From 02ef075cde1f3c11a5cde19776d8554b51f7f5bc Mon Sep 17 00:00:00 2001 From: Kori Kuzma Date: Thu, 26 Dec 2024 11:05:26 -0500 Subject: [PATCH] test: update test data (#385) close #384 --- ..._GRCh38_110.gff => ensembl_GRCh38_113.gff} | 20 +- ...{hgnc_20210810.json => hgnc_20241206.json} | 1458 ++++++++--------- tests/unit/data/etl_data/ncbi_GRCh38.p14.gff | 38 +- ...20210813.tsv => ncbi_history_20241224.tsv} | 0 .../unit/data/etl_data/ncbi_info_20210813.tsv | 26 - .../unit/data/etl_data/ncbi_info_20241224.tsv | 25 + tests/unit/test_ensembl_source.py | 14 +- tests/unit/test_hgnc_source.py | 18 - tests/unit/test_ncbi_source.py | 43 +- tests/unit/test_query.py | 49 +- 10 files changed, 767 insertions(+), 924 deletions(-) rename tests/unit/data/etl_data/{ensembl_GRCh38_110.gff => ensembl_GRCh38_113.gff} (93%) rename tests/unit/data/etl_data/{hgnc_20210810.json => hgnc_20241206.json} (80%) rename tests/unit/data/etl_data/{ncbi_history_20210813.tsv => ncbi_history_20241224.tsv} (100%) delete mode 100644 tests/unit/data/etl_data/ncbi_info_20210813.tsv create mode 100644 tests/unit/data/etl_data/ncbi_info_20241224.tsv diff --git a/tests/unit/data/etl_data/ensembl_GRCh38_110.gff b/tests/unit/data/etl_data/ensembl_GRCh38_113.gff similarity index 93% rename from tests/unit/data/etl_data/ensembl_GRCh38_110.gff rename to tests/unit/data/etl_data/ensembl_GRCh38_113.gff index 78687c6e..dd5234e5 100644 --- a/tests/unit/data/etl_data/ensembl_GRCh38_110.gff +++ b/tests/unit/data/etl_data/ensembl_GRCh38_113.gff @@ -192,15 +192,15 @@ ##sequence-region KI270757.1 1 71251 ##sequence-region MT 1 16569 ##sequence-region X 1 156040895 -##sequence-region Y 2752083 56887902 -#!genome-build Genome Reference Consortium GRCh38.p13 +##sequence-region Y 1 57227415 +#!genome-build Genome Reference Consortium GRCh38.p14 #!genome-version GRCh38 #!genome-date 2013-12 -#!genome-build-accession GCA_000001405.28 -#!genebuild-last-updated 2022-04 +#!genome-build-accession GCA_000001405.29 +#!genebuild-last-updated 2024-07 1 GRCh38 chromosome 1 248956422 . . . ID=chromosome:1;Alias=CM000663.2,chr1,NC_000001.11 ### -1 havana pseudogene 11869 14409 . + . ID=gene:ENSG00000223972;Name=DDX11L1;biotype=transcribed_unprocessed_pseudogene;description=DEAD/H-box helicase 11 like 1 (pseudogene) [Source:HGNC Symbol%3BAcc:HGNC:37102];gene_id=ENSG00000223972;logic_name=havana_homo_sapiens;version=5 +1 havana pseudogene 12010 13670 . + . ID=gene:ENSG00000223972;Name=DDX11L1;biotype=transcribed_unprocessed_pseudogene;description=DEAD/H-box helicase 11 like 1 (pseudogene) [Source:HGNC Symbol%3BAcc:HGNC:37102];gene_id=ENSG00000223972;logic_name=havana_homo_sapiens;version=6 ### 1 ensembl_havana gene 220148293 220272529 . - . ID=gene:ENSG00000118873;Name=RAB3GAP2;biotype=protein_coding;description=RAB3 GTPase activating non-catalytic protein subunit 2 [Source:HGNC Symbol%3BAcc:HGNC:17168];gene_id=ENSG00000118873;logic_name=ensembl_havana_gene_homo_sapiens;version=17 ### @@ -214,24 +214,24 @@ ### 7 GRCh38 chromosome 1 159345973 . . . ID=chromosome:7;Alias=CM000669.2,chr7,NC_000007.14 ### -7 ensembl_havana gene 100889994 100896974 . - . ID=gene:ENSG00000087085;Name=ACHE;biotype=protein_coding;description=acetylcholinesterase (Cartwright blood group) [Source:HGNC Symbol%3BAcc:HGNC:108];gene_id=ENSG00000087085;logic_name=ensembl_havana_gene_homo_sapiens;version=16 +7 ensembl_havana gene 100889994 100896974 . - . ID=gene:ENSG00000087085;Name=ACHE;biotype=protein_coding;description=acetylcholinesterase (Yt blood group) [Source:HGNC Symbol%3BAcc:HGNC:108];gene_id=ENSG00000087085;logic_name=ensembl_havana_gene_homo_sapiens;version=16 ### 7 ensembl_havana gene 140719327 140924929 . - . ID=gene:ENSG00000157764;Name=BRAF;biotype=protein_coding;description=B-Raf proto-oncogene%2C serine/threonine kinase [Source:HGNC Symbol%3BAcc:HGNC:1097];gene_id=ENSG00000157764;logic_name=ensembl_havana_gene_homo_sapiens;version=14 ### 9 GRCh38 chromosome 1 138394717 . . . ID=chromosome:9;Alias=CM000671.2,chr9,NC_000009.12 ### -9 ensembl_havana gene 130713016 130887675 . + . ID=gene:ENSG00000097007;Name=ABL1;biotype=protein_coding;description=ABL proto-oncogene 1%2C non-receptor tyrosine kinase [Source:HGNC Symbol%3BAcc:HGNC:76];gene_id=ENSG00000097007;logic_name=ensembl_havana_gene_homo_sapiens;version=19 +9 ensembl_havana gene 130713043 130887675 . + . ID=gene:ENSG00000097007;Name=ABL1;biotype=protein_coding;description=ABL proto-oncogene 1%2C non-receptor tyrosine kinase [Source:HGNC Symbol%3BAcc:HGNC:76];gene_id=ENSG00000097007;logic_name=ensembl_havana_gene_homo_sapiens;version=20 ### 11 GRCh38 chromosome 1 135086622 . . . ID=chromosome:11;Alias=CM000673.2,chr11,NC_000011.10 ### -11 ensembl_havana gene 10751246 10801625 . + . ID=gene:ENSG00000198730;Name=CTR9;biotype=protein_coding;description=CTR9 homolog%2C Paf1/RNA polymerase II complex component [Source:HGNC Symbol%3BAcc:HGNC:16850];gene_id=ENSG00000198730;logic_name=ensembl_havana_gene_homo_sapiens;version=9 +11 ensembl_havana gene 10751018 10801625 . + . ID=gene:ENSG00000198730;Name=CTR9;biotype=protein_coding;description=CTR9 homolog%2C Paf1/RNA polymerase II complex component [Source:HGNC Symbol%3BAcc:HGNC:16850];gene_id=ENSG00000198730;logic_name=ensembl_havana_gene_homo_sapiens;version=10 ### 15 GRCh38 chromosome 1 101991189 . . . ID=chromosome:15;Alias=CM000677.2,chr15,NC_000015.10 15 ensembl_havana gene 89784895 89815401 . - . ID=gene:ENSG00000166825;Name=ANPEP;biotype=protein_coding;description=alanyl aminopeptidase%2C membrane [Source:HGNC Symbol%3BAcc:HGNC:500];gene_id=ENSG00000166825;logic_name=ensembl_havana_gene_homo_sapiens;version=15 ### 17 GRCh38 chromosome 1 83257441 . . . ID=chromosome:17;Alias=CM000679.2,chr17,NC_000017.11 ### -17 ensembl_havana gene 7661779 7687538 . - . ID=gene:ENSG00000141510;Name=TP53;biotype=protein_coding;description=tumor protein p53 [Source:HGNC Symbol%3BAcc:HGNC:11998];gene_id=ENSG00000141510;logic_name=ensembl_havana_gene_homo_sapiens;version=18 +17 ensembl_havana gene 7661779 7687546 . - . ID=gene:ENSG00000141510;Name=TP53;biotype=protein_coding;description=tumor protein p53 [Source:HGNC Symbol%3BAcc:HGNC:11998];gene_id=ENSG00000141510;logic_name=ensembl_havana_gene_homo_sapiens;version=19 ### 17 havana ncRNA_gene 2748078 2748182 . + . ID=gene:ENSG00000272920;Name=hsa-mir-1253;biotype=lncRNA;description=hsa-mir-1253 [Source:miRBase%3BAcc:MI0006387];gene_id=ENSG00000272920;logic_name=havana_homo_sapiens;version=1 ### @@ -241,7 +241,7 @@ ### X GRCh38 chromosome 1 156040895 . . . ID=chromosome:X;Alias=CM000685.2,chrX,NC_000023.11 ### -X havana ncRNA_gene 154424378 154428526 . - . ID=gene:ENSG00000197180;Name=ATP6AP1-DT;biotype=lncRNA;description=ATP6AP1 divergent transcript [Source:HGNC Symbol%3BAcc:HGNC:25138];gene_id=ENSG00000197180;logic_name=havana_homo_sapiens;version=4 +X havana ncRNA_gene 154424377 154428549 . - . ID=gene:ENSG00000197180;Name=ATP6AP1-DT;biotype=lncRNA;description=ATP6AP1 divergent transcript [Source:HGNC Symbol%3BAcc:HGNC:25138];gene_id=ENSG00000197180;logic_name=havana_homo_sapiens;version=5 ### X ensembl_havana gene 155612572 155782459 . + . ID=gene:ENSG00000168939;Name=SPRY3;biotype=protein_coding;description=sprouty RTK signaling antagonist 3 [Source:HGNC Symbol%3BAcc:HGNC:11271];gene_id=ENSG00000168939;logic_name=ensembl_havana_gene_homo_sapiens;version=13 ### diff --git a/tests/unit/data/etl_data/hgnc_20210810.json b/tests/unit/data/etl_data/hgnc_20241206.json similarity index 80% rename from tests/unit/data/etl_data/hgnc_20210810.json rename to tests/unit/data/etl_data/hgnc_20241206.json index 172ae169..1e2fd726 100644 --- a/tests/unit/data/etl_data/hgnc_20210810.json +++ b/tests/unit/data/etl_data/hgnc_20241206.json @@ -1,183 +1,182 @@ { "responseHeader": { "status": 0, - "QTime": 21 + "QTime": 25 }, "response": { - "numFound": 42759, + "numFound": 43839, "docs": [ { - "symbol_report_tag": [ - "Stable symbol" - ], - "vega_id": "OTTHUMG00000157033", - "locus_group": "protein-coding gene", "mane_select": [ "ENST00000241069.11", "NM_000665.5" ], - "_version_": 1707696195519905792, - "uuid": "ac1d39ff-c8fd-4ad1-b713-4731cad0ee18", + "entrez_id": "43", + "rgd_id": [ + "RGD:69313" + ], + "pubmed_id": [ + 1380483 + ], + "refseq_accession": [ + "NM_015831" + ], + "date_modified": "2023-11-07", + "agr": "HGNC:108", "prev_name": [ "acetylcholinesterase (YT blood group)", - "acetylcholinesterase (Yt blood group)" + "acetylcholinesterase (Yt blood group)", + "acetylcholinesterase (Cartwright blood group)" ], + "merops": "S09.979", + "locus_group": "protein-coding gene", + "vega_id": "OTTHUMG00000157033", + "ucsc_id": "uc003uxi.4", + "locus_type": "gene with protein product", "lsdb": [ "Blood Group Antigen Mutation Database|http://www.ncbi.nlm.nih.gov/gv/mhc/xslcgi.cgi?cmd=bgmut/home", "LRG_804|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_804.xml" ], - "refseq_accession": [ - "NM_015831" + "prev_symbol": [ + "YT" + ], + "gene_group": [ + "Blood group antigens" ], - "hgnc_id": "HGNC:108", - "entrez_id": "43", "symbol": "ACHE", - "location": "7q22.1", - "name": "acetylcholinesterase (Cartwright blood group)", + "location_sortable": "07q22.1", + "status": "Approved", "mgd_id": [ "MGI:87876" ], - "prev_symbol": [ - "YT" - ], - "alias_name": [ - "Yt blood group" + "uniprot_ids": [ + "P22303" ], + "name": "acetylcholinesterase (Yt blood group)", + "hgnc_id": "HGNC:108", "date_approved_reserved": "1989-06-02", - "status": "Approved", - "merops": "S09.979", - "locus_type": "gene with protein product", - "iuphar": "objectId:2465", - "agr": "HGNC:108", - "rgd_id": [ - "RGD:69313" - ], "ensembl_gene_id": "ENSG00000087085", - "gene_group": [ - "Blood group antigens" - ], - "date_name_changed": "2016-03-30", - "omim_id": [ - "100740" + "gene_group_id": [ + 454 ], - "date_modified": "2021-05-26", - "ucsc_id": "uc003uxi.4", "enzyme_id": [ "3.1.1.7" ], - "uniprot_ids": [ - "P22303" - ], - "ccds_id": [ - "CCDS64736", - "CCDS5709", - "CCDS5710" - ], - "pubmed_id": [ - 1380483 + "alias_name": [ + "Yt blood group" ], - "gene_group_id": [ - 454 + "omim_id": [ + "100740" ], - "location_sortable": "07q22.1" + "location": "7q22.1", + "uuid": "a7c80b74-a344-4a4d-aca5-5c757957b043", + "date_name_changed": "2023-11-07", + "iuphar": "objectId:2465" }, { - "symbol_report_tag": [ - "Stable symbol" - ], - "vega_id": "OTTHUMG00000157457", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000644969.2", - "NM_001374258.1" + "date_approved_reserved": "1991-07-16", + "hgnc_id": "HGNC:1097", + "ensembl_gene_id": "ENSG00000157764", + "ena": [ + "M95712" ], + "status": "Approved", "alias_symbol": [ "BRAF1", "BRAF-1" ], - "_version_": 1707696197057118209, - "uuid": "fbac0c54-1e0e-47af-a39a-82949139939c", - "prev_name": [ - "v-raf murine sarcoma viral oncogene homolog B" - ], - "lsdb": [ - "LRG_299|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_299.xml" - ], - "refseq_accession": [ - "NM_004333" - ], - "cosmic": "BRAF", - "hgnc_id": "HGNC:1097", - "entrez_id": "673", - "symbol": "BRAF", - "location": "7q34", - "name": "B-Raf proto-oncogene, serine/threonine kinase", "mgd_id": [ "MGI:88190" ], - "orphanet": 119066, - "date_approved_reserved": "1991-07-16", - "status": "Approved", - "locus_type": "gene with protein product", - "iuphar": "objectId:1943", - "agr": "HGNC:1097", - "rgd_id": [ - "RGD:619908" + "gencc": "HGNC:1097", + "uniprot_ids": [ + "P15056" ], - "ensembl_gene_id": "ENSG00000157764", + "name": "B-Raf proto-oncogene, serine/threonine kinase", + "symbol": "BRAF", + "location_sortable": "07q34", "gene_group": [ "Mitogen-activated protein kinase kinase kinases", "RAF family" ], + "uuid": "bc1beb27-6bd8-4a37-982b-e637cb941f7b", + "iuphar": "objectId:1943", "date_name_changed": "2014-06-26", "omim_id": [ "164757" ], - "date_modified": "2021-05-26", - "ucsc_id": "uc003vwc.5", - "uniprot_ids": [ - "P15056" - ], - "ena": [ - "M95712" + "location": "7q34", + "gene_group_id": [ + 654, + 1157 ], - "ccds_id": [ - "CCDS94218", - "CCDS94219", - "CCDS87555", - "CCDS5863" + "agr": "HGNC:1097", + "date_modified": "2023-01-20", + "refseq_accession": [ + "NM_004333" ], "pubmed_id": [ 2284096, 1565476 ], - "gene_group_id": [ - 654, - 1157 + "rgd_id": [ + "RGD:619908" + ], + "entrez_id": "673", + "mane_select": [ + "ENST00000646891.2", + "NM_004333.6" ], - "location_sortable": "07q34" + "ucsc_id": "uc003vwc.5", + "locus_type": "gene with protein product", + "lsdb": [ + "LRG_299|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_299.xml" + ], + "orphanet": 119066, + "vega_id": "OTTHUMG00000157457", + "prev_name": [ + "v-raf murine sarcoma viral oncogene homolog B" + ], + "cosmic": "BRAF", + "locus_group": "protein-coding gene" }, { - "symbol_report_tag": [ - "Stable symbol" + "uuid": "94b45872-4e2b-44dd-9a62-f22b9c1da4cb", + "date_name_changed": "2008-01-16", + "omim_id": [ + "191170" ], - "date_approved_reserved": "1986-01-01", "alias_name": [ "Li-Fraumeni syndrome" ], - "vega_id": "OTTHUMG00000162125", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000269305.9", - "NM_000546.6" + "location": "17p13.1", + "symbol": "TP53", + "location_sortable": "17p13.1", + "date_approved_reserved": "1986-01-01", + "hgnc_id": "HGNC:11998", + "ensembl_gene_id": "ENSG00000141510", + "mgd_id": [ + "MGI:98834" + ], + "ena": [ + "AF307851" ], - "status": "Approved", "alias_symbol": [ "p53", "LFS1" ], - "_version_": 1707696218478477314, - "uuid": "d674d23a-6ac1-4482-a2da-81a8837c07f3", + "status": "Approved", + "name": "tumor protein p53", + "uniprot_ids": [ + "P04637" + ], + "gencc": "HGNC:11998", + "orphanet": 120204, + "vega_id": "OTTHUMG00000162125", + "cosmic": "TP53", + "locus_group": "protein-coding gene", + "ucsc_id": "uc060aur.1", + "locus_type": "gene with protein product", "lsdb": [ "IARC TP53 Mutation Database|http://www-p53.iarc.fr/", "p53 UMD TP53 mutation database|http://p53.fr/", @@ -188,211 +187,212 @@ "refseq_accession": [ "NM_000546" ], - "locus_type": "gene with protein product", - "agr": "HGNC:11998", - "cosmic": "TP53", - "hgnc_id": "HGNC:11998", "rgd_id": [ "RGD:3889" ], - "ensembl_gene_id": "ENSG00000141510", - "entrez_id": "7157", - "omim_id": [ - "191170" - ], - "symbol": "TP53", - "date_name_changed": "2008-01-16", - "location": "17p13.1", - "name": "tumor protein p53", - "date_modified": "2021-05-26", - "mgd_id": [ - "MGI:98834" - ], - "ucsc_id": "uc060aur.1", - "uniprot_ids": [ - "P04637" - ], - "orphanet": 120204, - "ccds_id": [ - "CCDS73964", - "CCDS11118", - "CCDS45605", - "CCDS45606", - "CCDS73967", - "CCDS73963", - "CCDS73968", - "CCDS73971", - "CCDS73970", - "CCDS73966", - "CCDS73965", - "CCDS73969" - ], - "ena": [ - "AF307851" - ], "pubmed_id": [ 6396087, 3456488, 2047879 ], - "location_sortable": "17p13.1" + "mane_select": [ + "ENST00000269305.9", + "NM_000546.6" + ], + "entrez_id": "7157", + "agr": "HGNC:11998", + "date_modified": "2023-01-20" }, { - "date_approved_reserved": "2001-06-22", + "entrez_id": "1055", "symbol": "CECR", - "locus_group": "other", - "location": "22pter-q11", + "location_sortable": "22pter-q11", "status": "Approved", - "date_modified": "2012-10-02", "name": "cat eye syndrome chromosome region", - "_version_": 1707696198085771265, - "uuid": "6c4dc1c7-6e7a-4775-a185-1d86d544e732", - "locus_type": "region", + "date_modified": "2012-10-02", "hgnc_id": "HGNC:1838", - "entrez_id": "1055", - "location_sortable": "22pter-q11" + "date_approved_reserved": "2001-06-22", + "locus_group": "other", + "location": "22pter-q11", + "locus_type": "region", + "uuid": "0407d1d2-7cca-4c5b-9b51-b9e1ba648cf8" }, { + "vega_id": "OTTHUMG00000181922", + "locus_group": "protein-coding gene", + "prev_name": [ + "chromatin assembly factor 1, subunit A (p150)" + ], + "locus_type": "gene with protein product", + "ucsc_id": "uc002mal.4", + "refseq_accession": [ + "NM_005483" + ], "mane_select": [ "ENST00000301280.10", "NM_005483.3" - ], - "locus_group": "protein-coding gene", - "alias_name": [ - "chromatin assembly factor I (150 kDa)" - ], - "status": "Approved", - "vega_id": "OTTHUMG00000181922", - "hgnc_id": "HGNC:1910", - "location_sortable": "19p13.3", - "uuid": "cacf6159-9c08-4ca4-a648-cb1895edee54", - "date_name_changed": "2015-11-23", - "entrez_id": "10036", - "pubmed_id": [ + ], + "entrez_id": "10036", + "pubmed_id": [ 7600578 - ], - "ccds_id": [ + ], + "rgd_id": [ + "RGD:1590865" + ], + "agr": "HGNC:1910", + "ccds_id": [ "CCDS32875" - ], - "ucsc_id": "uc002mal.4", - "name": "chromatin assembly factor 1 subunit A", - "ena": [ + ], + "date_modified": "2023-01-20", + "date_name_changed": "2015-11-23", + "uuid": "e68c0506-4f35-4fc1-b772-ccbf2651f643", + "location": "19p13.3", + "alias_name": [ + "chromatin assembly factor I (150 kDa)" + ], + "omim_id": [ + "601246" + ], + "location_sortable": "19p13.3", + "symbol": "CHAF1A", + "ensembl_gene_id": "ENSG00000167670", + "hgnc_id": "HGNC:1910", + "date_approved_reserved": "1999-09-29", + "name": "chromatin assembly factor 1 subunit A", + "uniprot_ids": [ + "Q13111" + ], + "ena": [ "U20979" - ], - "mgd_id": [ - "MGI:1351331" - ], - "date_modified": "2019-08-21", - "rgd_id": [ - "RGD:1590865" - ], - "alias_symbol": [ + ], + "alias_symbol": [ "CAF1P150", "CAF1B", "CAF-1", "CAF1", "P150", "MGC71229" - ], - "symbol": "CHAF1A", - "date_approved_reserved": "1999-09-29", - "prev_name": [ - "chromatin assembly factor 1, subunit A (p150)" - ], - "omim_id": [ - "601246" - ], - "refseq_accession": [ - "NM_005483" - ], - "location": "19p13.3", - "locus_type": "gene with protein product", - "_version_": 1741469986589769728, - "agr": "HGNC:1910", - "ensembl_gene_id": "ENSG00000167670", - "uniprot_ids": [ - "Q13111" - ] + ], + "mgd_id": [ + "MGI:1351331" + ], + "status": "Approved" }, { - "date_approved_reserved": "2003-11-13", - "alias_name": [ - "CTF4, chromosome transmission fidelity factor 4 homolog (S. cerevisiae)" + "location_sortable": "14q22.2-q22.3", + "symbol": "WDHD1", + "gene_group": [ + "WD repeat domain containing" ], - "vega_id": "OTTHUMG00000140304", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000360586.8", - "NM_007086.4" + "ensembl_gene_id": "ENSG00000198554", + "hgnc_id": "HGNC:23170", + "date_approved_reserved": "2003-11-13", + "uniprot_ids": [ + "O75717" ], + "name": "WD repeat and HMG-box DNA binding protein 1", "status": "Approved", + "mgd_id": [ + "MGI:2443514" + ], + "ena": [ + "AJ006266" + ], "alias_symbol": [ "AND-1", "CTF4", "CHTF4" ], - "_version_": 1707696220276785153, - "uuid": "85c49e45-d6a8-483b-9531-927ec4786436", - "refseq_accession": [ - "NM_007086" - ], - "locus_type": "gene with protein product", - "agr": "HGNC:23170", - "hgnc_id": "HGNC:23170", - "rgd_id": [ - "RGD:1310200" + "gene_group_id": [ + 362 ], - "ensembl_gene_id": "ENSG00000198554", - "entrez_id": "11169", - "gene_group": [ - "WD repeat domain containing" + "uuid": "e0793c5b-5339-43cb-a5c1-b037321220e5", + "location": "14q22.2-q22.3", + "alias_name": [ + "CTF4, chromosome transmission fidelity factor 4 homolog (S. cerevisiae)" ], "omim_id": [ "608126" ], - "symbol": "WDHD1", - "location": "14q22.2-q22.3", - "name": "WD repeat and HMG-box DNA binding protein 1", - "date_modified": "2018-02-13", - "mgd_id": [ - "MGI:2443514" - ], - "ucsc_id": "uc001xbm.3", - "uniprot_ids": [ - "O75717" - ], - "ccds_id": [ - "CCDS41955", - "CCDS9721" + "refseq_accession": [ + "NM_007086" ], - "ena": [ - "AJ006266" + "entrez_id": "11169", + "mane_select": [ + "ENST00000360586.8", + "NM_007086.4" ], - "gene_group_id": [ - 362 + "rgd_id": [ + "RGD:1310200" ], "pubmed_id": [ 9175701, 20028748 ], - "location_sortable": "14q22.2-q22.3" + "ccds_id": [ + "CCDS9721", + "CCDS41955" + ], + "agr": "HGNC:23170", + "date_modified": "2023-01-20", + "vega_id": "OTTHUMG00000140304", + "locus_group": "protein-coding gene", + "locus_type": "gene with protein product", + "ucsc_id": "uc001xbm.3" }, { - "vega_id": "OTTHUMG00000012533", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000381529.9", - "NM_172245.4" + "gene_group_id": [ + 471, + 715 + ], + "uuid": "59c56e1b-8b36-4667-855c-130c853075bf", + "cd": "CD116", + "iuphar": "objectId:1707", + "date_name_changed": "2019-11-26", + "omim_id": [ + "306250", + "425000" + ], + "alias_name": [ + "alpha-GM-CSF receptor" + ], + "location": "Xp22.32 and Yp11.3", + "symbol": "CSF2RA", + "location_sortable": "Xp22.32 and Yp11.3", + "gene_group": [ + "CD molecules", + "Pseudoautosomal region 1" + ], + "prev_symbol": [ + "CSF2R" + ], + "date_approved_reserved": "1990-07-03", + "hgnc_id": "HGNC:2435", + "ensembl_gene_id": "ENSG00000198223", + "ena": [ + "M64445" ], "alias_symbol": [ "CD116", "alphaGMR" ], - "_version_": 1707696198915194881, - "uuid": "3095e0d7-4533-41e7-a543-8ef63f9d2037", + "status": "Approved", + "mgd_id": [ + "MGI:1339754" + ], + "uniprot_ids": [ + "P15509" + ], + "name": "colony stimulating factor 2 receptor subunit alpha", + "gencc": "HGNC:2435", + "orphanet": 209477, + "vega_id": "OTTHUMG00000012533", "prev_name": [ "colony stimulating factor 2 receptor, alpha, low-affinity (granulocyte-macrophage)" ], + "locus_group": "protein-coding gene", + "ucsc_id": "uc010nvv.3", + "locus_type": "gene with protein product", "lsdb": [ "Global Variome shared LOVD|https://databases.lovd.nl/shared/genes/CSF2RA", "LRG_186|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_186.xml" @@ -400,140 +400,95 @@ "refseq_accession": [ "NM_001161529" ], - "hgnc_id": "HGNC:2435", - "entrez_id": "1438", - "symbol": "CSF2RA", - "location": "Xp22.32 and Yp11.3", - "name": "colony stimulating factor 2 receptor subunit alpha", - "mgd_id": [ - "MGI:1339754" - ], - "prev_symbol": [ - "CSF2R" - ], - "orphanet": 209477, - "alias_name": [ - "alpha-GM-CSF receptor" + "pubmed_id": [ + 1702217 ], - "date_approved_reserved": "1990-07-03", - "status": "Approved", - "locus_type": "gene with protein product", - "iuphar": "objectId:1707", - "agr": "HGNC:2435", "rgd_id": [ "RGD:1594330" ], - "ensembl_gene_id": "ENSG00000198223", - "gene_group": [ - "CD molecules", - "Pseudoautosomal region 1" + "entrez_id": "1438", + "mane_select": [ + "ENST00000381529.9", + "NM_172245.4" ], - "date_name_changed": "2019-11-26", - "cd": "CD116", + "agr": "HGNC:2435", + "date_modified": "2023-03-15" + }, + { "omim_id": [ - "306250", - "425000" - ], - "date_modified": "2021-04-13", - "ucsc_id": "uc010nvv.3", - "uniprot_ids": [ - "P15509" - ], - "ena": [ - "M64445" - ], - "ccds_id": [ - "CCDS35193", - "CCDS35190", - "CCDS35191", - "CCDS55359", - "CCDS35192", - "CCDS55360" + "619850" ], - "pubmed_id": [ - 1702217 + "alias_name": [ + "iGb3 synthase", + "isoglobotriaosylceramide synthase" ], + "location": "1p35.1", + "uuid": "69ebf111-6778-412d-a55a-4a28928017d1", + "date_name_changed": "2013-03-11", "gene_group_id": [ - 471, - 715 + 429 ], - "location_sortable": "Xp22.32 and Yp11.3" - }, - { - "prev_symbol": [ - "A3GALT2P" + "alias_symbol": [ + "IGBS3S", + "IGB3S" ], - "date_symbol_changed": "2013-03-11", - "entrez_id": "127550", - "date_modified": "2018-02-08", "mgd_id": [ "MGI:2685279" ], - "location_sortable": "01p35.1", "status": "Approved", - "vega_id": "OTTHUMG00000004125", - "date_name_changed": "2013-03-11", - "uuid": "68885c2c-4b8a-4001-a77e-41db23685bfe", - "alias_name": [ - "iGb3 synthase", - "isoglobotriaosylceramide synthase" + "uniprot_ids": [ + "U3KPV4" ], - "locus_group": "protein-coding gene", + "name": "alpha 1,3-galactosyltransferase 2", + "date_approved_reserved": "2005-05-06", + "hgnc_id": "HGNC:30005", "ensembl_gene_id": "ENSG00000184389", - "_version_": 1741469984037535744, + "date_symbol_changed": "2013-03-11", + "gene_group": [ + "Glycosyltransferase family 6" + ], + "prev_symbol": [ + "A3GALT2P" + ], + "symbol": "A3GALT2", + "location_sortable": "01p35.1", "locus_type": "gene with protein product", - "rgd_id": [ - "RGD:727913" + "ucsc_id": "uc031plq.1", + "prev_name": [ + "alpha 1,3-galactosyltransferase 2, pseudogene" ], - "date_approved_reserved": "2005-05-06", + "locus_group": "protein-coding gene", + "vega_id": "OTTHUMG00000004125", + "date_modified": "2023-01-20", + "agr": "HGNC:30005", "ccds_id": [ "CCDS60080" ], - "ucsc_id": "uc031plq.1", + "rgd_id": [ + "RGD:727913" + ], "pubmed_id": [ 10854427, 18630988 ], - "name": "alpha 1,3-galactosyltransferase 2", - "hgnc_id": "HGNC:30005", - "gene_group": [ - "Glycosyltransferase family 6" - ], + "entrez_id": "127550", "mane_select": [ "ENST00000442999.3", "NM_001080438.1" ], - "gene_group_id": [ - 429 - ], - "uniprot_ids": [ - "U3KPV4" - ], - "agr": "HGNC:30005", - "location": "1p35.1", "refseq_accession": [ "NM_001080438" - ], - "omim_id": [ - "619850" - ], - "symbol": "A3GALT2", - "alias_symbol": [ - "IGBS3S", - "IGB3S" - ], - "prev_name": [ - "alpha 1,3-galactosyltransferase 2, pseudogene" ] }, { + "ensembl_gene_id": "ENSG00000274847", "date_approved_reserved": "2009-02-18", - "alias_name": [ - "tektin 4 pseudogene 4" + "hgnc_id": "HGNC:31102", + "name": "MAFF interacting protein", + "date_modified": "2023-04-20", + "uniprot_ids": [ + "Q8WZ33" ], - "vega_id": "OTTHUMG00000188065", - "locus_group": "pseudogene", - "status": "Approved", "alias_symbol": [ "FLJ35473", "FLJ00219", @@ -542,324 +497,333 @@ "pp5644", "TEKT4P4" ], - "_version_": 1707696205983645696, - "uuid": "3347c721-7e09-4350-a8e7-ed466ac4b616", - "prev_name": [ - "MAFF interacting protein" + "ena": [ + "AK074146", + "AF289559" ], + "status": "Approved", "refseq_accession": [ "NR_046439" ], - "locus_type": "unknown", - "hgnc_id": "HGNC:31102", - "ensembl_gene_id": "ENSG00000274847", - "entrez_id": "727764", + "location_sortable": "14 unplaced", "symbol": "MAFIP", - "date_name_changed": "2012-03-26", - "location": "14 unplaced", - "name": "MAFF interacting protein", - "date_modified": "2017-09-21", - "uniprot_ids": [ - "Q8WZ33" - ], - "ena": [ - "AK074146", - "AF289559" - ], "pubmed_id": [ 16549056, 15881666 ], - "location_sortable": "14 unplaced" + "entrez_id": "727764", + "date_name_changed": "2023-04-20", + "uuid": "0c426816-de7e-4740-83d2-679b98b88809", + "locus_type": "unknown", + "location": "14 unplaced", + "alias_name": [ + "tektin 4 pseudogene 4" + ], + "vega_id": "OTTHUMG00000188065", + "locus_group": "other", + "prev_name": [ + "MAFF interacting protein", + "MAFF interacting protein (pseudogene)" + ] }, { + "hgnc_id": "HGNC:34692", + "agr": "HGNC:34692", "date_approved_reserved": "2008-08-29", - "locus_group": "non-coding RNA", + "name": "tRNA-Leu (anticodon CAG) 2-1", + "date_modified": "2023-07-27", "status": "Approved", "alias_symbol": [ "tRNA-Leu-CAG-2-1" ], - "_version_": 1707696219107622913, - "uuid": "6d4dfe64-1599-4570-8287-da84de9c772d", - "rna_central_id": [ - "URS00000FB60D" - ], - "prev_name": [ - "transfer RNA leucine 13 (anticodon CAG)", - "transfer RNA-Leu (CAG) 2-1" + "ena": [ + "HG983896" ], - "locus_type": "RNA, transfer", - "agr": "HGNC:34692", - "hgnc_id": "HGNC:34692", "gtrnadb": "tRNA-Leu-CAG-2-1", + "location_sortable": "16q13-q21", + "symbol": "TRL-CAG2-1", "entrez_id": "100189130", + "prev_symbol": [ + "TRNAL13" + ], "gene_group": [ "Cytoplasmic transfer RNAs" ], - "symbol": "TRL-CAG2-1", + "date_symbol_changed": "2014-06-19", "date_name_changed": "2019-04-04", - "location": "16q13-21", - "name": "tRNA-Leu (anticodon CAG) 2-1", - "date_modified": "2019-04-04", - "prev_symbol": [ - "TRNAL13" + "locus_type": "RNA, transfer", + "uuid": "f7778985-f79e-4949-9d82-2f7ce07dbe1f", + "location": "16q13-q21", + "rna_central_id": [ + "URS00000FB60D" ], - "ena": [ - "HG983896" + "locus_group": "non-coding RNA", + "prev_name": [ + "transfer RNA leucine 13 (anticodon CAG)", + "transfer RNA-Leu (CAG) 2-1" ], "gene_group_id": [ 842 - ], - "date_symbol_changed": "2014-06-19", - "location_sortable": "16q13-21" + ] }, { - "date_approved_reserved": "2009-03-06", + "pubmed_id": [ + 19123937 + ], + "entrez_id": "100271094", "symbol": "RPS24P5", - "locus_group": "pseudogene", - "location": "1p36.13-q41", - "status": "Approved", - "date_modified": "2009-03-11", - "name": "ribosomal protein S24 pseudogene 5", - "_version_": 1707696215183851521, - "uuid": "547b3b9d-dcae-45d3-b6dd-d344bc433681", "refseq_accession": [ "NG_011274" ], - "locus_type": "pseudogene", + "location_sortable": "01p36.13-q41", + "status": "Approved", + "name": "ribosomal protein S24 pseudogene 5", + "date_modified": "2009-03-11", + "date_approved_reserved": "2009-03-06", "agr": "HGNC:36026", "hgnc_id": "HGNC:36026", - "pubmed_id": [ - 19123937 - ], - "entrez_id": "100271094", - "location_sortable": "01p36.13-q41" + "locus_group": "pseudogene", + "location": "1p36.13-q41", + "uuid": "49c50ee0-0472-4601-bd98-7e9e5f7313e8", + "locus_type": "pseudogene" }, { - "date_approved_reserved": "2009-07-20", - "vega_id": "OTTHUMG00000183508", - "locus_group": "non-coding RNA", - "status": "Approved", - "alias_symbol": [ - "FLJ23569" - ], - "_version_": 1707696195375202304, - "uuid": "7241a986-d17e-4b06-9851-2f8e7dec7d01", - "rna_central_id": [ - "URS00007E4F6E" - ], + "locus_type": "RNA, long non-coding", + "ucsc_id": "uc002qse.3", "prev_name": [ "non-protein coding RNA 181", "A1BG antisense RNA (non-protein coding)", "A1BG antisense RNA 1 (non-protein coding)" ], - "refseq_accession": [ - "NR_015380" - ], - "locus_type": "RNA, long non-coding", + "locus_group": "non-coding RNA", + "vega_id": "OTTHUMG00000183508", + "date_modified": "2013-06-27", "agr": "HGNC:37133", - "hgnc_id": "HGNC:37133", - "ensembl_gene_id": "ENSG00000268895", "entrez_id": "503538", - "gene_group": [ - "Antisense RNAs" + "refseq_accession": [ + "NR_015380" ], - "symbol": "A1BG-AS1", - "date_name_changed": "2012-08-15", "location": "19q13.43", - "lncipedia": "A1BG-AS1", + "uuid": "091b4740-5768-49cd-945a-721e309cb517", + "date_name_changed": "2012-08-15", + "gene_group_id": [ + 1987 + ], + "rna_central_id": [ + "URS00007E4F6E" + ], + "ena": [ + "BC040926" + ], + "status": "Approved", + "alias_symbol": [ + "FLJ23569" + ], "name": "A1BG antisense RNA 1", - "date_modified": "2013-06-27", - "ucsc_id": "uc002qse.3", + "hgnc_id": "HGNC:37133", + "date_approved_reserved": "2009-07-20", + "ensembl_gene_id": "ENSG00000268895", + "date_symbol_changed": "2010-11-25", "prev_symbol": [ "NCRNA00181", "A1BGAS", "A1BG-AS" ], - "ena": [ - "BC040926" - ], - "gene_group_id": [ - 1987 + "gene_group": [ + "Antisense RNAs" ], - "date_symbol_changed": "2010-11-25", + "lncipedia": "A1BG-AS1", + "symbol": "A1BG-AS1", "location_sortable": "19q13.43" }, { - "gene_group": [ - "Piwi-interacting RNA clusters" - ], - "date_approved_reserved": "2009-11-05", - "symbol": "PIRC24", "locus_group": "non-coding RNA", - "location": "6", - "status": "Approved", - "date_modified": "2014-11-18", - "name": "piwi-interacting RNA cluster 24", - "_version_": 1707696210573262850, - "uuid": "fb149011-fbe7-454e-852b-9b694324ea30", - "locus_type": "RNA, cluster", - "hgnc_id": "HGNC:37528", "gene_group_id": [ 851 ], + "location": "6", + "uuid": "6404e01d-1943-4de0-a49d-9375f5ffb061", + "locus_type": "RNA, cluster", + "gene_group": [ + "Piwi-interacting RNA clusters" + ], "pubmed_id": [ 17881367 ], "entrez_id": "100313810", - "location_sortable": "06" + "location_sortable": "06", + "symbol": "PIRC24", + "name": "piwi-interacting RNA cluster 24", + "date_modified": "2014-11-18", + "status": "Approved", + "date_approved_reserved": "2009-11-05", + "hgnc_id": "HGNC:37528" }, { "date_approved_reserved": "1998-07-15", - "locus_group": "other", - "status": "Approved", - "alias_symbol": [ - "GSD1aSP" - ], - "_version_": 1707696201536634880, - "uuid": "87b7050e-610d-4e4b-9359-e40f0d316d85", + "hgnc_id": "HGNC:4059", "curator_notes": [ "This gene has the locus type unknown because it has never been mapped to the human genome." ], - "prev_name": [ - "glucose-6-phosphatase, regulatory" + "status": "Approved", + "alias_symbol": [ + "GSD1aSP" ], - "locus_type": "unknown", - "hgnc_id": "HGNC:4059", - "entrez_id": "2541", - "symbol": "G6PR", - "date_name_changed": "2004-05-20", - "location": "reserved", "name": "glucose-6-phosphatase regulator", "date_modified": "2016-04-20", + "symbol": "G6PR", + "location_sortable": "reserved", "pubmed_id": [ 2172641, 7814621, 2996501 ], - "location_sortable": "reserved" + "entrez_id": "2541", + "uuid": "4f4a5d9b-5f51-4552-9c78-8b2424521a77", + "locus_type": "unknown", + "date_name_changed": "2004-05-20", + "location": "reserved", + "prev_name": [ + "glucose-6-phosphatase, regulatory" + ], + "locus_group": "other" }, { - "date_approved_reserved": "1995-05-10", + "locus_group": "protein-coding gene", + "gene_group_id": [ + 1845 + ], + "uuid": "0a959b59-7ebe-49dc-b1b6-a9d4130381d7", + "locus_type": "gene with protein product", + "location": "Xp11.4-p11.2 not on reference assembly", + "omim_id": [ + "300597" + ], "alias_name": [ "cancer/testis antigen family 4, member 4" ], - "locus_group": "protein-coding gene", - "status": "Approved", - "alias_symbol": [ - "CT4.4" - ], - "_version_": 1707696201573335041, - "uuid": "81d15344-3ea2-4f99-8232-aca8f42c9830", + "location_sortable": "Xp11.4-p11.2 not on reference assembly", "refseq_accession": [ "NM_001474" ], - "locus_type": "gene with protein product", - "hgnc_id": "HGNC:4101", - "entrez_id": "2576", + "symbol": "GAGE4", "gene_group": [ "GAGE family" ], - "omim_id": [ - "300597" + "pubmed_id": [ + 7544395 ], - "symbol": "GAGE4", - "location": "Xp11.4-p11.2 not on reference assembly", + "entrez_id": "2576", + "date_approved_reserved": "1995-05-10", + "hgnc_id": "HGNC:4101", "name": "G antigen 4", - "date_modified": "2019-06-20", "uniprot_ids": [ "P0DSO3" ], + "date_modified": "2023-03-15", "ena": [ "U19145" ], - "gene_group_id": [ - 1845 - ], - "pubmed_id": [ - 7544395 - ], - "location_sortable": "Xp11.4-p11.2 not on reference assembly" + "status": "Approved", + "alias_symbol": [ + "CT4.4" + ] }, { - "date_approved_reserved": "1994-08-10", "locus_group": "protein-coding gene", - "status": "Approved", - "_version_": 1707696202216112128, - "uuid": "1faed30e-867c-483f-830a-0d9e8c40ba74", - "refseq_accession": [ - "NM_000853" - ], + "orphanet": 470418, "locus_type": "gene with protein product", - "hgnc_id": "HGNC:4641", + "ucsc_id": "uc002zze.4", + "mane_select": [ + "ENST00000612885.4", + "NM_000853.4" + ], + "entrez_id": "2952", "rgd_id": [ "RGD:2765" ], - "ensembl_gene_id": "ENSG00000277656", - "entrez_id": "2952", - "gene_group": [ - "Soluble glutathione S-transferases" + "pubmed_id": [ + 8617495 + ], + "refseq_accession": [ + "NM_000853" + ], + "date_modified": "2023-03-15", + "gene_group_id": [ + 567 + ], + "enzyme_id": [ + "2.5.1.18" ], "omim_id": [ "600436" ], - "symbol": "GSTT1", "location": "22q11.23 alternate reference locus", - "name": "glutathione S-transferase theta 1", - "date_modified": "2015-07-31", + "uuid": "f7b9c5e4-fb32-4a3b-8d04-36c7281e9af7", + "gene_group": [ + "Soluble glutathione S-transferases" + ], + "symbol": "GSTT1", + "location_sortable": "22q11.23 alternate reference locus", "mgd_id": [ "MGI:107379" ], - "ucsc_id": "uc002zze.4", - "enzyme_id": [ - "2.5.1.18" + "status": "Approved", + "ena": [ + "KI270879" ], + "name": "glutathione S-transferase theta 1", "uniprot_ids": [ "P30711" ], - "orphanet": 470418, - "ena": [ - "KI270879" - ], - "gene_group_id": [ - 567 - ], - "pubmed_id": [ - 8617495 - ], - "location_sortable": "22q11.23 alternate reference locus" + "hgnc_id": "HGNC:4641", + "date_approved_reserved": "1994-08-10", + "ensembl_gene_id": "ENSG00000277656" }, { "vega_id": "OTTHUMG00000149814", "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000300060.7", - "NM_001150.3" - ], - "alias_symbol": [ - "LAP1", - "gp150", - "p150" - ], - "_version_": 1707696196168974337, - "uuid": "496dd55c-564d-4ec3-996c-4e08b2385543", + "merops": "M01.001", "prev_name": [ "alanyl (membrane) aminopeptidase" ], + "ucsc_id": "uc002bop.5", + "locus_type": "gene with protein product", "refseq_accession": [ "NM_001150" ], - "hgnc_id": "HGNC:500", + "pubmed_id": [ + 2428842, + 1977688 + ], + "rgd_id": [ + "RGD:2991" + ], + "mane_select": [ + "ENST00000300060.7", + "NM_001150.3" + ], "entrez_id": "290", - "symbol": "ANPEP", - "location": "15q26.1", - "name": "alanyl aminopeptidase, membrane", - "mgd_id": [ - "MGI:5000466" + "agr": "HGNC:500", + "ccds_id": [ + "CCDS10356" ], - "prev_symbol": [ - "CD13", - "PEPN" + "date_modified": "2023-01-20", + "enzyme_id": [ + "3.4.11.2" + ], + "gene_group_id": [ + 104, + 471, + 1437 + ], + "iuphar": "objectId:1560", + "date_name_changed": "2016-01-06", + "cd": "CD13", + "uuid": "ecc965ed-9a40-40e1-befb-dce16e4f2cf6", + "location": "15q26.1", + "omim_id": [ + "151530" ], "alias_name": [ "aminopeptidase N", @@ -867,338 +831,312 @@ "microsomal aminopeptidase", "membrane alanyl aminopeptidase" ], - "date_approved_reserved": "1989-02-28", - "status": "Approved", - "merops": "M01.001", - "locus_type": "gene with protein product", - "iuphar": "objectId:1560", - "agr": "HGNC:500", - "rgd_id": [ - "RGD:2991" - ], - "ensembl_gene_id": "ENSG00000166825", + "location_sortable": "15q26.1", + "symbol": "ANPEP", "gene_group": [ "Aminopeptidases", "CD molecules", "M1 metallopeptidases" ], - "date_name_changed": "2016-01-06", - "cd": "CD13", - "omim_id": [ - "151530" - ], - "date_modified": "2020-09-17", - "ucsc_id": "uc002bop.5", - "enzyme_id": [ - "3.4.11.2" + "prev_symbol": [ + "CD13", + "PEPN" ], + "ensembl_gene_id": "ENSG00000166825", + "date_approved_reserved": "1989-02-28", + "hgnc_id": "HGNC:500", + "name": "alanyl aminopeptidase, membrane", "uniprot_ids": [ "P15144" ], - "ena": [ - "M22324" - ], - "ccds_id": [ - "CCDS10356" + "alias_symbol": [ + "LAP1", + "gp150", + "p150", + "AP-N", + "hAPN" ], - "pubmed_id": [ - 2428842, - 1977688 + "mgd_id": [ + "MGI:5000466" ], - "gene_group_id": [ - 104, - 471, - 1437 + "ena": [ + "M22324" ], - "location_sortable": "15q26.1" + "status": "Approved" }, { - "date_approved_reserved": "1989-10-11", - "locus_group": "other", - "status": "Approved", - "_version_": 1707696207810265089, - "uuid": "9faf5b05-e788-4d19-b2a6-c467ec68d246", - "prev_name": [ - "7S DNA" + "prev_symbol": [ + "MT7SDNA" ], - "locus_type": "region", - "hgnc_id": "HGNC:7409", "gene_group": [ "Mitochondrially encoded regions" ], - "symbol": "MT-7SDNA", - "date_name_changed": "2005-02-15", - "location": "mitochondria", - "name": "mitochondrially encoded 7S DNA", - "date_modified": "2019-10-09", - "prev_symbol": [ - "MT7SDNA" - ], "pubmed_id": [ 24709344, 273237 ], "date_symbol_changed": "2019-10-09", + "location_sortable": "mitochondria", + "symbol": "MT-7SDNA", + "name": "mitochondrially encoded 7S DNA", + "date_modified": "2019-10-09", + "status": "Approved", + "hgnc_id": "HGNC:7409", + "date_approved_reserved": "1989-10-11", + "locus_group": "other", + "prev_name": [ + "7S DNA" + ], "gene_group_id": [ 1973 ], - "location_sortable": "mitochondria" + "location": "mitochondria", + "date_name_changed": "2005-02-15", + "locus_type": "region", + "uuid": "2274dbbf-0f83-4e9e-a618-254277ce6a5b" }, { - "symbol_report_tag": [ - "Stable symbol" + "gene_group": [ + "SH2 domain containing", + "Abl family tyrosine kinases" ], - "vega_id": "OTTHUMG00000020813", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000318560.6", - "NM_005157.6" + "prev_symbol": [ + "ABL" + ], + "symbol": "ABL1", + "location_sortable": "09q34.12", + "ena": [ + "M14752" + ], + "mgd_id": [ + "MGI:87859" ], + "status": "Approved", "alias_symbol": [ "JTK7", "c-ABL", "p150" ], - "_version_": 1707696195483205632, - "uuid": "f3c383ea-b6bd-4a03-bff0-aa3be952a670", - "prev_name": [ - "v-abl Abelson murine leukemia viral oncogene homolog 1", - "c-abl oncogene 1, receptor tyrosine kinase", - "c-abl oncogene 1, non-receptor tyrosine kinase" - ], - "lsdb": [ - "LRG_769|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_769.xml" - ], - "refseq_accession": [ - "NM_007313" - ], - "cosmic": "ABL1", - "hgnc_id": "HGNC:76", - "entrez_id": "25", - "symbol": "ABL1", - "location": "9q34.12", "name": "ABL proto-oncogene 1, non-receptor tyrosine kinase", - "mgd_id": [ - "MGI:87859" - ], - "prev_symbol": [ - "ABL" + "gencc": "HGNC:76", + "uniprot_ids": [ + "P00519" ], - "orphanet": 117691, "date_approved_reserved": "1986-01-01", - "status": "Approved", - "locus_type": "gene with protein product", - "iuphar": "objectId:1923", - "agr": "HGNC:76", - "rgd_id": [ - "RGD:1584969" - ], + "hgnc_id": "HGNC:76", "ensembl_gene_id": "ENSG00000097007", - "gene_group": [ - "SH2 domain containing", - "Abl family tyrosine kinases" + "gene_group_id": [ + 741, + 1463 ], - "date_name_changed": "2014-06-26", "omim_id": [ "189980" ], - "date_modified": "2021-05-26", - "ucsc_id": "uc004bzv.4", - "uniprot_ids": [ - "P00519" - ], - "ena": [ - "M14752" - ], - "ccds_id": [ - "CCDS35165", - "CCDS35166" + "location": "9q34.12", + "uuid": "92f4a55c-69a2-4be1-acbb-ec6a06629fd3", + "iuphar": "objectId:1923", + "date_name_changed": "2014-06-26", + "rgd_id": [ + "RGD:1584969" ], "pubmed_id": [ 1857987, 12626632 ], - "gene_group_id": [ - 741, - 1463 + "mane_select": [ + "ENST00000318560.6", + "NM_005157.6" + ], + "entrez_id": "25", + "refseq_accession": [ + "NM_007313" ], - "location_sortable": "09q34.12" + "date_modified": "2023-01-20", + "agr": "HGNC:76", + "prev_name": [ + "v-abl Abelson murine leukemia viral oncogene homolog 1", + "c-abl oncogene 1, receptor tyrosine kinase", + "c-abl oncogene 1, non-receptor tyrosine kinase" + ], + "cosmic": "ABL1", + "locus_group": "protein-coding gene", + "orphanet": 117691, + "vega_id": "OTTHUMG00000020813", + "locus_type": "gene with protein product", + "ucsc_id": "uc004bzv.4", + "lsdb": [ + "LRG_769|http://ftp.ebi.ac.uk/pub/databases/lrgex/LRG_769.xml" + ] }, { - "symbol_report_tag": [ - "Stable symbol" - ], - "date_approved_reserved": "1996-04-04", - "vega_id": "OTTHUMG00000179843", "locus_group": "protein-coding gene", + "vega_id": "OTTHUMG00000179843", + "orphanet": 171089, + "locus_type": "gene with protein product", + "ucsc_id": "uc002leb.3", "mane_select": [ "ENST00000285039.12", "NM_001080467.3" ], - "status": "Approved", - "alias_symbol": [ - "KIAA1119" + "entrez_id": "4645", + "pubmed_id": [ + 8884266, + 17462998 + ], + "rgd_id": [ + "RGD:621347" ], - "_version_": 1707696208307290113, - "uuid": "e6878d55-46d4-406a-ab31-e1e51f3041f1", "refseq_accession": [ "NM_001080467" ], - "locus_type": "gene with protein product", + "date_modified": "2023-07-27", + "ccds_id": [ + "CCDS42436" + ], "agr": "HGNC:7603", - "hgnc_id": "HGNC:7603", - "rgd_id": [ - "RGD:621347" + "gene_group_id": [ + 1100, + 1691 ], - "ensembl_gene_id": "ENSG00000167306", - "entrez_id": "4645", + "omim_id": [ + "606540" + ], + "location": "18q21.1", + "uuid": "d211db1a-54e4-4318-9e52-64cdd2ada9cf", "gene_group": [ "Myosin heavy chains, class V", "MicroRNA protein coding host genes" ], - "omim_id": [ - "606540" - ], "symbol": "MYO5B", - "location": "18q", - "name": "myosin VB", - "date_modified": "2021-05-26", + "location_sortable": "18q21.1", + "ena": [ + "AB032945" + ], "mgd_id": [ "MGI:106598" ], - "ucsc_id": "uc002leb.3", + "status": "Approved", + "alias_symbol": [ + "KIAA1119" + ], "uniprot_ids": [ "Q9ULV0" ], - "orphanet": 171089, - "ccds_id": [ - "CCDS42436" - ], - "ena": [ - "AB032945" - ], - "gene_group_id": [ - 1100, - 1691 - ], - "pubmed_id": [ - 8884266, - 17462998 - ], - "location_sortable": "18q" + "name": "myosin VB", + "gencc": "HGNC:7603", + "hgnc_id": "HGNC:7603", + "date_approved_reserved": "1996-04-04", + "ensembl_gene_id": "ENSG00000167306" }, { - "date_approved_reserved": "2000-04-11", - "vega_id": "OTTHUMG00000159645", - "locus_group": "protein-coding gene", - "mane_select": [ - "ENST00000356763.8", - "NM_014602.3" - ], - "status": "Approved", - "alias_symbol": [ - "VPS15", - "p150" - ], - "_version_": 1707696210538659841, - "uuid": "870b459d-1527-4192-a8a3-f09cb4de0f65", - "prev_name": [ - "phosphoinositide-3-kinase, regulatory subunit 4" + "gene_group_id": [ + 362, + 1492, + 1596 ], - "refseq_accession": [ - "NM_014602" + "omim_id": [ + "602610" ], - "locus_type": "gene with protein product", + "location": "3q22.1", + "uuid": "673aeb03-12c7-4e1c-980d-cf318021b10c", "iuphar": "objectId:2157", - "agr": "HGNC:8982", - "hgnc_id": "HGNC:8982", - "rgd_id": [ - "RGD:1311809" - ], - "ensembl_gene_id": "ENSG00000196455", - "entrez_id": "30849", + "date_name_changed": "2015-11-17", "gene_group": [ "WD repeat domain containing", "Armadillo like helical domain containing", "PIK3C3 complex subunits" ], - "omim_id": [ - "602610" - ], "symbol": "PIK3R4", - "date_name_changed": "2015-11-17", - "location": "3q22.1", - "name": "phosphoinositide-3-kinase regulatory subunit 4", - "date_modified": "2015-11-17", + "location_sortable": "03q22.1", "mgd_id": [ "MGI:1922919" ], - "ucsc_id": "uc003enj.4", - "uniprot_ids": [ - "Q99570" - ], - "ccds_id": [ - "CCDS3067" + "alias_symbol": [ + "VPS15", + "p150" ], "ena": [ "Y08991" ], - "gene_group_id": [ - 362, - 1492, - 1596 + "status": "Approved", + "uniprot_ids": [ + "Q99570" + ], + "name": "phosphoinositide-3-kinase regulatory subunit 4", + "date_approved_reserved": "2000-04-11", + "hgnc_id": "HGNC:8982", + "ensembl_gene_id": "ENSG00000196455", + "prev_name": [ + "phosphoinositide-3-kinase, regulatory subunit 4" ], + "locus_group": "protein-coding gene", + "vega_id": "OTTHUMG00000159645", + "locus_type": "gene with protein product", + "ucsc_id": "uc003enj.4", "pubmed_id": [ 8999962 ], - "location_sortable": "03q22.1" + "rgd_id": [ + "RGD:1311809" + ], + "entrez_id": "30849", + "mane_select": [ + "ENST00000356763.8", + "NM_014602.3" + ], + "refseq_accession": [ + "NM_014602" + ], + "date_modified": "2023-01-20", + "agr": "HGNC:8982", + "ccds_id": [ + "CCDS3067" + ] }, { - "date_approved_reserved": "1986-01-01", - "symbol": "FRA10A", "locus_group": "other", "location": "10q23.3 or 10q24.2", - "status": "Approved", - "date_modified": "2020-04-20", - "name": "fragile site, folic acid type, rare, fra(10)(q23.3) or fra(10)(q24.2)", - "_version_": 1707696201387737088, - "uuid": "334225e1-0a3b-4407-afbc-47f2fd98bfc9", - "refseq_accession": [ - "NG_052564" - ], "locus_type": "fragile site", - "hgnc_id": "HGNC:3829", + "uuid": "8524a4e7-e07d-4f18-8766-7abe482cf47e", + "entrez_id": "109280162", "pubmed_id": [ 15203205 ], - "entrez_id": "109280162", - "location_sortable": "10q23.3 or 10q24.2" + "refseq_accession": [ + "NG_052564" + ], + "location_sortable": "10q23.3 or 10q24.2", + "symbol": "FRA10A", + "name": "fragile site, folic acid type, rare, fra(10)(q23.3) or fra(10)(q24.2)", + "date_modified": "2020-04-20", + "status": "Approved", + "hgnc_id": "HGNC:3829", + "date_approved_reserved": "1986-01-01" }, { - "date_approved_reserved": "1986-01-01", - "symbol": "IFNR", "locus_type": "unknown", + "uuid": "e9ce6ff6-f4e0-47a4-b59b-4a15fe514913", "location": "16", "omim_id": [ - "147573" + "147573" ], - "_version_": 1741469995314970627, + "locus_group": "other", "curator_notes": [ - "This gene has the locus type unknown because it has never been mapped to the human genome." + "This gene has the locus type unknown because it has never been mapped to the human genome." ], - "locus_group": "other", - "uuid": "6af5e088-63ac-4f7e-b1ce-3edb4fd551aa", - "location_sortable": "16", "hgnc_id": "HGNC:5447", - "status": "Approved", + "date_approved_reserved": "1986-01-01", "date_modified": "2019-06-26", "name": "interferon production regulator", + "status": "Approved", + "location_sortable": "16", + "symbol": "IFNR", + "entrez_id": "3466", "pubmed_id": [ - 1906174, - 1193239 - ], - "entrez_id": "3466" - } + 1906174, + 1193239 + ] + } ], "start": 0 } diff --git a/tests/unit/data/etl_data/ncbi_GRCh38.p14.gff b/tests/unit/data/etl_data/ncbi_GRCh38.p14.gff index 46599b07..a8f3ce0b 100644 --- a/tests/unit/data/etl_data/ncbi_GRCh38.p14.gff +++ b/tests/unit/data/etl_data/ncbi_GRCh38.p14.gff @@ -1,14 +1,14 @@ ##gff-version 3 #!gff-spec-version 1.21 #!processor NCBI annotwriter -#!genome-build GRCh38.p13 -#!genome-build-accession NCBI_Assembly:GCF_000001405.39 -#!annotation-date 05/14/2021 -#!annotation-source NCBI Homo sapiens Updated Annotation Release 109.20210514 +#!genome-build GRCh38.p14 +#!genome-build-accession NCBI_Assembly:GCF_000001405.40 +#!annotation-date 10/02/2023 +#!annotation-source NCBI RefSeq GCF_000001405.40-RS_2023_10 ##sequence-region NC_000001.11 1 248956422 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000001.11 RefSeq region 1 248956422 . + . ID=NC_000001.11:1..248956422;Dbxref=taxon:9606;Name=1;chromosome=1;gbkey=Src;genome=chromosome;mol_type=genomic DNA -NC_000001.11 BestRefSeq gene 220148293 220272453 . - . ID=gene-RAB3GAP2;Dbxref=GeneID:25782,HGNC:HGNC:17168,MIM:609275;Name=RAB3GAP2;description=RAB3 GTPase activating non-catalytic protein subunit 2;gbkey=Gene;gene=RAB3GAP2;gene_biotype=protein_coding;gene_synonym=p150,RAB3-GAP150,RAB3GAP150,SPG69,WARBM2 +NC_000001.11 BestRefSeq gene 220148293 220272453 . - . ID=gene-RAB3GAP2;Dbxref=GeneID:25782,HGNC:HGNC:17168,MIM:609275;Name=RAB3GAP2;description=RAB3 GTPase activating non-catalytic protein subunit 2;gbkey=Gene;gene=RAB3GAP2;gene_biotype=protein_coding;gene_synonym=MARTS1,p150,RAB3-GAP150,RAB3GAP150,SPG69,WARBM2 ##sequence-region NT_187370.1 1 161471 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NT_187370.1 RefSeq region 1 161471 . + . ID=NT_187370.1:1..161471;Dbxref=taxon:9606;Name=2;chromosome=2;gbkey=Src;genome=genomic;map=unlocalized;mol_type=genomic DNA @@ -23,7 +23,7 @@ NC_000003.12 BestRefSeq gene 130678934 130746829 . - . ID=gene-PIK3R4;Dbxref=Gen ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000007.14 RefSeq region 1 159345973 . + . ID=NC_000007.14:1..159345973;Dbxref=taxon:9606;Name=7;chromosome=7;gbkey=Src;genome=chromosome;mol_type=genomic DNA NC_000007.14 BestRefSeq gene 100889994 100896994 . - . ID=gene-ACHE;Dbxref=GeneID:43,HGNC:HGNC:108,MIM:100740;Name=ACHE;description=acetylcholinesterase (Cartwright blood group);gbkey=Gene;gene=ACHE;gene_biotype=protein_coding;gene_synonym=ACEE,ARACHE,N-ACHE,YT -NC_000007.14 BestRefSeq%2CGnomon gene 140713328 140924929 . - . ID=gene-BRAF;Dbxref=GeneID:673,HGNC:HGNC:1097,MIM:164757;Name=BRAF;description=B-Raf proto-oncogene%2C serine/threonine kinase;gbkey=Gene;gene=BRAF;gene_biotype=protein_coding;gene_synonym=B-raf,B-RAF1,BRAF1,NS7,RAFB1 +NC_000007.14 BestRefSeq%2CGnomon gene 140713328 140924929 . - . ID=gene-BRAF;Dbxref=GeneID:673,HGNC:HGNC:1097,MIM:164757;Name=BRAF;description=B-Raf proto-oncogene%2C serine/threonine kinase;gbkey=Gene;gene=BRAF;gene_biotype=protein_coding;gene_synonym=B-raf,B-RAF1,BRAF-1,BRAF1,NS7,RAFB1 ##sequence-region NC_000008.11 1 145138636 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000008.11 RefSeq region 1 145138636 . + . ID=NC_000008.11:1..145138636;Dbxref=taxon:9606;Name=8;chromosome=8;gbkey=Src;genome=chromosome;mol_type=genomic DNA @@ -32,20 +32,20 @@ NC_000008.11 BestRefSeq%2CGnomon gene 93916923 93926068 . + . ID=gene-PDP1;Dbxre ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000009.12 RefSeq region 1 138394717 . + . ID=NC_000009.12:1..138394717;Dbxref=taxon:9606;Name=9;chromosome=9;gbkey=Src;genome=chromosome;mol_type=genomic DNA NC_000009.12 BestRefSeq gene 130713043 130887675 . + . ID=gene-ABL1;Dbxref=GeneID:25,HGNC:HGNC:76,MIM:189980;Name=ABL1;description=ABL proto-oncogene 1%2C non-receptor tyrosine kinase;gbkey=Gene;gene=ABL1;gene_biotype=protein_coding;gene_synonym=ABL,BCR-ABL,bcr/abl,c-ABL,c-ABL1,CHDSKM,JTK7,p150,v-abl -NC_000009.12 BestRefSeq gene 4662294 4665258 . + . ID=gene-PLPP6;Dbxref=GeneID:403313,HGNC:HGNC:23682,MIM:611666;Name=PLPP6;description=phospholipid phosphatase 6;gbkey=Gene;gene=PLPP6;gene_biotype=protein_coding;gene_synonym=bA6J24.6,PDP1,PPAPDC2,PSDP -NC_000009.12 BestRefSeq mRNA 4662294 4665258 . + . ID=rna-NM_203453.5;Parent=gene-PLPP6;Dbxref=Ensembl:ENST00000381883.5,GeneID:403313,Genbank:NM_203453.5,HGNC:HGNC:23682,MIM:611666;Name=NM_203453.5;gbkey=mRNA;gene=PLPP6;product=phospholipid phosphatase 6;tag=MANE Select;transcript_id=NM_203453.5 -NC_000009.12 BestRefSeq exon 4662294 4665258 . + . ID=exon-NM_203453.5-1;Parent=rna-NM_203453.5;Dbxref=Ensembl:ENST00000381883.5,GeneID:403313,Genbank:NM_203453.5,HGNC:HGNC:23682,MIM:611666;gbkey=mRNA;gene=PLPP6;product=phospholipid phosphatase 6;tag=MANE Select;transcript_id=NM_203453.5 -NC_000009.12 BestRefSeq CDS 4662376 4663263 . + 0 ID=cds-NP_982278.3;Parent=rna-NM_203453.5;Dbxref=CCDS:CCDS34981.1,Ensembl:ENSP00000371307.2,GeneID:403313,Genbank:NP_982278.3,HGNC:HGNC:23682,MIM:611666;Name=NP_982278.3;gbkey=CDS;gene=PLPP6;product=phospholipid phosphatase 6;protein_id=NP_982278.3;tag=MANE Select +NC_000009.12 BestRefSeq gene 4662294 4665258 . + . ID=gene-PLPP6;Dbxref=GeneID:403313,HGNC:HGNC:23682,MIM:611666;Name=PLPP6;description=phospholipid phosphatase 6;gbkey=Gene;gene=PLPP6;gene_biotype=protein_coding;gene_synonym=bA6J24.6,LPRP-B,PA-PSP,PDP1,PPAPDC2,PSDP +NC_000009.12 BestRefSeq mRNA 4662294 4665258 . + . ID=rna-NM_203453.5;Parent=gene-PLPP6;Dbxref=Ensembl:ENST00000381883.5,GeneID:403313,GenBank:NM_203453.5,HGNC:HGNC:23682,MIM:611666;Name=NM_203453.5;gbkey=mRNA;gene=PLPP6;product=phospholipid phosphatase 6;tag=MANE Select;transcript_id=NM_203453.5 +NC_000009.12 BestRefSeq exon 4662294 4665258 . + . ID=exon-NM_203453.5-1;Parent=rna-NM_203453.5;Dbxref=Ensembl:ENST00000381883.5,GeneID:403313,GenBank:NM_203453.5,HGNC:HGNC:23682,MIM:611666;gbkey=mRNA;gene=PLPP6;product=phospholipid phosphatase 6;tag=MANE Select;transcript_id=NM_203453.5 +NC_000009.12 BestRefSeq CDS 4662376 4663263 . + 0 ID=cds-NP_982278.3;Parent=rna-NM_203453.5;Dbxref=CCDS:CCDS34981.1,Ensembl:ENSP00000371307.2,GeneID:403313,GenBank:NP_982278.3,HGNC:HGNC:23682,MIM:611666;Name=NP_982278.3;gbkey=CDS;gene=PLPP6;product=polyisoprenoid diphosphate/phosphate phosphohydrolase PLPP6;protein_id=NP_982278.3;tag=MANE Select ##sequence-region NC_000011.10 1 135086622 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000011.10 RefSeq region 1 135086622 . + . ID=NC_000011.10:1..135086622;Dbxref=taxon:9606;Name=11;chromosome=11;gbkey=Src;genome=chromosome;mol_type=genomic DNA NC_000011.10 BestRefSeq gene 10751246 10779746 . + . ID=gene-CTR9;Dbxref=GeneID:9646,HGNC:HGNC:16850,MIM:609366;Name=CTR9;description=CTR9 homolog%2C Paf1/RNA polymerase II complex component;gbkey=Gene;gene=CTR9;gene_biotype=protein_coding;gene_synonym=p150,p150TSP,SH2BP1,TSBP NC_000011.10 Curated Genomic pseudogene 117135529 117138867 . + . ID=gene-LOC653303;Dbxref=GeneID:653303;Name=LOC653303;description=proprotein convertase subtilisin/kexin type 7 pseudogene;gbkey=Gene;gene=LOC653303;gene_biotype=pseudogene;pseudo=true -NC_000011.10 Curated Genomic exon 117135529 117135686 . + . ID=id-LOC653303;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true -NC_000011.10 Curated Genomic exon 117136519 117136613 . + . ID=id-LOC653303-2;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true -NC_000011.10 Curated Genomic exon 117137423 117137516 . + . ID=id-LOC653303-3;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true -NC_000011.10 Curated Genomic exon 117137785 117137902 . + . ID=id-LOC653303-4;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true -NC_000011.10 Curated Genomic exon 117138227 117138867 . + . ID=id-LOC653303-5;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true +NC_000011.10 Curated Genomic exon 117135529 117135686 . + . ID=id-LOC653303;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true +NC_000011.10 Curated Genomic exon 117136519 117136613 . + . ID=id-LOC653303-2;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true +NC_000011.10 Curated Genomic exon 117137423 117137516 . + . ID=id-LOC653303-3;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true +NC_000011.10 Curated Genomic exon 117137785 117137902 . + . ID=id-LOC653303-4;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true +NC_000011.10 Curated Genomic exon 117138227 117138867 . + . ID=id-LOC653303-5;Parent=gene-LOC653303;Dbxref=GeneID:653303;gbkey=exon;gene=LOC653303;pseudo=true ##sequence-region NC_000012.12 1 133275309 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000012.12 RefSeq region 1 133275309 . + . ID=NC_000012.12:1..133275309;Dbxref=taxon:9606;Name=12;chromosome=12;gbkey=Src;genome=chromosome;mol_type=genomic DNA @@ -53,11 +53,11 @@ NC_000012.12 BestRefSeq%2CGnomon gene 133037509 133063299 . + . ID=gene-ZNF84;Db ##sequence-region NC_000015.10 1 101991189 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000015.10 RefSeq region 1 101991189 . + . ID=NC_000015.10:1..101991189;Dbxref=taxon:9606;Name=15;chromosome=15;gbkey=Src;genome=chromosome;mol_type=genomic DNA -NC_000015.10 BestRefSeq gene 89784895 89814852 . - . ID=gene-ANPEP;Dbxref=GeneID:290,HGNC:HGNC:500,MIM:151530;Name=ANPEP;description=alanyl aminopeptidase%2C membrane;gbkey=Gene;gene=ANPEP;gene_biotype=protein_coding;gene_synonym=APN,CD13,GP150,LAP1,P150,PEPN +NC_000015.10 BestRefSeq gene 89784895 89814852 . - . ID=gene-ANPEP;Dbxref=GeneID:290,HGNC:HGNC:500,MIM:151530;Name=ANPEP;description=alanyl aminopeptidase%2C membrane;gbkey=Gene;gene=ANPEP;gene_biotype=protein_coding;gene_synonym=AP-M,AP-N,APN,CD13,GP150,hAPN,LAP1,P150,PEPN ##sequence-region NC_000019.10 1 58617616 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000019.10 RefSeq region 1 58617616 . + . ID=NC_000019.10:1..58617616;Dbxref=taxon:9606;Name=19;chromosome=19;gbkey=Src;genome=chromosome;mol_type=genomic DNA -NC_000019.10 BestRefSeq%2CGnomon gene 38211006 38229695 . - . ID=gene-DPF1;Dbxref=GeneID:8193,HGNC:HGNC:20225,MIM:601670;Name=DPF1;description=double PHD fingers 1;gbkey=Gene;gene=DPF1;gene_biotype=protein_coding;gene_synonym=BAF45b,NEUD4,neuro-d4 +NC_000019.10 BestRefSeq%2CGnomon gene 38211006 38229695 . - . ID=gene-DPF1;Dbxref=GeneID:8193,HGNC:HGNC:20225,MIM:601670;Name=DPF1;description=double PHD fingers 1;gbkey=Gene;gene=DPF1;gene_biotype=protein_coding;gene_synonym=BAF45b,NEUD4,neuro-d4,SMARCG1 NC_000019.10 BestRefSeq%2CGnomon gene 4402640 4450830 . + . ID=gene-CHAF1A;Dbxref=GeneID:10036,HGNC:HGNC:1910,MIM:601246;Name=CHAF1A;description=chromatin assembly factor 1 subunit A;gbkey=Gene;gene=CHAF1A;gene_biotype=protein_coding;gene_synonym=CAF-1,CAF1,CAF1B,CAF1P150,P150 ##sequence-region NT_187390.1 1 42811 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 @@ -83,9 +83,9 @@ NC_000023.11 BestRefSeq gene 155612586 155782459 . + . ID=gene-SPRY3;Dbxref=Gene ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NC_000024.10 RefSeq region 1 57227415 . + . ID=NC_000024.10:1..57227415;Dbxref=taxon:9606;Name=Y;chromosome=Y;gbkey=Src;genome=chromosome;mol_type=genomic DNA NC_000024.10 BestRefSeq gene 1386152 1392113 . - . ID=gene-SLC25A6-2;Dbxref=GeneID:293,HGNC:HGNC:10992,MIM:403000;Name=SLC25A6;description=solute carrier family 25 member 6;gbkey=Gene;gene=SLC25A6;gene_biotype=protein_coding;gene_synonym=AAC3,ANT,ANT 2,ANT 3,ANT3,ANT3Y -NC_000024.10 BestRefSeq gene 56954316 56968979 . + . ID=gene-SPRY3-2;Dbxref=GeneID:10251,HGNC:HGNC:11271,MIM:300531;Name=SPRY3;description=sprouty RTK signaling antagonist 3;gbkey=Gene;gene=SPRY3;gene_biotype=protein_coding;gene_synonym=spry-3 +NC_000024.10 BestRefSeq gene 56923423 56968979 . + . ID=gene-SPRY3-2;Dbxref=GeneID:10251,HGNC:HGNC:11271,MIM:300531;Name=SPRY3;description=sprouty RTK signaling antagonist 3;gbkey=Gene;gene=SPRY3;gene_biotype=protein_coding;gene_synonym=spry-3;partial=true;start_range=.,56923423 ##sequence-region NT_167246.2 1 4677643 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=9606 NT_167246.2 RefSeq region 1 4677643 . + . ID=NT_167246.2:1..4677643;Dbxref=taxon:9606;Name=6;chromosome=6;gbkey=Src;genome=genomic;map=6p22.1-21.32;mol_type=genomic DNA NT_167246.2 Curated Genomic pseudogene 3940270 3941874 . + . ID=gene-PRKRAP1;Dbxref=GeneID:731716,HGNC:HGNC:33447;Name=PRKRAP1;description=protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1;gbkey=Gene;gene=PRKRAP1;gene_biotype=pseudogene;pseudo=true -NT_167249.2 Curated Genomic pseudogene 3930481 3932085 . + . ID=gene-PRKRAP1-2;Dbxref=GeneID:731716,HGNC:HGNC:33447;Name=PRKRAP1;description=protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1;gbkey=Gene;gene=PRKRAP1;gene_biotype=pseudogene;pseudo=trueNC_000023.11 BestRefSeq gene 1386152 1392113 . - . ID=gene-SLC25A6;Dbxref=GeneID:293,HGNC:HGNC:10992,MIM:403000;Name=SLC25A6;description=solute carrier family 25 member 6;gbkey=Gene;gene=SLC25A6;gene_biotype=protein_coding;gene_synonym=AAC3,ANT,ANT 2,ANT 3,ANT3,ANT3Y +NT_167249.2 Curated Genomic pseudogene 3930481 3932085 . + . ID=gene-PRKRAP1-2;Dbxref=GeneID:731716,HGNC:HGNC:33447;Name=PRKRAP1;description=protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1;gbkey=Gene;gene=PRKRAP1;gene_biotype=pseudogene;pseudo=true diff --git a/tests/unit/data/etl_data/ncbi_history_20210813.tsv b/tests/unit/data/etl_data/ncbi_history_20241224.tsv similarity index 100% rename from tests/unit/data/etl_data/ncbi_history_20210813.tsv rename to tests/unit/data/etl_data/ncbi_history_20241224.tsv diff --git a/tests/unit/data/etl_data/ncbi_info_20210813.tsv b/tests/unit/data/etl_data/ncbi_info_20210813.tsv deleted file mode 100644 index ed2e4a3f..00000000 --- a/tests/unit/data/etl_data/ncbi_info_20210813.tsv +++ /dev/null @@ -1,26 +0,0 @@ -#tax_id GeneID Symbol LocusTag Synonyms dbXrefs chromosome map_location description type_of_gene Symbol_from_nomenclature_authority Full_name_from_nomenclature_authority Nomenclature_status Other_designations Modification_date Feature_type -9606 25 ABL1 - ABL|BCR-ABL|CHDSKM|JTK7|bcr/abl|c-ABL|c-ABL1|p150|v-abl MIM:189980|HGNC:HGNC:76|Ensembl:ENSG00000097007 9 9q34.12 ABL proto-oncogene 1, non-receptor tyrosine kinase protein-coding ABL1 ABL proto-oncogene 1, non-receptor tyrosine kinase O tyrosine-protein kinase ABL1|ABL protooncogene 1 nonreceptor tyrosine kinase|Abelson tyrosine-protein kinase 1|bcr/c-abl oncogene protein|c-abl oncogene 1, receptor tyrosine kinase|proto-oncogene c-Abl|proto-oncogene tyrosine-protein kinase ABL1|truncated ABL protooncogene 1 nonreceptor tyrosine kinase|v-abl Abelson murine leukemia viral oncogene homolog 1 20210809 - -9606 43 ACHE - ACEE|ARACHE|N-ACHE|YT MIM:100740|HGNC:HGNC:108|Ensembl:ENSG00000087085 7 7q22.1 acetylcholinesterase (Cartwright blood group) protein-coding ACHE acetylcholinesterase (Cartwright blood group) O acetylcholinesterase|Yt blood group|acetylcholinesterase (Yt blood group)|apoptosis-related acetylcholinesterase 20210719 - -9606 106 ADCP1 - - HGNC:HGNC:229 6 - adenosine deaminase complexing protein 1 unknown ADCP1 adenosine deaminase complexing protein 1 O - 20190324 - -9606 170 AFA - - MIM:106250 - - ankyloblepharon filiforme adnatum unknown - - - - 20191002 - -9606 290 ANPEP - APN|CD13|GP150|LAP1|P150|PEPN MIM:151530|HGNC:HGNC:500|Ensembl:ENSG00000166825 15 15q26.1 alanyl aminopeptidase, membrane protein-coding ANPEP alanyl aminopeptidase, membrane O aminopeptidase N|AP-M|AP-N|alanyl (membrane) aminopeptidase|aminopeptidase M|hAPN|membrane alanyl aminopeptidase|microsomal aminopeptidase|myeloid plasma membrane glycoprotein CD13 20210708 - -9606 673 BRAF - B-RAF1|B-raf|BRAF1|NS7|RAFB1 MIM:164757|HGNC:HGNC:1097|Ensembl:ENSG00000157764 7 7q34 B-Raf proto-oncogene, serine/threonine kinase protein-coding BRAF B-Raf proto-oncogene, serine/threonine kinase O serine/threonine-protein kinase B-raf|94 kDa B-raf protein|B-Raf proto-oncogene serine/threonine-protein kinase (p94)|B-Raf serine/threonine-protein|murine sarcoma viral (v-raf) oncogene homolog B1|proto-oncogene B-Raf|v-raf murine sarcoma viral oncogene homolog B|v-raf murine sarcoma viral oncogene homolog B1 20210809 - -9606 10036 CHAF1A - CAF-1|CAF1|CAF1B|CAF1P150|P150 MIM:601246|HGNC:HGNC:1910|Ensembl:ENSG00000167670 19 19p13.3 chromatin assembly factor 1 subunit A protein-coding CHAF1A chromatin assembly factor 1 subunit A O chromatin assembly factor 1 subunit A|CAF-1 subunit A|CAF-I 150 kDa subunit|CAF-I p150|CTB-50L17.7|chromatin assembly factor I (150 kDa)|chromatin assembly factor I p150 subunit|hp150 20210808 - -9606 9646 CTR9 - SH2BP1|TSBP|p150|p150TSP MIM:609366|HGNC:HGNC:16850|Ensembl:ENSG00000198730 11 11p15.4 CTR9 homolog, Paf1/RNA polymerase II complex component protein-coding CTR9 CTR9 homolog, Paf1/RNA polymerase II complex component O RNA polymerase-associated protein CTR9 homolog|Ctr9, Paf1/RNA polymerase II complex component, homolog|SH2 domain binding protein 1 (tetratricopeptide repeat containing)|TPR-containing, SH2-binding phosphoprotein 20210708 - -9606 8193 DPF1 - BAF45b|NEUD4|SMARCG1|neuro-d4 MIM:601670|HGNC:HGNC:20225|Ensembl:ENSG00000011332 19 19q13.2 double PHD fingers 1 protein-coding DPF1 double PHD fingers 1 O zinc finger protein neuro-d4|BRG1-associated factor 45B|D4, zinc and double PHD fingers family 1|neuro-d4 homolog 20210726 - -9606 2722 GLC1B - - MIM:606689 2 2cen-q13 glaucoma 1, open angle, B (adult-onset) unknown - - - - 20191002 - -9606 50829 HDPA - - MIM:300221 X Xpter-p22.32 Hodgkin disease, susceptibility, pseudoautosomal unknown - - - - 20190816 - -9606 106783576 LOC106783576 - - - 10 10p nonconserved acetylation island sequence 68 enhancer biological-region - - - non-conserved AI 68 20210518 regulatory:enhancer -9606 619511 MHB - - MIM:255160 3 3p22.2-p21.32 myopathy, hyaline body, autosomal recessive unknown - - - - 20170408 - -9606 54704 PDP1 - PDH|PDP|PDPC|PPM2A|PPM2C MIM:605993|HGNC:HGNC:9279|Ensembl:ENSG00000164951 8 8q22.1 pyruvate dehydrogenase phosphatase catalytic subunit 1 protein-coding PDP1 pyruvate dehydrogenase phosphatase catalytic subunit 1 O pyruvate dehyrogenase phosphatase catalytic subunit 1|PDP 1|PDPC 1|[Pyruvate dehydrogenase [acetyl-transferring]]-phosphatase 1, mitochondrial|protein phosphatase 2C, magnesium-dependent, catalytic subunit|protein phosphatase, Mg2+/Mn2+ dependent 2A|pyruvate dehydrogenase (Lipoamide) phosphatase-phosphatase 20210708 - -9606 403313 PLPP6 - LPRP-B|PA-PSP|PDP1|PPAPDC2|PSDP|bA6J24.6 MIM:611666|HGNC:HGNC:23682|Ensembl:ENSG00000205808|AllianceGenome:HGNC:23682 9 9p24.1 phospholipid phosphatase 6 protein-coding PLPP6 phospholipid phosphatase 6 O polyisoprenoid diphosphate/phosphate phosphohydrolase PLPP6|PPAP2 domain-containing protein 2|lipid phosphatase-related protein-B|phosphatidic acid phosphatase type 2 domain containing 2|phosphatidic acid phosphatase type 2 domain-containing protein 2|polyisoprenoid diphosphate phosphatase type 1|presqualene diphosphate phosphatase|type 1 polyisoprenoid diphosphate phosphatase 20220317 - -9606 30849 PIK3R4 - VPS15|p150 MIM:602610|HGNC:HGNC:8982|Ensembl:ENSG00000196455 3 3q22.1 phosphoinositide-3-kinase regulatory subunit 4 protein-coding PIK3R4 phosphoinositide-3-kinase regulatory subunit 4 O phosphoinositide 3-kinase regulatory subunit 4|PI3-kinase p150 subunit|PI3-kinase regulatory subunit 4|phosphatidylinositol 3-kinase-associated p150|phosphoinositide 3-kinase adaptor protein|phosphoinositide-3-kinase, regulatory subunit 4, p150 20210808 - -9606 731716 PRKRAP1 - - HGNC:HGNC:33447 6 6p21.3 alternate reference locus protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1 pseudo PRKRAP1 protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1 O protein kinase, interferon-inducible double stranded RNA dependent activator pseudogene 1 20210611 - -9606 25782 RAB3GAP2 - MARTS1|RAB3-GAP150|RAB3GAP150|SPG69|WARBM2|p150 MIM:609275|HGNC:HGNC:17168|Ensembl:ENSG00000118873 1 1q41 RAB3 GTPase activating non-catalytic protein subunit 2 protein-coding RAB3GAP2 RAB3 GTPase activating non-catalytic protein subunit 2 O rab3 GTPase-activating protein non-catalytic subunit|RAB3 GTPase activating protein subunit 2 (non-catalytic)|RGAP-iso|rab3 GTPase-activating protein 150 kDa subunit|rab3-GAP p150|rab3-GAP regulatory subunit 20210709 - -9606 293 SLC25A6 - AAC3|ANT|ANT 2|ANT 3|ANT3|ANT3Y MIM:300151|MIM:403000|HGNC:HGNC:10992|Ensembl:ENSG00000169100|Ensembl:ENSG00000292334|AllianceGenome:HGNC:10992 X|Y Xp22.33 and Yp11.2 solute carrier family 25 member 6 protein-coding SLC25A6 solute carrier family 25 member 6 O ADP/ATP translocase 3|ADP,ATP carrier protein 3|ADP,ATP carrier protein, liver|ADP/ATP translocator of liver|adenine nucleotide translocator 3|epididymis secretory sperm binding protein|solute carrier family 25 (mitochondrial carrier; adenine nucleotide translocator), member 6 20230718 - -9606 100049159 SPG37 - - MIM:611945 8 8p21.2-q13.3 spastic paraplegia 37 (autosomal dominant) unknown - - - - 20191002 - -9606 10251 SPRY3 - spry-3 MIM:300531|HGNC:HGNC:11271|Ensembl:ENSG00000168939|AllianceGenome:HGNC:11271 X|Y Xq28 and Yq12 sprouty RTK signaling antagonist 3 protein-coding SPRY3 sprouty RTK signaling antagonist 3 O protein sprouty homolog 3|antagonist of FGF signaling|sprouty homolog 3|sprouty3 20220805 - -9606 7637 ZNF84 - HPF2 MIM:618554|HGNC:HGNC:13159|Ensembl:ENSG00000198040 12 12q24.33|map from Rosati ref via FISH [AFS] zinc finger protein 84 protein-coding ZNF84 zinc finger protein 84 O zinc finger protein 84|zinc finger protein HPF2 20210611 - -9606 619538 OMS - COME/ROM MIM:166760 10|19|3 10q26.3;19q13.42-q13.43;3p25.3 otitis media, susceptibility to unknown - - - chronic/recurrent otitis media 20170408 - -9606 653303 LOC653303 - - - 11 11q23.3 proprotein convertase subtilisin/kexin type 7 pseudogene pseudo - - - - 20211123 - -9606 3466 IFNR - IFNGM|IFNGM2 MIM:147573|HGNC:HGNC:5447 16 - interferon production regulator unknown IFNR interferon production regulator O - 20190324 - diff --git a/tests/unit/data/etl_data/ncbi_info_20241224.tsv b/tests/unit/data/etl_data/ncbi_info_20241224.tsv new file mode 100644 index 00000000..63362f43 --- /dev/null +++ b/tests/unit/data/etl_data/ncbi_info_20241224.tsv @@ -0,0 +1,25 @@ +#tax_id GeneID Symbol LocusTag Synonyms dbXrefs chromosome map_location description type_of_gene Symbol_from_nomenclature_authority Full_name_from_nomenclature_authority Nomenclature_status Other_designations Modification_date Feature_type +9606 25 ABL1 - ABL|BCR-ABL|CHDSKM|JTK7|bcr/abl|c-ABL|c-ABL1|p150|v-abl MIM:189980|HGNC:HGNC:76|Ensembl:ENSG00000097007|AllianceGenome:HGNC:76 9 9q34.12 ABL proto-oncogene 1, non-receptor tyrosine kinase protein-coding ABL1 ABL proto-oncogene 1, non-receptor tyrosine kinase O tyrosine-protein kinase ABL1|ABL protooncogene 1 nonreceptor tyrosine kinase|Abelson tyrosine-protein kinase 1|BCR-ABL1 p190|BCR/ABL e8a2 fusion|BCR/ABL1 e1a2 fusion protein|BCR/ABL1 fusion|bcr/c-abl oncogene protein|c-abl oncogene 1, receptor tyrosine kinase|chimeric BCR::ABL1 protein|proto-oncogene c-Abl|proto-oncogene tyrosine-protein kinase ABL1|v-abl Abelson murine leukemia viral oncogene homolog 1 20241210 - +9606 43 ACHE - ACEE|ARACHE|N-ACHE|YT MIM:100740|HGNC:HGNC:108|Ensembl:ENSG00000087085|AllianceGenome:HGNC:108 7 7q22.1 acetylcholinesterase (Yt blood group) protein-coding ACHE acetylcholinesterase (Yt blood group) O acetylcholinesterase|Yt blood group|acetylcholinesterase (Cartwright blood group)|apoptosis-related acetylcholinesterase 20241210 - +9606 106 ADCP1 - - HGNC:HGNC:229 6 - adenosine deaminase complexing protein 1 unknown ADCP1 adenosine deaminase complexing protein 1 O - 20240817 - +9606 170 AFA - - MIM:106250 - - ankyloblepharon filiforme adnatum unknown - - - - 20241207 - +9606 290 ANPEP - AP-M|AP-N|APN|CD13|GP150|LAP1|P150|PEPN|hAPN MIM:151530|HGNC:HGNC:500|Ensembl:ENSG00000166825|AllianceGenome:HGNC:500 15 15q26.1 alanyl aminopeptidase, membrane protein-coding ANPEP alanyl aminopeptidase, membrane O aminopeptidase N|alanyl (membrane) aminopeptidase|aminopeptidase M|membrane alanyl aminopeptidase|microsomal aminopeptidase|myeloid plasma membrane glycoprotein CD13 20241210 - +9606 673 BRAF - B-RAF1|B-raf|BRAF-1|BRAF1|NS7|RAFB1 MIM:164757|HGNC:HGNC:1097|Ensembl:ENSG00000157764|AllianceGenome:HGNC:1097 7 7q34 B-Raf proto-oncogene, serine/threonine kinase protein-coding BRAF B-Raf proto-oncogene, serine/threonine kinase O serine/threonine-protein kinase B-raf|94 kDa B-raf protein|B-Raf proto-oncogene serine/threonine-protein kinase (p94)|B-Raf serine/threonine-protein|murine sarcoma viral (v-raf) oncogene homolog B1|proto-oncogene B-Raf|v-raf murine sarcoma viral oncogene homolog B|v-raf murine sarcoma viral oncogene homolog B1 20241210 - +9606 10036 CHAF1A - CAF-1|CAF1|CAF1B|CAF1P150|P150 MIM:601246|HGNC:HGNC:1910|Ensembl:ENSG00000167670|AllianceGenome:HGNC:1910 19 19p13.3 chromatin assembly factor 1 subunit A protein-coding CHAF1A chromatin assembly factor 1 subunit A O chromatin assembly factor 1 subunit A|CAF-1 subunit A|CAF-I 150 kDa subunit|CAF-I p150|CTB-50L17.7|chromatin assembly factor I (150 kDa)|chromatin assembly factor I p150 subunit|hp150 20241210 - +9606 9646 CTR9 - SH2BP1|TSBP|p150|p150TSP MIM:609366|HGNC:HGNC:16850|Ensembl:ENSG00000198730|AllianceGenome:HGNC:16850 11 11p15.4 CTR9 homolog, Paf1/RNA polymerase II complex component protein-coding CTR9 CTR9 homolog, Paf1/RNA polymerase II complex component O RNA polymerase-associated protein CTR9 homolog|Ctr9, Paf1/RNA polymerase II complex component, homolog|SH2 domain binding protein 1 (tetratricopeptide repeat containing)|TPR-containing, SH2-binding phosphoprotein 20241210 - +9606 8193 DPF1 - BAF45b|NEUD4|SMARCG1|neuro-d4 MIM:601670|HGNC:HGNC:20225|Ensembl:ENSG00000011332|AllianceGenome:HGNC:20225 19 19q13.2 double PHD fingers 1 protein-coding DPF1 double PHD fingers 1 O zinc finger protein neuro-d4|BRG1-associated factor 45B|D4, zinc and double PHD fingers family 1|neuro-d4 homolog 20241210 - +9606 2722 GLC1B - - MIM:606689 2 2cen-q13 glaucoma 1, open angle, B (adult-onset) unknown - - - - 20241207 - +9606 50829 HDPA - - MIM:300221 X Xpter-p22.32 Hodgkin disease, susceptibility, pseudoautosomal unknown - - - - 20241207 - +9606 106783576 LOC106783576 - - - 10 10p nonconserved acetylation island sequence 68 enhancer biological-region - - - non-conserved AI 68 20241210 regulatory:enhancer +9606 54704 PDP1 - PDH|PDP|PDPC|PDPC 1|PPM2A|PPM2C MIM:605993|HGNC:HGNC:9279|Ensembl:ENSG00000164951|AllianceGenome:HGNC:9279 8 8q22.1 pyruvate dehydrogenase phosphatase catalytic subunit 1 protein-coding PDP1 pyruvate dehydrogenase phosphatase catalytic subunit 1 O pyruvate dehyrogenase phosphatase catalytic subunit 1|[Pyruvate dehydrogenase [acetyl-transferring]]-phosphatase 1, mitochondrial|protein phosphatase 2C, magnesium-dependent, catalytic subunit|protein phosphatase, Mg2+/Mn2+ dependent 2A|pyruvate dehydrogenase (Lipoamide) phosphatase-phosphatase 20241210 - +9606 403313 PLPP6 - LPRP-B|PA-PSP|PDP1|PPAPDC2|PSDP|bA6J24.6 MIM:611666|HGNC:HGNC:23682|Ensembl:ENSG00000205808|AllianceGenome:HGNC:23682 9 9p24.1 phospholipid phosphatase 6 protein-coding PLPP6 phospholipid phosphatase 6 O polyisoprenoid diphosphate/phosphate phosphohydrolase PLPP6|PPAP2 domain-containing protein 2|lipid phosphatase-related protein-B|phosphatidic acid phosphatase type 2 domain containing 2|phosphatidic acid phosphatase type 2 domain-containing protein 2|polyisoprenoid diphosphate phosphatase type 1|presqualene diphosphate phosphatase|type 1 polyisoprenoid diphosphate phosphatase 20241210 - +9606 30849 PIK3R4 - VPS15|p150 MIM:602610|HGNC:HGNC:8982|Ensembl:ENSG00000196455|AllianceGenome:HGNC:8982 3 3q22.1 phosphoinositide-3-kinase regulatory subunit 4 protein-coding PIK3R4 phosphoinositide-3-kinase regulatory subunit 4 O phosphoinositide 3-kinase regulatory subunit 4|PI3-kinase p150 subunit|PI3-kinase regulatory subunit 4|phosphatidylinositol 3-kinase-associated p150|phosphoinositide 3-kinase adaptor protein|phosphoinositide-3-kinase, regulatory subunit 4, p150 20241210 - +9606 731716 PRKRAP1 - - HGNC:HGNC:33447|AllianceGenome:HGNC:33447 6 6p21.3 alternate reference locus protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1 pseudo PRKRAP1 protein activator of interferon induced protein kinase EIF2AK2 pseudogene 1 O protein kinase, interferon-inducible double stranded RNA dependent activator pseudogene 1 20241210 - +9606 25782 RAB3GAP2 - MARTS1|RAB3-GAP150|RAB3GAP150|SPG69|WARBM2|p150 MIM:609275|HGNC:HGNC:17168|Ensembl:ENSG00000118873|AllianceGenome:HGNC:17168 1 1q41 RAB3 GTPase activating non-catalytic protein subunit 2 protein-coding RAB3GAP2 RAB3 GTPase activating non-catalytic protein subunit 2 O rab3 GTPase-activating protein non-catalytic subunit|RAB3 GTPase activating protein subunit 2 (non-catalytic)|RGAP-iso|rab3 GTPase-activating protein 150 kDa subunit|rab3-GAP p150|rab3-GAP regulatory subunit 20241210 - +9606 293 SLC25A6 - AAC3|ANT|ANT 2|ANT 3|ANT3|ANT3Y MIM:300151|MIM:403000|HGNC:HGNC:10992|Ensembl:ENSG00000169100|Ensembl:ENSG00000292334|AllianceGenome:HGNC:10992 X|Y X;Y solute carrier family 25 member 6 protein-coding SLC25A6 solute carrier family 25 member 6 O ADP/ATP translocase 3|ADP,ATP carrier protein 3|ADP,ATP carrier protein, liver|ADP/ATP translocator of liver|adenine nucleotide translocator 3|epididymis secretory sperm binding protein|solute carrier family 25 (mitochondrial carrier; adenine nucleotide translocator), member 6 20241210 - +9606 100049159 SPG37 - - MIM:611945 8 8p21.2-q13.3 spastic paraplegia 37 (autosomal dominant) unknown - - - - 20241207 - +9606 10251 SPRY3 - spry-3 MIM:300531|HGNC:HGNC:11271|Ensembl:ENSG00000168939|AllianceGenome:HGNC:11271 X|Y Xq28 and Yq12 sprouty RTK signaling antagonist 3 protein-coding SPRY3 sprouty RTK signaling antagonist 3 O protein sprouty homolog 3|antagonist of FGF signaling|sprouty homolog 3|sprouty3 20241210 - +9606 7637 ZNF84 - HPF2 MIM:618554|HGNC:HGNC:13159|Ensembl:ENSG00000198040|AllianceGenome:HGNC:13159 12 12q24.33|map from Rosati ref via FISH [AFS] zinc finger protein 84 protein-coding ZNF84 zinc finger protein 84 O zinc finger protein 84|zinc finger protein HPF2 20241210 - +9606 653303 LOC653303 - - - 11 11q23.3 proprotein convertase subtilisin/kexin type 7 pseudogene pseudo - - - - 20241210 - +9606 3466 IFNR - IFNGM|IFNGM2 MIM:147573|HGNC:HGNC:5447 16 - interferon production regulator unknown IFNR interferon production regulator O - 20240817 - +9606 4625 MYH7 - CMD1S|CMH1|CMYO7A|CMYO7B|CMYP7A|CMYP7B|MPD1|MYHCB|SPMD|SPMM MIM:160760|HGNC:HGNC:7577|Ensembl:ENSG00000092054|AllianceGenome:HGNC:7577 14 14q11.2 myosin heavy chain 7 protein-coding MYH7 myosin heavy chain 7 O myosin-7|cardiac muscle myosin heavy chain 7 beta|myHC-beta|myhc-slow|myosin 7|myosin heavy chain beta-subunit|myosin, heavy chain 7, cardiac muscle, beta|myosin, heavy polypeptide 7, cardiac muscle, beta|rhabdomyosarcoma antigen MU-RMS-40.7A 20241210 - diff --git a/tests/unit/test_ensembl_source.py b/tests/unit/test_ensembl_source.py index 0bc9cd4a..c5f38843 100644 --- a/tests/unit/test_ensembl_source.py +++ b/tests/unit/test_ensembl_source.py @@ -36,8 +36,8 @@ def ddx11l1(): "location_annotations": [], "locations": [ { - "end": 14409, - "start": 11868, + "end": 13670, + "start": 12009, "sequenceReference": { "type": "SequenceReference", "refgetAccession": "SQ.Ya6Rs7DHhDeg7YaOSg1EoNi3U_nQ9SvO", @@ -67,7 +67,7 @@ def tp53(): "location_annotations": [], "locations": [ { - "end": 7687538, + "end": 7687546, "start": 7661778, "sequenceReference": { "type": "SequenceReference", @@ -98,8 +98,8 @@ def ATP6AP1_DT(): # noqa: N802 "location_annotations": [], "locations": [ { - "end": 154428526, - "start": 154424377, + "end": 154428549, + "start": 154424376, "sequenceReference": { "type": "SequenceReference", "refgetAccession": "SQ.w0WZEvgJF0zf_P4yyTzjjv9oW1z61HHP", @@ -302,9 +302,9 @@ def test_meta_info(ensembl): resp.source_meta_.data_license_url == "https://useast.ensembl.org/info/about/legal/disclaimer.html" ) - assert resp.source_meta_.version == "110" + assert resp.source_meta_.version == "113" assert resp.source_meta_.data_url == { - "genome_annotations": "ftp://ftp.ensembl.org/pub/release-110/gff3/homo_sapiens/Homo_sapiens.GRCh38.110.gff3.gz" + "genome_annotations": "ftp://ftp.ensembl.org/pub/release-113/gff3/homo_sapiens/Homo_sapiens.GRCh38.113.gff3.gz" } assert resp.source_meta_.rdp_url is None assert resp.source_meta_.genome_assemblies == ["GRCh38"] diff --git a/tests/unit/test_hgnc_source.py b/tests/unit/test_hgnc_source.py index db38d8d4..96314b80 100644 --- a/tests/unit/test_hgnc_source.py +++ b/tests/unit/test_hgnc_source.py @@ -76,18 +76,6 @@ def tp53(): "ucsc:uc060aur.1", "uniprot:P04637", "orphanet:120204", - "ccds:CCDS73968", - "ccds:CCDS73971", - "ccds:CCDS73970", - "ccds:CCDS73969", - "ccds:CCDS73967", - "ccds:CCDS73966", - "ccds:CCDS73965", - "ccds:CCDS73964", - "ccds:CCDS73963", - "ccds:CCDS11118", - "ccds:CCDS45605", - "ccds:CCDS45606", "ena.embl:AF307851", "pubmed:6396087", "pubmed:3456488", @@ -328,12 +316,6 @@ def csf2ra(): "ucsc:uc010nvv.3", "uniprot:P15509", "ena.embl:M64445", - "ccds:CCDS35190", - "ccds:CCDS55360", - "ccds:CCDS35191", - "ccds:CCDS55359", - "ccds:CCDS35192", - "ccds:CCDS35193", "pubmed:1702217", ], "gene_type": "gene with protein product", diff --git a/tests/unit/test_ncbi_source.py b/tests/unit/test_ncbi_source.py index aca8fd61..d8a323e7 100644 --- a/tests/unit/test_ncbi_source.py +++ b/tests/unit/test_ncbi_source.py @@ -86,7 +86,7 @@ def pdp1_symbol(): "label": "pyruvate dehydrogenase phosphatase catalytic subunit 1", "concept_id": "ncbigene:54704", "symbol": "PDP1", - "aliases": ["PDH", "PDP", "PDPC", "PPM2A", "PPM2C"], + "aliases": ["PDH", "PDP", "PDPC", "PPM2A", "PPM2C", "PDPC 1"], "xrefs": ["hgnc:9279", "ensembl:ENSG00000164951"], "previous_symbols": ["LOC157663", "PPM2C"], "associated_with": ["omim:605993"], @@ -168,7 +168,7 @@ def spry3(): }, { "end": 56968979, - "start": 56954315, + "start": 56923422, "sequenceReference": { "type": "SequenceReference", "refgetAccession": "SQ.8_liLu1aycC0tPQPFmUaGXJLDs5SbPZ5", @@ -271,7 +271,7 @@ def slc25a6(): "previous_symbols": ["ANT3Y"], "associated_with": ["omim:300151", "omim:403000"], "symbol_status": None, - "location_annotations": [], + "location_annotations": ["X", "Y"], "strand": "-", "locations": [ { @@ -406,28 +406,6 @@ def prkrap1(): return Gene(**params) -# start > end -@pytest.fixture(scope="module") -def mhb(): - """Create gene fixture for MHB.""" - params = { - "match_type": MatchType.NO_MATCH, - "label": "myopathy, hyaline body, autosomal recessive", - "concept_id": "ncbigene:619511", - "symbol": "MHB", - "aliases": [], - "xrefs": [], - "previous_symbols": [], - "associated_with": ["omim:255160"], - "symbol_status": None, - "location_annotations": [], - "strand": None, - "locations": [], - "gene_type": "unknown", - } - return Gene(**params) - - # Different arms @pytest.fixture(scope="module") def spg37(): @@ -661,21 +639,6 @@ def test_prkrap1(check_resp_single_record, ncbi, prkrap1): check_resp_single_record(resp, prkrap1, MatchType.XREF) -def test_mhb(check_resp_single_record, ncbi, mhb): - """Test that MHB normalizes to correct gene concept.""" - # Concept ID - resp = ncbi.search("NCBIgene:619511") - check_resp_single_record(resp, mhb, MatchType.CONCEPT_ID) - - # Symbol - resp = ncbi.search("MHB") - check_resp_single_record(resp, mhb, MatchType.SYMBOL) - - # associated_with - resp = ncbi.search("OMIM:255160") - check_resp_single_record(resp, mhb, MatchType.ASSOCIATED_WITH) - - def test_spg37(check_resp_single_record, ncbi, spg37): """Test that SPG37 normalizes to correct gene concept.""" # Concept ID diff --git a/tests/unit/test_query.py b/tests/unit/test_query.py index b23dc3c8..3be75c57 100644 --- a/tests/unit/test_query.py +++ b/tests/unit/test_query.py @@ -57,18 +57,6 @@ def normalized_ache(): "coding": {"code": "uc003uxi.4", "system": "ucsc"}, "relation": "relatedMatch", }, - { - "coding": {"code": "CCDS5710", "system": "ccds"}, - "relation": "relatedMatch", - }, - { - "coding": {"code": "CCDS64736", "system": "ccds"}, - "relation": "relatedMatch", - }, - { - "coding": {"code": "CCDS5709", "system": "ccds"}, - "relation": "relatedMatch", - }, { "coding": {"code": "P22303", "system": "uniprot"}, "relation": "relatedMatch", @@ -99,7 +87,7 @@ def normalized_ache(): {"name": "previous_symbols", "value": ["ACEE", "YT"]}, { "name": "approved_name", - "value": "acetylcholinesterase (Cartwright blood group)", + "value": "acetylcholinesterase (Yt blood group)", }, {"name": "symbol_status", "value": "approved"}, { @@ -160,10 +148,6 @@ def normalized_braf(): "coding": {"code": "ENSG00000157764", "system": "ensembl"}, "relation": "relatedMatch", }, - { - "coding": {"code": "CCDS5863", "system": "ccds"}, - "relation": "relatedMatch", - }, { "coding": {"code": "1943", "system": "iuphar"}, "relation": "relatedMatch", @@ -192,10 +176,6 @@ def normalized_braf(): "coding": {"code": "NM_004333", "system": "refseq"}, "relation": "relatedMatch", }, - { - "coding": {"code": "CCDS87555", "system": "ccds"}, - "relation": "relatedMatch", - }, { "coding": {"code": "P15056", "system": "uniprot"}, "relation": "relatedMatch", @@ -212,14 +192,6 @@ def normalized_braf(): "coding": {"code": "1565476", "system": "pubmed"}, "relation": "relatedMatch", }, - { - "coding": {"code": "CCDS94219", "system": "ccds"}, - "relation": "relatedMatch", - }, - { - "coding": {"code": "CCDS94218", "system": "ccds"}, - "relation": "relatedMatch", - }, ], "extensions": [ { @@ -300,14 +272,6 @@ def normalized_abl1(): "coding": {"code": "uc004bzv.4", "system": "ucsc"}, "relation": "relatedMatch", }, - { - "coding": {"code": "CCDS35166", "system": "ccds"}, - "relation": "relatedMatch", - }, - { - "coding": {"code": "CCDS35165", "system": "ccds"}, - "relation": "relatedMatch", - }, { "coding": {"code": "P00519", "system": "uniprot"}, "relation": "relatedMatch", @@ -393,7 +357,7 @@ def normalized_abl1(): "type": "SequenceReference", "refgetAccession": "SQ.KEO-4XBcm1cxeo_DIQ8_ofqGUkp4iZhI", }, - "start": 130713015, + "start": 130713042, "end": 130887675, } ], @@ -729,7 +693,7 @@ def normalize_unmerged_ache(): "concept_id": "ncbigene:43", "symbol": "ACHE", "symbol_status": None, - "label": "acetylcholinesterase (Cartwright blood group)", + "label": "acetylcholinesterase (Yt blood group)", "strand": "-", "location_annotations": [], "locations": [ @@ -757,7 +721,7 @@ def normalize_unmerged_ache(): "concept_id": "ensembl:ENSG00000087085", "symbol": "ACHE", "symbol_status": None, - "label": "acetylcholinesterase (Cartwright blood group)", + "label": "acetylcholinesterase (Yt blood group)", "strand": "-", "location_annotations": [], "locations": [ @@ -785,7 +749,7 @@ def normalize_unmerged_ache(): "concept_id": "hgnc:108", "symbol": "ACHE", "symbol_status": "approved", - "label": "acetylcholinesterase (Cartwright blood group)", + "label": "acetylcholinesterase (Yt blood group)", "strand": None, "location_annotations": [], "locations": [], @@ -796,14 +760,11 @@ def normalize_unmerged_ache(): "ucsc:uc003uxi.4", "vega:OTTHUMG00000157033", "merops:S09.979", - "ccds:CCDS5710", "omim:100740", "iuphar:2465", - "ccds:CCDS5709", "refseq:NM_015831", "pubmed:1380483", "uniprot:P22303", - "ccds:CCDS64736", ], "gene_type": "gene with protein product", }