{ "bcoid": "GLY_000089", "title": "Human Disease Ontology Mapping", "description": "The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession ...", "filename": "domap.csv", "filetype": "csv", "categories": { "species": "Homo Sapiens", "molecule": "Protein", "tags": "Human Disease Ontology Mapping", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "0110887...", "inflammatory..." ], [ "2012...", "Nezelof synd..." ] ], "headers": [ "do_id...", "do_name..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "do_id" }, { "type": "string", "label": "do_name" }, { "type": "string", "label": "xref_database" }, { "type": "string", "label": "xref_database_id" } ], [ "0110887", "inflammatory bowel disease 12", "mondo", "0012829" ], [ "2012", "Nezelof syndrome", "icd10cm", "D81.4" ], [ "2012", "Nezelof syndrome", "icd9cm", "279.13" ], [ "2012", "Nezelof syndrome", "mesh", "C536288" ], [ "2012", "Nezelof syndrome", "umls", "C0152094" ], [ "2012", "Nezelof syndrome", "mondo", "0009451" ], [ "10968", "spastic monoplegia", "icd9cm", "343.3" ], [ "10968", "spastic monoplegia", "mesh", "D002547" ], [ "10968", "spastic monoplegia", "umls", "C0154698" ], [ "10968", "spastic monoplegia", "mondo", "0001169" ], [ "0070071", "autosomal dominant non-syndromic intellectual disability 41", "mondo", "0014842" ], [ "4024", "scirrhous adenocarcinoma", "mesh", "D002293" ], [ "4024", "scirrhous adenocarcinoma", "umls", "C0007135" ], [ "4024", "scirrhous adenocarcinoma", "mondo", "0005953" ], [ "0070070", "autosomal dominant non-syndromic intellectual disability 40", "mondo", "0014699" ], [ "12385", "shigellosis", "kegg", "05131" ], [ "12385", "shigellosis", "icd10cm", "A03" ], [ "12385", "shigellosis", "icd10cm", "A03.0" ], [ "12385", "shigellosis", "icd10cm", "A03.1" ], [ "12385", "shigellosis", "icd10cm", "A03.2" ], [ "12385", "shigellosis", "icd10cm", "A03.9" ], [ "12385", "shigellosis", "icd9cm", "004" ], [ "12385", "shigellosis", "icd9cm", "004.0" ], [ "12385", "shigellosis", "icd9cm", "004.1" ], [ "12385", "shigellosis", "icd9cm", "004.2" ], [ "12385", "shigellosis", "icd9cm", "004.9" ], [ "12385", "shigellosis", "mesh", "D004405" ], [ "12385", "shigellosis", "umls", "C0013371" ], [ "12385", "shigellosis", "umls", "C0302358" ], [ "12385", "shigellosis", "umls", "C0302359" ], [ "12385", "shigellosis", "umls", "C0302360" ], [ "12385", "shigellosis", "mondo", "0019345" ], [ "11549", "Adie syndrome", "mesh", "D000270" ], [ "11549", "Adie syndrome", "umls", "C0001519" ], [ "11549", "Adie syndrome", "mondo", "0018690" ], [ "0080351", "CLOVES syndrome", "icd10cm", "Q87.3" ], [ "0080351", "CLOVES syndrome", "mondo", "0013038" ], [ "4028", "angioma serpiginosum", "icd10cm", "L81.7" ], [ "4028", "angioma serpiginosum", "mesh", "C536366" ], [ "4028", "angioma serpiginosum", "umls", "C0263637" ], [ "4028", "angioma serpiginosum", "mondo", "0019803" ], [ "4029", "gastritis", "icd10cm", "K29.7" ], [ "4029", "gastritis", "mesh", "D005756" ], [ "4029", "gastritis", "umls", "C0017152" ], [ "4029", "gastritis", "mondo", "0004966" ], [ "0110434", "dilated cardiomyopathy 1Z", "icd10cm", "I42.0" ], [ "0110434", "dilated cardiomyopathy 1Z", "mondo", "0012745" ], [ "0070072", "autosomal dominant non-syndromic intellectual disability 42", "mondo", "0014855" ], [ "11385", "expressive language disorder", "icd10cm", "F80.1" ], [ "11385", "expressive language disorder", "icd9cm", "315.31" ], [ "11385", "expressive language disorder", "umls", "C0236826" ], [ "11385", "expressive language disorder", "mondo", "0001276" ], [ "0110435", "dilated cardiomyopathy 1GG", "icd10cm", "I42.0" ], [ "0110435", "dilated cardiomyopathy 1GG", "mondo", "0013339" ], [ "5983", "kidney osteogenic sarcoma", "umls", "C1335747" ], [ "5983", "kidney osteogenic sarcoma", "mondo", "0003721" ], [ "0110436", "dilated cardiomyopathy 1L", "icd10cm", "I42.0" ], [ "0110436", "dilated cardiomyopathy 1L", "mondo", "0011702" ], [ "0070024", "autosomal recessive dyskeratosis congenita 6", "mondo", "0014600" ], [ "0070293", "primary autosomal recessive microcephaly 2 with or without cortical malformations", "mondo", "0011435" ], [ "0110437", "dilated cardiomyopathy 1K", "icd10cm", "I42.0" ], [ "0110437", "dilated cardiomyopathy 1K", "mondo", "0011567" ], [ "341", "peripheral vascular disease", "icd9cm", "443.81" ], [ "341", "peripheral vascular disease", "mesh", "D016491" ], [ "341", "peripheral vascular disease", "umls", "C0003838" ], [ "341", "peripheral vascular disease", "umls", "C0031115" ], [ "341", "peripheral vascular disease", "mondo", "0005294" ], [ "3999", "Bartholin's gland carcinoma", "umls", "C0349561" ], [ "3999", "Bartholin's gland carcinoma", "mondo", "0002829" ], [ "3998", "Bartholin's gland transitional cell carcinoma", "umls", "C1511053" ], [ "3998", "Bartholin's gland transitional cell carcinoma", "mondo", "0002828" ], [ "0110430", "dilated cardiomyopathy 1G", "icd10cm", "I42.0" ], [ "0110430", "dilated cardiomyopathy 1G", "mondo", "0011400" ], [ "7519", "endocervical carcinoma", "umls", "C1299237" ], [ "7519", "endocervical carcinoma", "mondo", "0004259" ], [ "0110431", "dilated cardiomyopathy 1I", "icd10cm", "I42.0" ], [ "0110431", "dilated cardiomyopathy 1I", "mondo", "0011482" ], [ "0090114", "Sorsby's fundus dystrophy", "mondo", "0007640" ], [ "0060911", "karyomegalic interstitial nephritis", "icd10cm", "N11.8" ], [ "0060911", "karyomegalic interstitial nephritis", "mondo", "0013898" ], [ "0110432", "dilated cardiomyopathy 1NN", "icd10cm", "I42.0" ], [ "0110432", "dilated cardiomyopathy 1NN", "mondo", "0014396" ], [ "0090115", "spinocerebellar ataxia type 1 with axonal neuropathy", "icd10cm", "G60.2" ], [ "0090115", "spinocerebellar ataxia type 1 with axonal neuropathy", "mondo", "0011801" ] ] }, "readme": "Name\n - Human Disease Ontology Mapping\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-01-23T17:21:05.958718\n\nModified on\n - 2019-09-12T15:24:09.336037\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - \n\nChecksum\n - \n\nUsability Domain\n - The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)\n - If you use this dataset please provide proper attribution to GlyGen and Diease ontology\n\nDescription Domain\n Keywords\n - disease ontology\n - mesh id\n - icd 10\n - icd 9\n - umls id\n - kegg\n\n Pipeline Steps\n - Step-1: The script extract-from-endpoint.py extracts the cross-reference mapping between DOID and other databases such as ICD 9, ICD 10, UMLS, MeSH, Kegg and maps it to UniProtKB canonical accessions to be finally processed into a csv. The source owl file is loaded as triples in into the triplestore prior to the extraction\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: human_do_061419.owl\n URI: https://data.glygen.org/ln2wwwdata/source/human_do_061419.owl\n Output Subdomain\n Name: domap.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/domap.csv\n Name: human_protein_idmapping.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.stat.csv\n\nFields\n Name: \"status\"\n Description: \"Status of the protein record in UniProtKB database that can be reviewed for UniProtKB/Swiss-Prot entry or unreviewed for UniProtKB/TrEMBL entry\"\n Unique Values: \"2\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"20950\"\n Name: \"unreviewed_isoforms\"\n Description: \"Protein records from UniProtKB/TrEMBL database that have been computationally annotated\"\n Unique Values: \"52136\"\n Name: \"gene_name\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\n Unique Values: \"20302\"\n Name: \"reviewed_isoforms\"\n Description: \"Protein records from UniProtKB/SwissProt database that have been manually curated and annotated based on experimental results\n Unique Values: \"42417\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/domap.csv" }