{ "bcoid": "GLY_000040", "title": "Human Glycosylation Sites (UniCarbKB)", "description": "List of human [taxid:9606] proteins with information on glycosylation sites from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ...", "filename": "human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv", "filetype": "csv", "categories": { "status": "Reviewed" }, "minitable": { "content": [ [ "P07498-1...", "151..." ], [ "P07498-1...", "148..." ] ], "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" } ], [ "P07498-1", "151", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "148", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "157", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "181", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "162", "3342257", "4", "G00031MO", "Ser", "o-linked" ], [ "P07498-1", "148", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "133", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "143", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "167", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "157", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "181", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "162", "3342257", "357", "G05848DX", "Ser", "o-linked" ], [ "P07498-1", "148", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "133", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "157", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "181", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "169", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "162", "3342257", "5", "G64973KT", "Ser", "o-linked" ], [ "P07498-1", "133", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "151", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "178", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "151", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "167", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "143", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "169", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "133", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "162", "3342257", "351", "G30871VQ", "Ser", "o-linked" ], [ "P07498-1", "181", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "169", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "178", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "151", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "178", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "178", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "169", "3342257", "4", "G00031MO", "Thr", "o-linked" ], [ "P07498-1", "157", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "167", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "143", "3342257", "5", "G64973KT", "Thr", "o-linked" ], [ "P07498-1", "148", "3342257", "351", "G30871VQ", "Thr", "o-linked" ], [ "P07498-1", "167", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P07498-1", "143", "3342257", "357", "G05848DX", "Thr", "o-linked" ], [ "P19835-1", "207", "10024660", "1653", "G16828VN", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1653", "G16828VN", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "2983", "G55373ZG", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "2985", "G53276NK", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "1489", "G66937TJ", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1489", "G66937TJ", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "2977", "G87073UP", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "2539", "G24748QU", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1785", "G25837HW", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "1785", "G25837HW", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "3553", "G86750HK", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "1603", "G78059CC", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1603", "G78059CC", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "3553", "G86750HK", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1521", "G36191CD", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "1761", "G76675AB", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "2979", "G52080WL", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "2979", "G52080WL", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1761", "G76675AB", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "2985", "G53276NK", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "2985", "G53276NK", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1489", "G66937TJ", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "2977", "G87073UP", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "2539", "G24748QU", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "2539", "G24748QU", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "2977", "G87073UP", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1653", "G16828VN", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "2983", "G55373ZG", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "2983", "G55373ZG", "Asn", "n-linked" ], [ "P19835-1", "207", "14693913", "1521", "G36191CD", "Asn", "n-linked" ], [ "P19835-1", "207", "10024660", "1521", "G36191CD", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "2979", "G52080WL", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1761", "G76675AB", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1785", "G25837HW", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "3553", "G86750HK", "Asn", "n-linked" ], [ "P19835-1", "207", "8404899", "1603", "G78059CC", "Asn", "n-linked" ], [ "P01375-1", "80", "8631363", "4", "G00031MO", "Ser", "o-linked" ], [ "P01375-1", "80", "8631363", "8", "G56682BC", "Ser", "o-linked" ], [ "P01374-1", "96", "8323280", "1663", "G86357DX", "Asn", "n-linked" ], [ "P01374-1", "96", "8323280", "1669", "G63889NK", "Asn", "n-linked" ], [ "P01374-1", "96", "8323280", "1879", "G29228MX", "Asn", "n-linked" ], [ "P01374-1", "96", "8323280", "1659", "G45359RY", "Asn", "n-linked" ], [ "P01374-1", "96", "8323280", "1881", "G52038JM", "Asn", "n-linked" ], [ "P01374-1", "96", "8323280", "1603", "G78059CC", "Asn", "n-linked" ] ] }, "readme": "Name\n - Human Glycosylation Sites (UniCarbKB)\n\nVersion\n - 1.0.13\n\nCreated on\n - 2019-01-23T17:21:05.907769\n\nModified on\n - 2019-04-11T13:36:49.822332\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu]\n\nAuthors\n - Matthew Campbell [m.campbell2@griffith.edu.au], Robel Kahsay [rykahsay@email.gwu.edu], Brian Fochtman [bfochtman@email.gwu.edu]\n\nChecksum\n - \n\nUsability Domain\n - List of human [taxid:9606] proteins with information on glycosylation sites from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation\n - glycan\n\n Pipeline Steps\n - Step-1: The input file was retrieved directly from source was \"cleaned\" for further processing and the glycosylation type (linkage type) was assigned using a python script [make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py] based on motif label provided by the author. \n - Step-2: The UniProtKB protein accessions were mapped to canonical accessions and the final data was processed for quality check using a python script[make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.py] and the records which fall under one or more following criteria's were flagged and eliminated (eliminated records can be accessed using the log file through Output subdomain): a. If the protein accession is not included in UniProt protein list [UniProt Nov-2017 Release] b. If the amino acid position does not match to the amino acid on the associated position on fasta sequence [UniProt Nov-2017 Release] c. If the id (UnicarbKB structure id) is not present in input file. d. If the glycosylation type (linkage type) is not retrieved through step 2. e. If a serine or threonine is reported for an N-linked glycan structure. f. If an asparagine is reported for an O-linked glycan structure. g. If the glycosylation type (linkage type) has both \"N-linked;O-linked\" assignment through step 2\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend/blob/master/integration/\n - https://github.com/glygener/glygen-backend/blob/master/integration/\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: unicarbkb_human_2018_10_31_02_22_23.clean.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/unicarbkb_human_2018_10_31_02_22_23.clean.csv\n Name: human_glytoucan_140918_2018_10_31_02_17_32.txt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/human_glytoucan_140918_2018_10_31_02_17_32.txt\n Name: human_protein_all.fasta\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_protein_all.fasta\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv\n Name: human_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv\n\nFields\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"glytoucan_acc\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"341\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"3\"\n Name: \"uckb_id\"\n Description: \"UnicarbKB database identifier\"\n Unique Values: \"343\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"114\"\n Name: \"glycosylation_site\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"145\"\n Name: \"uniprotkb_acc_canonical\"\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: \"52\"", "downloadurl": "/ln2data/releases/data/v-1.0.13/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv" }