ def test_request_backoff_handling(self, mocked_requests_get): ) self.assertEqual(mocked_requests_get.call_count, MAX_HTTP_ATTEMPTS) - def test_is_label_or_synonym(self): label = "10x 3' v2" possible_matches = { @@ -904,7 +906,8 @@ def test_will_allow_synonym_matches(self): ) validate_input_metadata(metadata, convention) self.assertFalse( - report_issues(metadata), "Valid ontology synonym content should not elicit error" + report_issues(metadata), + "Valid ontology synonym content should not elicit error", ) self.teardown_metadata(metadata) @@ -915,7 +918,7 @@ def test_array_synonym_replacement(self): metadata_name = "ethnicity__ontology_label" matches_before_replace = [v == ["white"] for v in df[metadata_name]] - replace_single_value_array(df, metadata_name, "white", "European") + replace_single_value_array(df, metadata_name, "white", "European ancestry") matches_after_replace = [v == ["white"] for v in df[metadata_name]] self.assertTrue(