{ "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...", "omim..." ], [ "P30613-1...", "omim..." ] ], "headers": [ "uniprotkb_ca...", "database_nam..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "database_name" }, { "type": "string", "label": "database_id" }, { "type": "string", "label": "database_label" }, { "type": "string", "label": "do_id" } ], [ "P30613-1", "omim", "102900", "Pyruvate kinase hyperactivity", "" ], [ "P30613-1", "omim", "266200", "Pyruvate kinase deficiency of red cells", "0111077" ], [ "P20930-1", "omim", "146700", "Ichthyosis vulgaris", "1702" ], [ "P20930-1", "omim", "605803", "Dermatitis atopic 2", "0110098" ], [ "P20933-1", "mondo", "0008830", "Aspartylglucosaminuria", "0050461" ], [ "P20933-1", "omim", "208400", "Aspartylglucosaminuria", "0050461" ], [ "P20936-1", "omim", "608354", "Capillary malformation-arteriovenous malformation 1", "" ], [ "Q8NHX9-1", "omim", "612267", "", "" ], [ "Q9NXR8-1", "omim", "275355", "Squamous cell carcinoma of the head and neck", "5520" ], [ "Q9NXR1-2", "omim", "605013", "Microhydranencephaly", "" ], [ "Q9NXR1-2", "omim", "614019", "Lissencephaly 4", "0050453" ], [ "Q96J66-1", "omim", "117800", "", "" ], [ "Q13835-1", "omim", "604536", "Ectodermal dysplasia-skin fragility syndrome", "" ], [ "P40424-1", "omim", "617641", "Congenital anomalies of kidney and urinary tract syndrome with or without hearing loss, abnormal ears, or developmental delay", "" ], [ "P09001-1", "omim", "614582", "Combined oxidative phosphorylation deficiency 9", "0111472" ], [ "Q8WTV0-1", "omim", "610762", "", "" ], [ "Q9H2I8-1", "omim", "615179", "Albinism, oculocutaneous, 7", "0070100" ], [ "P08842-1", "omim", "308100", "Ichthyosis, X-linked", "1700" ], [ "P03891-1", "omim", "502500", "Alzheimer disease mitochondrial", "" ], [ "P03891-1", "omim", "535000", "Leber hereditary optic neuropathy", "705" ], [ "P03897-1", "omim", "256000", "Leigh syndrome", "3652" ], [ "P03897-1", "omim", "500014", "Mitochondrial complex I deficiency, mitochondrial type 1", "" ], [ "P02768-1", "omim", "615999", "Hyperthyroxinemia, familial dysalbuminemic", "" ], [ "P02768-1", "omim", "616000", "Analbuminemia", "" ], [ "P08559-1", "omim", "312170", "Pyruvate dehydrogenase E1-alpha deficiency", "3649" ], [ "P02765-1", "omim", "203650", "Alopecia-mental retardation syndrome 1", "" ], [ "P02766-1", "omim", "105210", "Amyloidosis, transthyretin-related", "0050638" ], [ "P02766-1", "omim", "115430", "Carpal tunnel syndrome 1", "12169" ], [ "P02766-1", "omim", "145680", "Hyperthyroxinemia, dystransthyretinemic", "0080219" ], [ "Q9UJ71-1", "omim", "613393", "Birbeck granule deficiency", "" ], [ "P35579-1", "omim", "155100", "Macrothrombocytopenia and granulocyte inclusions with or without nephritis or sensorineural hearing loss", "0060651" ], [ "P35579-1", "omim", "603622", "Deafness, autosomal dominant, 17", "0110548" ], [ "Q8N1G0-1", "omim", "616833", "Paget disease of bone 6", "" ], [ "O15259-1", "omim", "256100", "Nephronophthisis 1", "12712" ], [ "O15259-1", "omim", "266900", "Senior-Loken syndrome 1", "0050576" ], [ "O15259-1", "omim", "609583", "Joubert syndrome 4", "0110999" ], [ "P41180-1", "omim", "145980", "Hypocalciuric hypercalcemia, familial 1", "0060699" ], [ "P41180-1", "omim", "239200", "Hyperparathyroidism, neonatal severe", "" ], [ "P41180-1", "omim", "601198", "Hypocalcemia, autosomal dominant 1", "0090107" ], [ "P41180-1", "omim", "612899", "Epilepsy, idiopathic generalized 8", "0111322" ], [ "Q86XA0-1", "omim", "615942", "Mental retardation, autosomal recessive 44", "0060308" ], [ "P29401-1", "omim", "617044", "Short stature, developmental delay, and congenital heart defects", "" ], [ "P41181-1", "omim", "125800", "Diabetes insipidus, nephrogenic, autosomal", "12387" ], [ "O00330-1", "omim", "245349", "Pyruvate dehydrogenase E3-binding protein deficiency", "3649" ], [ "Q7RTW8-1", "omim", "607039", "Deafness, autosomal recessive, 22", "0110480" ], [ "P12074-1", "omim", "616039", "Charcot-Marie-Tooth disease, recessive, intermediate type, D", "0110203" ], [ "Q9P219-1", "omim", "236600", "Hydrocephalus, congenital, 1", "10908" ], [ "Q9P219-1", "omim", "616053", "Spinocerebellar ataxia 40", "0050986" ], [ "Q9UK17-1", "omim", "607346", "Spinocerebellar ataxia 19", "0050970" ], [ "Q9UK17-1", "omim", "616399", "Brugada syndrome 9", "0110226" ], [ "Q9P212-1", "omim", "610725", "Nephrotic syndrome 3", "0080382" ], [ "Q92838-1", "omim", "305100", "Ectodermal dysplasia 1, hypohidrotic, X-linked", "14793" ], [ "Q92838-1", "omim", "313500", "Tooth agenesis, selective, X-linked, 1", "0050591" ], [ "Q9H845-1", "omim", "611126", "Mitochondrial complex I deficiency, nuclear type 20", "" ], [ "Q9BZG2-1", "omim", "617297", "Amelogenesis imperfecta 1J", "" ], [ "O43933-1", "omim", "214100", "Peroxisome biogenesis disorder 1A", "0080377" ], [ "O43933-1", "omim", "234580", "Heimler syndrome 1", "" ], [ "O43933-1", "omim", "601539", "Peroxisome biogenesis disorder 1B", "" ], [ "Q9BZG8-1", "omim", "616901", "Developmental delay with short stature, dysmorphic features, and sparse hair", "" ], [ "Q9Y592-1", "omim", "615862", "Nephronophthisis 18", "0111125" ], [ "P19099-1", "omim", "103900", "Hyperaldosteronism, familial, 1", "14080" ], [ "P19099-1", "omim", "203400", "Corticosterone methyloxidase 1 deficiency", "" ], [ "P19099-1", "omim", "610600", "Corticosterone methyloxidase 2 deficiency", "" ], [ "P53708-1", "omim", "191830", "Renal hypodysplasia/aplasia 1", "14766" ], [ "Q14563-1", "omim", "614897", "Hypogonadotropic hypogonadism 16 with or without anosmia", "0090080" ], [ "Q8WYB5-1", "omim", "603736", "Ohdo syndrome, SBBYS variant", "0060290" ], [ "Q8WYB5-1", "omim", "606170", "Genitopatellar syndrome", "" ], [ "Q14566-1", "omim", "223100", "", "10604" ], [ "O60741-1", "omim", "615871", "Epileptic encephalopathy, early infantile, 24", "0080429" ], [ "Q9UHF7-1", "omim", "150230", "Tricho-rhino-phalangeal syndrome 2", "4998" ], [ "Q9UHF7-1", "omim", "190350", "Tricho-rhino-phalangeal syndrome 1", "14743" ], [ "Q9UHF7-1", "omim", "190351", "Tricho-rhino-phalangeal syndrome 3", "0080376" ], [ "Q9UHC6-1", "omim", "610042", "Pitt-Hopkins-like syndrome 1", "0090130" ], [ "Q9UHC6-1", "omim", "612100", "Autism 15", "" ], [ "P41212-1", "omim", "601626", "Leukemia, acute myelogenous", "9119" ], [ "P41212-1", "omim", "131440", "Myeloproliferative disorder chronic with eosinophilia", "0111344" ], [ "P41212-1", "omim", "616216", "Thrombocytopenia 5", "" ], [ "Q92597-1", "omim", "601455", "Charcot-Marie-Tooth disease 4D", "0110186" ], [ "Q9BQP7-1", "omim", "615084", "Mitochondrial DNA depletion syndrome 11", "0080129" ], [ "P40200-1", "omim", "211750", "C syndrome", "0111581" ], [ "P27448-5", "omim", "618283", "Visual impairment and progressive phthisis bulbi", "" ], [ "P07202-1", "omim", "274500", "Thyroid dyshormonogenesis 2A", "" ], [ "P07204-1", "omim", "612926", "Hemolytic uremic syndrome atypical 6", "" ], [ "P07204-1", "omim", "614486", "Thrombophilia due to thrombomodulin defect", "2452" ] ] }, "readme": "Name\n - Human Protein Diseases\n\nVersion\n - 1.5.18\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/ln2data/releases/data/v-1.5.18/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_glyco_disease.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.18/compiled/human_protein_glyco_disease.csv\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.18/reviewed/human_protein_masterlist.csv\n Name: human_protein_genomics_england_disease.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.18/reviewed/human_protein_genomics_england_disease.csv\n Name: protein_domap.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.18/reviewed/protein_domap.csv\n Output Subdomain\n Name: human_protein_disease.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.18/reviewed/human_protein_disease.csv\n Name: human_protein_disease.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.18/reviewed/human_protein_disease.stat.csv\n\nFields\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"3156\"\n Name: \"database_id\"\n Description: \"Identifier in the database\"\n Unique Values: \"5628\"\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: \"4053\"\n Name: \"database_label\"\n Description: \"Label or name assigned to the corresponding identifier in the source database\"\n Unique Values: \"5447\"\n Name: \"database_name\"\n Description: \"The name of the source database\"\n Unique Values: \"3\"", "downloadurl": "/ln2data/releases/data/v-1.5.18/reviewed/human_protein_disease.csv" }