{ "bcoid": "GLY_000084", "title": "Human Protein Diseases", "description": "The Human Protein Diseases dataset contains list of human [taxid:9606] diseases from OMIM, MONDO and ...", "filename": "human_protein_disease.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Diseases", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P30613-1...", "protein_xref..." ], [ "P30613-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "database_label" }, { "type": "string", "label": "do_id" }, { "type": "string", "label": "mondo_id" } ], [ "P30613-1", "protein_xref_omim", "102900", "Pyruvate kinase hyperactivity", "", "0007067" ], [ "P30613-1", "protein_xref_omim", "266200", "Pyruvate kinase deficiency of red cells", "0111077", "0009950" ], [ "P20930-1", "protein_xref_omim", "146700", "Ichthyosis vulgaris", "1702", "0007810" ], [ "P20930-1", "protein_xref_omim", "605803", "Dermatitis atopic 2", "0110098", "0011596" ], [ "P20933-1", "protein_xref_mondo", "0008830", "Aspartylglucosaminuria", "0050461", "0008830" ], [ "P20933-1", "protein_xref_omim", "208400", "Aspartylglucosaminuria", "0050461", "0008830" ], [ "P20936-1", "protein_xref_omim", "608354", "Capillary malformation-arteriovenous malformation 1", "", "0012016" ], [ "Q8NHX9-1", "protein_xref_omim", "612267", "", "", "" ], [ "Q9NXR8-1", "protein_xref_omim", "275355", "Squamous cell carcinoma of the head and neck", "5520", "0010150" ], [ "Q9NXR1-2", "protein_xref_omim", "605013", "Microhydranencephaly", "", "0011504" ], [ "Q9NXR1-2", "protein_xref_omim", "614019", "Lissencephaly 4", "0050453", "0013527" ], [ "Q96J66-1", "protein_xref_omim", "117800", "", "", "0044224" ], [ "Q13835-1", "protein_xref_omim", "604536", "Ectodermal dysplasia-skin fragility syndrome", "", "0011472" ], [ "P40424-1", "protein_xref_omim", "617641", "Congenital anomalies of kidney and urinary tract syndrome with or without hearing loss, abnormal ears, or developmental delay", "", "0060549" ], [ "P09001-1", "protein_xref_omim", "614582", "Combined oxidative phosphorylation deficiency 9", "0111472", "0013811" ], [ "O00337-1", "protein_xref_omim", "618477", "Uridine-cytidineuria", "", "" ], [ "Q8WTV0-1", "protein_xref_omim", "610762", "", "", "" ], [ "Q9H2I8-1", "protein_xref_omim", "615179", "Albinism, oculocutaneous, 7", "0070100", "0014070" ], [ "P08842-1", "protein_xref_omim", "308100", "Ichthyosis, X-linked", "1700", "0010622" ], [ "P03891-1", "protein_xref_omim", "502500", "Alzheimer disease mitochondrial", "", "0010783" ], [ "P03891-1", "protein_xref_omim", "535000", "Leber hereditary optic neuropathy", "705", "0010788" ], [ "P03897-1", "protein_xref_omim", "256000", "Leigh syndrome", "3652", "0009723" ], [ "P03897-1", "protein_xref_omim", "500014", "Mitochondrial complex I deficiency, mitochondrial type 1", "", "" ], [ "P02768-1", "protein_xref_omim", "615999", "Hyperthyroxinemia, familial dysalbuminemic", "", "0014448" ], [ "P02768-1", "protein_xref_omim", "616000", "Analbuminemia", "", "0014449" ], [ "P08559-1", "protein_xref_omim", "312170", "Pyruvate dehydrogenase E1-alpha deficiency", "3649", "0010717" ], [ "P02765-1", "protein_xref_omim", "203650", "Alopecia-mental retardation syndrome 1", "0080628", "0021035" ], [ "P02765-1", "protein_xref_omim", "203650", "Alopecia-mental retardation syndrome 1", "0080627", "0021035" ], [ "P02766-1", "protein_xref_omim", "105210", "Amyloidosis, transthyretin-related", "0050638", "0007100" ], [ "P02766-1", "protein_xref_omim", "115430", "Carpal tunnel syndrome 1", "12169", "0020730" ], [ "P02766-1", "protein_xref_omim", "145680", "Hyperthyroxinemia, dystransthyretinemic", "0080219", "0007785" ], [ "Q9UJ71-1", "protein_xref_omim", "613393", "Birbeck granule deficiency", "", "0013251" ], [ "P35579-1", "protein_xref_omim", "155100", "Macrothrombocytopenia and granulocyte inclusions with or without nephritis or sensorineural hearing loss", "0060651", "0007954" ], [ "P35579-1", "protein_xref_omim", "603622", "Deafness, autosomal dominant, 17", "0110548", "0011350" ], [ "Q8N1G0-1", "protein_xref_omim", "616833", "Paget disease of bone 6", "", "0014792" ], [ "O15259-1", "protein_xref_omim", "256100", "Nephronophthisis 1", "12712", "0009728" ], [ "O15259-1", "protein_xref_omim", "256100", "Nephronophthisis 1", "0111112", "0009728" ], [ "O15259-1", "protein_xref_omim", "266900", "Senior-Loken syndrome 1", "0050576", "0009962" ], [ "O15259-1", "protein_xref_omim", "609583", "Joubert syndrome 4", "0110999", "0012308" ], [ "P41180-1", "protein_xref_omim", "145980", "Hypocalciuric hypercalcemia, familial 1", "0060699", "0007791" ], [ "P41180-1", "protein_xref_omim", "145980", "Hypocalciuric hypercalcemia, familial 1", "0060700", "0007791" ], [ "P41180-1", "protein_xref_omim", "239200", "Hyperparathyroidism, neonatal severe", "", "0009397" ], [ "P41180-1", "protein_xref_omim", "601198", "Hypocalcemia, autosomal dominant 1", "0090107", "0011013" ], [ "P41180-1", "protein_xref_omim", "601198", "Hypocalcemia, autosomal dominant 1", "0090109", "0011013" ], [ "P41180-1", "protein_xref_omim", "612899", "Epilepsy, idiopathic generalized 8", "0111322", "0013032" ], [ "Q86XA0-1", "protein_xref_omim", "615942", "Mental retardation, autosomal recessive 44", "0060308", "0014409" ], [ "P29401-1", "protein_xref_omim", "617044", "Short stature, developmental delay, and congenital heart defects", "", "0014881" ], [ "P41181-1", "protein_xref_omim", "125800", "Diabetes insipidus, nephrogenic, autosomal", "12387", "0007451" ], [ "O00330-1", "protein_xref_omim", "245349", "Pyruvate dehydrogenase E3-binding protein deficiency", "3649", "0009503" ], [ "Q7RTW8-1", "protein_xref_omim", "607039", "Deafness, autosomal recessive, 22", "0110480", "0011762" ], [ "P12074-1", "protein_xref_omim", "616039", "Charcot-Marie-Tooth disease, recessive, intermediate type, D", "0110203", "0014467" ], [ "Q9P219-1", "protein_xref_omim", "236600", "Hydrocephalus, congenital, 1", "10908", "0009360" ], [ "Q9P219-1", "protein_xref_omim", "616053", "Spinocerebellar ataxia 40", "0050986", "0014475" ], [ "Q9UK17-1", "protein_xref_omim", "607346", "Spinocerebellar ataxia 19", "0050970", "0011819" ], [ "Q9UK17-1", "protein_xref_omim", "616399", "Brugada syndrome 9", "0110226", "0014621" ], [ "Q9P212-1", "protein_xref_omim", "610725", "Nephrotic syndrome 3", "0080382", "0012546" ], [ "Q92838-1", "protein_xref_omim", "305100", "Ectodermal dysplasia 1, hypohidrotic, X-linked", "0111664", "0010585" ], [ "Q92838-1", "protein_xref_omim", "305100", "Ectodermal dysplasia 1, hypohidrotic, X-linked", "2121", "0010585" ], [ "Q92838-1", "protein_xref_omim", "313500", "Tooth agenesis, selective, X-linked, 1", "0050591", "0010741" ], [ "Q9H845-1", "protein_xref_omim", "611126", "Mitochondrial complex I deficiency, nuclear type 20", "", "0012624" ], [ "Q9BZG2-1", "protein_xref_omim", "617297", "Amelogenesis imperfecta 1J", "", "0015008" ], [ "O43933-1", "protein_xref_omim", "214100", "Peroxisome biogenesis disorder 1A", "0080377", "0008953" ], [ "O43933-1", "protein_xref_omim", "214100", "Peroxisome biogenesis disorder 1A", "0080476", "0008953" ], [ "O43933-1", "protein_xref_omim", "234580", "Heimler syndrome 1", "0080623", "0024544" ], [ "O43933-1", "protein_xref_omim", "601539", "Peroxisome biogenesis disorder 1B", "", "0011101" ], [ "Q9BZG8-1", "protein_xref_omim", "616901", "Developmental delay with short stature, dysmorphic features, and sparse hair", "", "0014824" ], [ "Q9Y592-1", "protein_xref_omim", "615862", "Nephronophthisis 18", "0111125", "0014374" ], [ "P19099-1", "protein_xref_omim", "103900", "Hyperaldosteronism, familial, 1", "14080", "0007080" ], [ "P19099-1", "protein_xref_omim", "203400", "Corticosterone methyloxidase 1 deficiency", "0080626", "0008751" ], [ "P19099-1", "protein_xref_omim", "610600", "Corticosterone methyloxidase 2 deficiency", "", "0012524" ], [ "P53708-1", "protein_xref_omim", "191830", "Renal hypodysplasia/aplasia 1", "14766", "0024519" ], [ "Q14563-1", "protein_xref_omim", "614897", "Hypogonadotropic hypogonadism 16 with or without anosmia", "0090080", "0013961" ], [ "Q8WYB5-1", "protein_xref_omim", "603736", "Ohdo syndrome, SBBYS variant", "0060290", "0011365" ], [ "Q8WYB5-1", "protein_xref_omim", "606170", "Genitopatellar syndrome", "", "0011640" ], [ "Q14566-1", "protein_xref_omim", "223100", "", "10604", "0009116" ], [ "O60741-1", "protein_xref_omim", "615871", "Epileptic encephalopathy, early infantile, 24", "0080429", "0014377" ], [ "O60741-1", "protein_xref_omim", "618482", "Generalized epilepsy with febrile seizures plus 10", "0111296", "" ], [ "Q9UHF7-1", "protein_xref_omim", "150230", "Tricho-rhino-phalangeal syndrome 2", "4998", "0007874" ], [ "Q9UHF7-1", "protein_xref_omim", "190350", "Tricho-rhino-phalangeal syndrome 1", "14743", "0008596" ], [ "Q9UHF7-1", "protein_xref_omim", "190351", "Tricho-rhino-phalangeal syndrome 3", "0080376", "0008597" ], [ "Q9UHC6-1", "protein_xref_omim", "610042", "Pitt-Hopkins-like syndrome 1", "0090130", "0012400" ], [ "Q9UHC6-1", "protein_xref_omim", "612100", "Autism 15", "", "0012801" ], [ "P41212-1", "protein_xref_omim", "601626", "Leukemia, acute myelogenous", "9119", "0018874" ], [ "P41212-1", "protein_xref_omim", "131440", "Myeloproliferative disorder chronic with eosinophilia", "0111344", "0007546" ] ] }, "readme": "Name\n - Human Protein Diseases\n\nVersion\n - 1.7.13\n\nCreated on\n - 2019-01-23T17:21:05.953432\n\nModified on\n - 2020-04-10T11:29:36.357255\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 Protein Diseases dataset contains list of human [taxid:9606] diseases from OMIM, MONDO and Genomics England databases mapped to the UniProtKB protein canonical accessions and Disease Ontology (DO) identifiers..\n - Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.\n - The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.\n - Genomics England is a company set up and owned by the Department of Health and Social Care to run the 100,000 Genomes Project, which aims to sequence 100,000 genomes from NHS patients with a rare disease and their families, and patients with cancer.\n - If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, Genomics England, EMBL-EBI-UniProt and GlyGen\n\nDescription Domain\n Keywords\n - disease\n - HPO\n - OMIM\n - Genomics England PanelApp\n - Monarch Initiative\n - MONDO\n - DO\n\n Pipeline Steps\n - Step-1: The script extracts the OMIM phenotypes for UniProtKB accessions and MONDO disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv and Genomics England disease data from . The script maps the UniProtKB accessions to the UniprotKB canonical accessions.\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.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: uniprot-proteome-homo-sapiens.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_glyco_disease.csv\n URI: https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Name: human_protein_genomics_england_disease.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.csv\n Name: protein_domap.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv\n Output Subdomain\n Name: human_protein_disease.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.csv\n Name: human_protein_disease.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.stat.csv\n\nFields\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"3532\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"4074\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"5662\"\n Name: \"database_label\"\n Description: \"Label or name assigned to the corresponding identifier in the source database\"\n Unique Values: \"5475\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"3\"\n Name: \"mondo_id\"\n Description: \"The Mondo Disease Ontology (MONDO) identifier\"\n Unique Values: \"5145\"", "downloadurl": "/ln2data/releases/data/v-1.7.13/reviewed/human_protein_disease.csv" }