{ "bcoid": "GLY_000329", "title": "Human Glycosylation Sites (GlyConnect) ", "description": "The Human Glycosylation Sites (GlyConnect) dataset contains human [taxid:9606] UniProtKB canonical accessions ...", "filename": "human_proteoform_glycosylation_sites_glyconnect.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P14780-1...", "120..." ], [ "P14780-1...", "120..." ] ], "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": "amino_acid" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "composition" }, { "type": "string", "label": "glyconnect_protein_id" }, { "type": "string", "label": "glyconnect_id" }, { "type": "string", "label": "is_composition_only" }, { "type": "string", "label": "glycan_core" }, { "type": "string", "label": "glytoucan_ac_composition" } ], [ "P14780-1", "120", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "6", "1021", "", "Undefined core", "G48414YA" ], [ "P14780-1", "120", "Asn", "", "N-Linked", "6", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "6", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "103", "Asn", "G40906DZ", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "3444", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G40906DZ", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "3444", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G88382QE", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "111", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G88382QE", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "111", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G40906DZ", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "3444", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G40906DZ", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "3444", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G98559XP", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "2606", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G98559XP", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "2606", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G88382QE", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "111", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G88382QE", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "111", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G98559XP", "N-Linked", "7240157", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1", "14", "2606", "", "Complex", "G90093AU" ], [ "P19652-1", "103", "Asn", "G98559XP", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1", "14", "2606", "", "Complex", "G90093AU" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:5 HexNAc:4", "14", "1478", "", "Undefined core", "G50045TK" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4", "14", "1478", "", "Undefined core", "G50045TK" ], [ "P19652-1", "33", "Asn", "G22140GZ", "N-Linked", "19838169", "protein_xref_pubmed", "Hex:5 HexNAc:4", "14", "3471", "", "Complex", "G50045TK" ], [ "P19652-1", "33", "Asn", "G22140GZ", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4", "14", "3471", "", "Complex", "G50045TK" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:8 HexNAc:2", "14", "3206", "", "Undefined core", "G64527OM" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:8 HexNAc:2", "14", "3206", "", "Undefined core", "G64527OM" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:9 HexNAc:2", "14", "1710", "", "Undefined core", "G70101JE" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:9 HexNAc:2", "14", "1710", "", "Undefined core", "G70101JE" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "33", "Asn", "G36131WL", "N-Linked", "19838169", "protein_xref_pubmed", "Hex:6 HexNAc:5", "14", "644", "", "Complex", "G20425TQ" ], [ "P19652-1", "33", "Asn", "G36131WL", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5", "14", "644", "", "Complex", "G20425TQ" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "19838169", "protein_xref_pubmed", "Hex:6 HexNAc:5 dHex:1", "14", "3534", "", "Complex", "G72797UR" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 dHex:1", "14", "3534", "", "Complex", "G72797UR" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:1", "14", "736", "", "Undefined core", "G59536GA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:1", "14", "736", "", "Undefined core", "G59536GA" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 dHex:1 NeuAc:1", "14", "356", "", "Undefined core", "G81263BG" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 dHex:1 NeuAc:1", "14", "356", "", "Undefined core", "G81263BG" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:2", "14", "857", "", "Undefined core", "G52527GH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:2", "14", "857", "", "Undefined core", "G52527GH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:2", "14", "857", "", "Undefined core", "G52527GH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:2", "14", "857", "", "Undefined core", "G52527GH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:7 HexNAc:6 NeuAc:1", "14", "8486", "", "Undefined core", "G41882MT" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 NeuAc:1", "14", "8486", "", "Undefined core", "G41882MT" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 dHex:1 NeuAc:2", "14", "2610", "", "Undefined core", "G11629QQ" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 dHex:1 NeuAc:2", "14", "2610", "", "Undefined core", "G11629QQ" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:3", "14", "308", "", "Undefined core", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:3", "14", "308", "", "Undefined core", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "24530628", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:3", "14", "251", "", "Complex", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:3", "14", "251", "", "Complex", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 NeuAc:3", "14", "308", "", "Undefined core", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 NeuAc:3", "14", "308", "", "Undefined core", "G47518TP" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:6 HexNAc:5 dHex:1 NeuAc:3", "14", "94", "", "Undefined core", "G15169WU" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5 dHex:1 NeuAc:3", "14", "94", "", "Undefined core", "G15169WU" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1 NeuAc:2", "14", "357", "", "Undefined core", "G64394MX" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1 NeuAc:2", "14", "357", "", "Undefined core", "G64394MX" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:7 HexNAc:6 NeuAc:3", "14", "95", "", "Undefined core", "G12793SR" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 NeuAc:3", "14", "95", "", "Undefined core", "G12793SR" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:7 HexNAc:6 dHex:1 NeuAc:3", "14", "1533", "", "Undefined core", "G39595FH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 dHex:1 NeuAc:3", "14", "1533", "", "Undefined core", "G39595FH" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:7 HexNAc:6 NeuAc:4", "14", "898", "", "Undefined core", "G66088HZ" ], [ "P19652-1", "33", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:7 HexNAc:6 NeuAc:4", "14", "898", "", "Undefined core", "G66088HZ" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:8 HexNAc:2", "14", "3206", "", "Undefined core", "G64527OM" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:8 HexNAc:2", "14", "3206", "", "Undefined core", "G64527OM" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:4 HexNAc:6 dHex:2", "14", "8489", "", "Undefined core", "G11911BT" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:4 HexNAc:6 dHex:2", "14", "8489", "", "Undefined core", "G11911BT" ], [ "P19652-1", "56", "Asn", "G42358LZ", "N-Linked", "24530628", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "3353", "", "Complex", "G48414YA" ], [ "P19652-1", "56", "Asn", "G42358LZ", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "3353", "", "Complex", "G48414YA" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:12 HexNAc:2", "14", "1163", "", "Undefined core", "" ], [ "P19652-1", "56", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:12 HexNAc:2", "14", "1163", "", "Undefined core", "" ], [ "P19652-1", "72", "Asn", "G22140GZ", "N-Linked", "19838169", "protein_xref_pubmed", "Hex:5 HexNAc:4", "14", "3471", "", "Complex", "G50045TK" ], [ "P19652-1", "72", "Asn", "G22140GZ", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4", "14", "3471", "", "Complex", "G50045TK" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:1", "14", "614", "", "Undefined core", "G06356OH" ], [ "P19652-1", "72", "Asn", "G36131WL", "N-Linked", "19838169", "protein_xref_pubmed", "Hex:6 HexNAc:5", "14", "644", "", "Complex", "G20425TQ" ], [ "P19652-1", "72", "Asn", "G36131WL", "N-Linked", "14", "protein_xref_glyconnect", "Hex:6 HexNAc:5", "14", "644", "", "Complex", "G20425TQ" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:4 HexNAc:6 dHex:2", "14", "8489", "", "Undefined core", "G11911BT" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:4 HexNAc:6 dHex:2", "14", "8489", "", "Undefined core", "G11911BT" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "29671580", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "29741879", "protein_xref_pubmed", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ], [ "P19652-1", "72", "Asn", "", "N-Linked", "14", "protein_xref_glyconnect", "Hex:5 HexNAc:4 NeuAc:2", "14", "1021", "", "Undefined core", "G48414YA" ] ] }, "readme": "Name\n - Human Glycosylation Sites (GlyConnect) \n\nVersion\n - 1.5.30\n\nCreated on\n - 2020-02-10T10:16:50.152756\n\nModified on\n - 2020-04-28T10:52:10.307161\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - Frederique Lisacek [frederique.lisacek@sib.swiss], Julien Mariethoz [julien.mariethoz@sib.swiss]\n\nChecksum\n - \n\nUsability Domain\n - The Human Glycosylation Sites (GlyConnect) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived directly from authors ( Frederique Lisacek; Julien Mariethoz) on 10/09/2019. If you use this dataset please provide proper attribution to GlyConnect and GlyGen.\n\nDescription Domain\n Keywords\n - glycosylation\n - reported glycosylation\n\n Pipeline Steps\n - Step-1: The script loads the glycosylation information from the input JSON file and extracts the data associated with Human [TaxID:9606] UniProtKB accessions. The QC checks filter out any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein.\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: glygen_2019_10_09_56_06.json\n URI: https://data.glygen.org/ln2wwwdata/source/glygen_2019_10_09_56_06.json\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Name: human_protein_canonicalsequences.fasta\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_glyconnect.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv\n Name: human_proteoform_glycosylation_sites_glyconnect.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.stat.csv\n\nFields\n Name: \"glyconnect_id\"\n Description: \"entity Id from GlyConnect database\"\n Unique Values: \"802\"\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: \"1096\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1081\"\n Name: \"xref_id\"\n Description: \"\"\n Unique Values: \"1188\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"3\"\n Name: \"glycan_core\"\n Description: \"Core of the associated glycan\"\n Unique Values: \"9\"\n Name: \"is_composition_only\"\n Description: \"Yes when the associated GlytouCan accession is a composition accession only.\"\n Unique Values: \"1\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"322\"\n Name: \"glyconnect_protein_id\"\n Description: \"Protein id from GlyConnect database\"\n Unique Values: \"1109\"\n Name: \"glytoucan_ac_composition\"\n Description: \"Composition of the associated glycan from GlyConnect database\"\n Unique Values: \"332\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"389\"\n Name: \"xref_key\"\n Description: \"\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.5.30/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv" }