{ "bcoid": "GLY_000529", "title": "Human Protein Diseases (GlyCosmos)", "description": "The file contain disease data associated to protein/gene downloaded from GlyCosmos database. [https://glycosmos.org/homes/download]. ...", "filename": "human_protein_disease_glycosmos.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Disease GlyCosmos", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q9H553-1...", "protein_xref..." ], [ "P51688-1...", "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": "do_id" }, { "type": "string", "label": "mondo_id" }, { "type": "string", "label": "mim_id" }, { "type": "string", "label": "ggd_id" }, { "type": "string", "label": "ggd_name" } ], [ "Q9H553-1", "protein_xref_glycosmos_disease", "85365", "0080561", "0011933", "607906", "CON00351", "CDG1I" ], [ "P51688-1", "protein_xref_glycosmos_disease", "6448", "0111395", "0009655", "252900", "CON00034", "MUCOPOLYSACCHARIDOSIS TYPE IIIA" ], [ "P22304-1", "protein_xref_glycosmos_disease", "3423", "12799", "0010674", "309900", "CON00032", "MUCOPOLYSACCHARIDOSIS TYPE II" ], [ "P39656-1", "protein_xref_glycosmos_disease", "1650", "0080569", "0013789", "614507", "CON00623", "CDG1R" ], [ "Q11203-1", "protein_xref_glycosmos_disease", "6487", "0060308", "0012612", "611090", "CON00630", "MRT12" ], [ "Q96A29-1", "protein_xref_glycosmos_disease", "55343", "0070255", "0009953", "266265", "CON00360", "CDG2C" ], [ "P83436-1", "protein_xref_glycosmos_disease", "91949", "0070257", "0012118", "608779", "CON00362", "CDG2E" ], [ "Q14435-1", "protein_xref_glycosmos_disease", "2591", "0111063", "0008897", "211900", "CON00402", "HFTC" ], [ "Q96EU7-1", "protein_xref_glycosmos_disease", "29071", "0080520", "0010381", "300622", "CON00401", "TNPS" ], [ "Q9BVK2-1", "protein_xref_glycosmos_disease", "79053", "0080560", "0011969", "608104", "CON00350", "CDG1H" ], [ "Q13724-1", "protein_xref_glycosmos_disease", "7841", "0070254", "0011629", "606056", "CON00359", "CDG2B" ], [ "P78382-1", "protein_xref_glycosmos_disease", "10559", "0070258", "0011342", "603585", "CON00363", "CDG2F" ], [ "Q13454-1", "protein_xref_glycosmos_disease", "7991", "0060308", "0012615", "611093", "CON00369", "MRT7" ], [ "Q10469-1", "protein_xref_glycosmos_disease", "4247", "0070253", "0008908", "212066", "CON00358", "CDG2A" ], [ "Q10469-1", "protein_xref_glycosmos_disease", "4247", "0050571", "0008908", "212066", "CON00358", "CDG2A" ], [ "O60762-1", "protein_xref_glycosmos_disease", "8813", "0080557", "0012123", "608799", "CON00347", "CDG1E" ], [ "Q9H3H5-1", "protein_xref_glycosmos_disease", "1798", "0080562", "0011964", "608093", "CON00352", "CDG1J" ], [ "Q9H3S5-1", "protein_xref_glycosmos_disease", "93183", "", "0012465", "610293", "CON00415", "GLYCOSYLPHOSPHATIDYLINOSITOL DEFICIENCY" ], [ "Q9BV10-1", "protein_xref_glycosmos_disease", "79087", "0080559", "0011783", "607143", "CON00349", "CDG1G" ], [ "P07602-1", "protein_xref_glycosmos_disease", "5660", "10581", "0009590", "249900", "CON00084", "METACHROMATIC LEUKODYSTROPHY DUE TO SAPOSIN B DEFICIENCY" ], [ "P15848-1", "protein_xref_glycosmos_disease", "411", "12800", "0009661", "253200", "CON00041", "MUCOPOLYSACCHARIDOSIS TYPE VI" ], [ "P50443-1", "protein_xref_glycosmos_disease", "1836", "14687", "0009107", "222600", "CON00395", "DIASTROPHIC DYSPLASIA" ], [ "P50443-1", "protein_xref_glycosmos_disease", "1836", "0080055", "0010966", "600972", "CON00396", "ACG1B" ], [ "P50443-1", "protein_xref_glycosmos_disease", "1836", "0050648", "0009727", "256050", "CON00397", "AOII" ], [ "P50443-1", "protein_xref_glycosmos_disease", "1836", "0070300", "0009189", "226900", "CON00398", "EDM4" ], [ "Q9H9E3-1", "protein_xref_glycosmos_disease", "25839", "0070262", "0013281", "613489", "CON00367", "CDG2J" ], [ "P07686-1", "protein_xref_glycosmos_disease", "3074", "3323", "0010006", "268800", "CON00058", "GM2\u30ac\u30f3\u30b0\u30ea\u30aa\u30b7\u30c9\u30fc\u30b7\u30b9O\u578b@ja, SANDHOFF DISEASE" ], [ "P07686-1", "protein_xref_glycosmos_disease", "3074", "3323", "0010006", "268800", "CON00059", "" ], [ "O94766-1", "protein_xref_glycosmos_disease", "26229", "0080575", "0009511", "245600", "CON00631", "MULTIPLE JOINT DISLOCATIONS, SHORT STATURE, CRANIOFACIAL DYSMORPHISM, AND CONGENITAL HEART DEFECTS" ], [ "O75352-1", "protein_xref_glycosmos_disease", "9526", "0080558", "0012211", "609180", "CON00348", "CDG1F" ], [ "Q9NP73-1", "protein_xref_glycosmos_disease", "79868", "0080470", "0010472", "300884", "CON00624", "CDG1S" ], [ "P35475-1", "protein_xref_glycosmos_disease", "3425", "0111389", "0011759", "607015", "CON00030", "HURLER-SCHEIE SYNDROME" ], [ "P35475-1", "protein_xref_glycosmos_disease", "3425", "0111390", "0011758", "607014", "CON00029", "HURLER SYNDROME" ], [ "P35475-1", "protein_xref_glycosmos_disease", "3425", "12798", "0011758", "607014", "CON00029", "HURLER SYNDROME" ], [ "P35475-1", "protein_xref_glycosmos_disease", "3425", "0060222", "0011760", "607016", "CON00031", "SCHEIE SYNDROME" ], [ "P11532-1", "protein_xref_glycosmos_disease", "1756", "11723", "0010679", "310200", "CON00384", "DMD" ], [ "Q9UNP4-1", "protein_xref_glycosmos_disease", "8869", "0060470", "0012189", "609056", "CON00412", "AMISH INFANTILE EPILEPSY SYNDROME" ], [ "Q9H8P0-1", "protein_xref_glycosmos_disease", "79644", "0080568", "0012885", "612379", "CON00622", "CDG1Q" ], [ "P37287-1", "protein_xref_glycosmos_disease", "5277", "0060284", "0010438", "300818", "CON00414", "PNH1" ], [ "Q96MW5-1", "protein_xref_glycosmos_disease", "84342", "0070260", "0012635", "611182", "CON00365", "CDG2H" ], [ "Q9NUD9-1", "protein_xref_glycosmos_disease", "55650", "", "0009398", "239300", "CON00635", "HPMRS1" ], [ "Q86X52-1", "protein_xref_glycosmos_disease", "22856", "0050814", "0011533", "605282", "CON00632", "TPBS" ], [ "Q06210-1", "protein_xref_glycosmos_disease", "2673", "0110660", "0012518", "610542", "CON00628", "CMSTA1" ], [ "Q9Y487-1", "protein_xref_glycosmos_disease", "23545", "0070134", "0009054", "219200", "CON00371", "ARCL2A" ], [ "Q02809-1", "protein_xref_glycosmos_disease", "5351", "0080734", "0016002", "225400", "CON00407", "EDS6" ], [ "P06865-1", "protein_xref_glycosmos_disease", "3073", "3320", "0010100", "272800", "CON00055", "TSD" ], [ "P06865-1", "protein_xref_glycosmos_disease", "3073", "3320", "0010100", "272800", "CON00056", "" ], [ "O95461-1", "protein_xref_glycosmos_disease", "9215", "0110637", "0012138", "608840", "CON00383", "MDDGB6" ], [ "O95340-1", "protein_xref_glycosmos_disease", "9060", "0050812", "0013019", "612847", "CON00393", "BRACHYOLMIA TYPE 4 WITH MILD EPIPHYSEAL AND METAPHYSEAL CHANGES" ], [ "P15586-1", "protein_xref_glycosmos_disease", "2799", "0111402", "0009658", "252940", "CON00037", "MUCOPOLYSACCHARIDOSIS TYPE IIID" ], [ "Q9UPQ8-1", "protein_xref_glycosmos_disease", "22845", "0080565", "0012556", "610768", "CON00355", "CDG1M" ], [ "Q8NES3-1", "protein_xref_glycosmos_disease", "3955", "0050568", "0012349", "609813", "CON00405", "SCDO3" ], [ "P16278-1", "protein_xref_glycosmos_disease", "2720", "0111392", "0009660", "253010", "CON00040", "MUCOPOLYSACCHARIDOSIS TYPE IVB" ], [ "P16278-1", "protein_xref_glycosmos_disease", "2720", "0080502", "0009260", "230500", "CON00051", "GM1-GANGLIOSIDOSIS, TYPE I" ], [ "P16278-1", "protein_xref_glycosmos_disease", "2720", "0080501", "0009261", "230600", "CON00052", "GM1-GANGLIOSIDOSIS, TYPE II" ], [ "P16278-1", "protein_xref_glycosmos_disease", "2720", "0080489", "0009262", "230650", "CON00053", "GM1-GANGLIOSIDOSIS, TYPE III" ], [ "Q8WZA1-1", "protein_xref_glycosmos_disease", "55624", "0111236", "0009667", "253280", "CON00377", "MDDGA3" ], [ "Q2TAA5-1", "protein_xref_glycosmos_disease", "440138", "0080567", "0013349", "613661", "CON00621", "CDG1P" ], [ "Q9Y672-1", "protein_xref_glycosmos_disease", "29929", "0080555", "0011291", "603147", "CON00345", "CDG1C" ], [ "Q92685-1", "protein_xref_glycosmos_disease", "10195", "0080556", "0010998", "601110", "CON00346", "CDG1D" ], [ "O00469-1", "protein_xref_glycosmos_disease", "5352", "0060231", "0012217", "609220", "CON00408", "BRKS2" ], [ "Q9Y223-1", "protein_xref_glycosmos_disease", "10020", "", "", "600737", "CON00385", "IBM2" ], [ "Q9Y223-1", "protein_xref_glycosmos_disease", "10020", "0080718", "0011603", "605820", "CON00386", "NM" ], [ "P04066-1", "protein_xref_glycosmos_disease", "2517", "14500", "0009254", "230000", "CON00006", "FUCOSIDOSIS" ], [ "Q6Y288-1", "protein_xref_glycosmos_disease", "145173", "0080201", "0009856", "261540", "CON00404", "PETERS-PLUS SYNDROME" ], [ "P36871-1", "protein_xref_glycosmos_disease", "5236", "0080570", "0013968", "614921", "CON00625", "CDG1T" ], [ "Q9UKM7-1", "protein_xref_glycosmos_disease", "11253", "0050889", "0013624", "614202", "CON00629", "MRT15" ], [ "Q8WTW3-1", "protein_xref_glycosmos_disease", "9382", "0070259", "0012637", "611209", "CON00364", "CDG2G" ], [ "Q9GZX3-1", "protein_xref_glycosmos_disease", "4166", "2565", "0009020", "217800", "CON00391", "MCDC1" ], [ "Q9NTN3-1", "protein_xref_glycosmos_disease", "23169", "0050775", "0010013", "269250", "CON00399", "SCHNECKENBECKEN DYSPLASIA" ], [ "Q9H9S5-1", "protein_xref_glycosmos_disease", "79147", "0110635", "0011688", "606612", "CON00381", "MDDGB5" ], [ "Q9H9S5-1", "protein_xref_glycosmos_disease", "79147", "0110299", "0011787", "607155", "CON00382", "MDDGC5" ], [ "O60568-1", "protein_xref_glycosmos_disease", "8985", "", "0012892", "612394", "CON00409", "BONE FRAGILITY WITH CONTRACTURES, ARTERIAL RUPTURE, AND DEAFNESS" ], [ "P34949-1", "protein_xref_glycosmos_disease", "4351", "0080554", "0011257", "602579", "CON00344", "CDG1B" ], [ "P15289-1", "protein_xref_glycosmos_disease", "410", "10581", "0009591", "250100", "CON00080", "METACHROMATIC LEUKODYSTROPHY" ], [ "P54803-1", "protein_xref_glycosmos_disease", "2581", "10587", "0009499", "245200", "CON00073", "KRABBE DISEASE" ], [ "Q9UBV7-1", "protein_xref_glycosmos_disease", "11285", "0080738", "0020682", "130070", "CON00388", "EDSP1" ], [ "Q9H6U8-1", "protein_xref_glycosmos_disease", "79796", "0080564", "0012117", "608776", "CON00354", "CDG1L" ], [ "Q9P2X0-1", "protein_xref_glycosmos_disease", "54344", "", "0013049", "612937", "CON00620", "CDG1O" ], [ "O95427-1", "protein_xref_glycosmos_disease", "23556", "0080503", "0013563", "614080", "CON00636", "MCAHS1" ], [ "O95427-1", "protein_xref_glycosmos_disease", "23556", "0080138", "0013563", "614080", "CON00636", "MCAHS1" ], [ "O75072-1", "protein_xref_glycosmos_disease", "2218", "0050559", "0009678", "253800", "CON00378", "MDDGA4" ], [ "O75072-1", "protein_xref_glycosmos_disease", "2218", "0110296", "0012699", "611588", "CON00379", "MDDGC4" ], [ "O75072-1", "protein_xref_glycosmos_disease", "2218", "0110444", "0012704", "611615", "CON00380", "CMD1X" ] ] }, "readme": "Name\n - Human Protein Diseases (GlyCosmos)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-09-24T13:34:03.947890\n\nModified on\n - 2022-01-18T12:24:09.466735\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.gwu.edu]\n\nAuthors\n - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The file contain disease data associated to protein/gene downloaded from GlyCosmos database. [https://glycosmos.org/homes/download]. \n\nDescription Domain\n Keywords\n - Gene\n - Protein\n - Disease\n - GlyCosmos\n\n Pipeline Steps\n - Step-0: The file is downloaded from the GlyCosmos database directly. The following steps are done to generate the final output file: 1. Mapping gene_id to UniProtKB accession from input file 1 2) Map the dd_uri to mim_id and disease name from input file 2 3) Map mim_id to doid and mongo ids using input file 3. \n\nExecution Domain\n Scripts - \n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/\n\nI/O Domain\n Input Subdomain\n Name: glycosmos_gdgdb.csv\n URI: https:/data.glygen.org/ln2downloads/glycosmos/04_08_2021/glycosmos_gdgdb.csv\n Name: human_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/human_protein_xref_geneid.csv\n Name: ggdonto.ttl\n URI: https:/data.glygen.org/ln2downloads/glycosmos/04_08_2021/graph-1/ggdonto.ttl\n Name: protein_disease_idmap.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/protein_disease_idmap.csv\n Output Subdomain\n Name: human_protein_disease_glycosmos.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/human_protein_disease_glycosmos.csv\n Name: human_protein_disease_glycosmos.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/human_protein_disease_glycosmos.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"80\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"80\"\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"91\"\n Name: \"mondo_id\"\n Description: \"The Mondo Disease Ontology (MONDO) identifier\"\n Unique Values: \"93\"\n Name: \"mim_id\"\n Description: \"Disease ID from the OMIM database\"\n Unique Values: \"93\"\n Name: \"ggd_id\"\n Description: \"\"\n Unique Values: \"95\"\n Name: \"ggd_name\"\n Description: \"\"\n Unique Values: \"93\"", "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/human_protein_disease_glycosmos.csv" }