{ "bcoid": "GLY_000221", "title": "Glycosylation sites - UniCarbKB [Rat proteins]", "description": "List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if ...", "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv", "filetype": "csv", "categories": { "status": "Reviewed", "molecule": "Proteoform", "species": "Rattus norvegicus", "tags": "UniCarbKB glycosylation sites", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "P32736-1...", "285..." ], [ "P32736-1...", "70..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "evidence" }, { "type": "string", "label": "unicarbkb_id" }, { "type": "string", "label": "glytoucan_ac" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "curation_notes" }, { "type": "string", "label": "additonal_notes" }, { "type": "string", "label": "composition" } ], [ "P32736-1", "285", "18729387", "7535", "G54652ZD", "Asn", "n-linked", "", "", "" ], [ "P32736-1", "70", "18729387", "7592", "G43947VZ", "Asn", "n-linked", "", "", "" ], [ "P32736-1", "293", "18729387", "7733", "G70258ML", "Asn", "n-linked", "", "", "" ], [ "P32736-1", "44", "18729387", "7874", "G76285RN", "Asn", "n-linked", "", "", "" ], [ "Q62718-1", "284", "18729387", "7621", "G35952BG", "Asn", "n-linked", "", "", "" ], [ "Q62718-1", "305", "18729387", "7465", "G12150CK", "Asn", "n-linked", "", "", "" ], [ "Q62718-1", "292", "18729387", "7733", "G70258ML", "Asn", "n-linked", "", "", "" ], [ "Q62718-1", "70", "18729387", "7592", "G43947VZ", "Asn", "n-linked", "", "", "" ], [ "Q62718-1", "44", "18729387", "7874", "G76285RN", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "66", "18729387", "7592", "G43947VZ", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "279", "18729387", "7676", "", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "287", "18729387", "7641", "G92129PT", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "300", "18729387", "7601", "G10898KH", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "40", "18729387", "7420", "G42081JA", "Asn", "n-linked", "", "", "" ], [ "Q62813-1", "136", "18729387", "7601", "G10898KH", "Asn", "n-linked", "", "", "" ], [ "Q9Z0J8-1", "67", "18729387", "7779", "G25386IJ", "Asn", "n-linked", "", "", "" ], [ "Q9Z0J8-1", "149", "18729387", "7641", "G92129PT", "Asn", "n-linked", "", "", "" ], [ "Q9Z0J8-1", "288", "18729387", "7527", "G03802LT", "Asn", "n-linked", "", "", "" ], [ "Q9Z0J8-1", "269", "18729387", "7875", "G51623PN", "Asn", "n-linked", "", "", "" ], [ "Q9Z0J8-1", "280", "18729387", "7847", "G08712ES", "Asn", "n-linked", "", "", "" ], [ "P35439-1", "440", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "440", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "440", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "368", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "368", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "368", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex8dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "368", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "368", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "771", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex8dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "771", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "771", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "771", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "350", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "350", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "350", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "350", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex8dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "203", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P35439-1", "203", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc6Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc6Hex4dHex3NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex4dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex3NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex6dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc6Hex5dHex3NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex9dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex4dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex6dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex2NeuAc0NeuGc1Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex1dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex5dHex3NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex6dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex2NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc6Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex5dHex2NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc3Hex6dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "Q63345-1", "58", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex8dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex3dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc6Hex4dHex3NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc5Hex4dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ], [ "P97546-2", "228", "24090084", "", "", "Asn", "n-linked", "", "", "comp_HexNAc4Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0" ] ] }, "readme": "Name\n - Glycosylation sites - UniCarbKB [Rat proteins]\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-09-05T14:34:59.005886\n\nModified on\n - 2019-09-12T12:46:30.503606\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu], Xavier Holmes [xavierh@gwu.edu]\n\nAuthors\n - Matthew Campbell [m.campbell2@griffith.edu.au], Nathan Edwards [Georgetown University]\n\nChecksum\n - \n\nUsability Domain\n - List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000244).\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - glycan\n - UniCarbKB\n - GlyTouCan\n\n Pipeline Steps\n - Step-0: The input file (rat_2019_07_16_05_30_14.csv ;for script:rat_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (rat_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The script additionally implements 10 QC checks. Any row that falls for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (rat_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. \n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-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: rat_2019_07_16_05_30_14.csv\n URI: https://data.glygen.org/ln2wwwdata/source/rat_2019_07_16_05_30_14.csv\n Name: rat_protein_idmapping.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv\n Name: classification.tsv\n URI: https://data.glygen.org/ln2wwwdata/source/classification.tsv\n Name: glycan_properties.tsv\n URI: https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv\n Name: rat_protein_allsequences.fasta\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta\n Name: aadict.csv\n URI: https://data.glygen.org/ln2wwwdata/source/aadict.csv\n Output Subdomain\n Name: rat_proteoform_glycosylation_sites_unicarbkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n Name: rat_proteoform_glycosylation_sites_unicarbkb.1.log\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n Name: rat_proteoform_glycosylation_sites_unicarbkb.2.log\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n Name: rat_proteoform_glycosylation_sites_unicarbkb.stats.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n Name: rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n\nFields\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: \"140\"\n Name: \"unicarbkb_id\"\n Description: \"\"\n Unique Values: \"83\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"213\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"1\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"1\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"6\"\n Name: \"additonal_notes\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"92\"\n Name: \"glytoucan_ac\"\n Description: \"\"\n Unique Values: \"73\"\n Name: \"curation_notes\"\n Description: \"\"\n Unique Values: \"254\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv" }