{ "bcoid": "GLY_000481", "title": "Human Glycosylation Sites [Automatic Literature Mining]", "description": "List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) ...", "filename": "human_proteoform_glycosylation_sites_literature_mining.csv", "filetype": "csv", "categories": { "status": "Reviewed", "molecule": "Proteoform", "species": "Homo sapiens", "tags": "glycosylation sites", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "O15431-1...", "15..." ], [ "O15431-1...", "15..." ] ], "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_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "src_xref_key" }, { "type": "string", "label": "src_xref_id" }, { "type": "string", "label": "n_sequon" }, { "type": "string", "label": "n_sequon_type" } ], [ "O15431-1", "15", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "17525160", "protein_xref_automatic_literature_mining", "17525160", "NST", "NXT" ], [ "O15431-1", "15", "Asn", "", "N-linked", "protein_xref_pubmed", "17525160", "protein_xref_automatic_literature_mining", "17525160", "NST", "NXT" ], [ "O15431-1", "27", "Thr", "", "O-linked", "protein_xref_automatic_literature_mining", "17525160", "protein_xref_automatic_literature_mining", "17525160", "", "" ], [ "O15431-1", "27", "Thr", "", "O-linked", "protein_xref_pubmed", "17525160", "protein_xref_automatic_literature_mining", "17525160", "", "" ], [ "O95255-1", "15", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "12901863", "protein_xref_automatic_literature_mining", "12901863", "NQT", "NXT" ], [ "O95255-1", "15", "Asn", "", "N-linked", "protein_xref_pubmed", "12901863", "protein_xref_automatic_literature_mining", "12901863", "NQT", "NXT" ], [ "P00738-1", "211", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "18214858", "protein_xref_automatic_literature_mining", "18214858", "NAT", "NXT" ], [ "P00738-1", "211", "Asn", "", "N-linked", "protein_xref_pubmed", "18214858", "protein_xref_automatic_literature_mining", "18214858", "NAT", "NXT" ], [ "P01009-1", "70", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "16622833", "protein_xref_automatic_literature_mining", "16622833", "NST", "NXT" ], [ "P01009-1", "70", "Asn", "", "N-linked", "protein_xref_pubmed", "16622833", "protein_xref_automatic_literature_mining", "16622833", "NST", "NXT" ], [ "P01106-1", "58", "Thr", "", "O-linked", "protein_xref_automatic_literature_mining", "11904304", "protein_xref_automatic_literature_mining", "11904304", "", "" ], [ "P01106-1", "58", "Thr", "", "O-linked", "protein_xref_pubmed", "11904304", "protein_xref_automatic_literature_mining", "11904304", "", "" ], [ "P01106-1", "58", "Thr", "", "O-linked", "protein_xref_automatic_literature_mining", "7642555", "protein_xref_automatic_literature_mining", "7642555", "", "" ], [ "P01106-1", "58", "Thr", "", "O-linked", "protein_xref_pubmed", "7642555", "protein_xref_automatic_literature_mining", "7642555", "", "" ], [ "P02730-1", "642", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "10861210", "protein_xref_automatic_literature_mining", "10861210", "NSS", "NXS" ], [ "P02730-1", "642", "Asn", "", "N-linked", "protein_xref_pubmed", "10861210", "protein_xref_automatic_literature_mining", "10861210", "NSS", "NXS" ], [ "P02786-1", "251", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "9136890", "protein_xref_automatic_literature_mining", "9136890", "NGS", "NXS" ], [ "P02786-1", "251", "Asn", "", "N-linked", "protein_xref_pubmed", "9136890", "protein_xref_automatic_literature_mining", "9136890", "NGS", "NXS" ], [ "P02786-1", "727", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "7780197", "protein_xref_automatic_literature_mining", "7780197", "NET", "NXT" ], [ "P02786-1", "727", "Asn", "", "N-linked", "protein_xref_pubmed", "7780197", "protein_xref_automatic_literature_mining", "7780197", "NET", "NXT" ], [ "P02786-1", "727", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "9136890", "protein_xref_automatic_literature_mining", "9136890", "NET", "NXT" ], [ "P02786-1", "727", "Asn", "", "N-linked", "protein_xref_pubmed", "9136890", "protein_xref_automatic_literature_mining", "9136890", "NET", "NXT" ], [ "P02786-1", "104", "Thr", "", "O-linked", "protein_xref_automatic_literature_mining", "1421757", "protein_xref_automatic_literature_mining", "1421757", "", "" ], [ "P02786-1", "104", "Thr", "", "O-linked", "protein_xref_pubmed", "1421757", "protein_xref_automatic_literature_mining", "1421757", "", "" ], [ "P02787-1", "432", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "15536627", "protein_xref_automatic_literature_mining", "15536627", "NKS", "NXS" ], [ "P02787-1", "432", "Asn", "", "N-linked", "protein_xref_pubmed", "15536627", "protein_xref_automatic_literature_mining", "15536627", "NKS", "NXS" ], [ "P02787-1", "630", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "15536627", "protein_xref_automatic_literature_mining", "15536627", "NVT", "NXT" ], [ "P02787-1", "630", "Asn", "", "N-linked", "protein_xref_pubmed", "15536627", "protein_xref_automatic_literature_mining", "15536627", "NVT", "NXT" ], [ "P03956-1", "120", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "10092871", "protein_xref_automatic_literature_mining", "10092871", "NYT", "NXT" ], [ "P03956-1", "120", "Asn", "", "N-linked", "protein_xref_pubmed", "10092871", "protein_xref_automatic_literature_mining", "10092871", "NYT", "NXT" ], [ "P07288-1", "69", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "25327667", "protein_xref_automatic_literature_mining", "25327667", "NKS", "NXS" ], [ "P07288-1", "69", "Asn", "", "N-linked", "protein_xref_pubmed", "25327667", "protein_xref_automatic_literature_mining", "25327667", "NKS", "NXS" ], [ "P08473-1", "628", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "22766194", "protein_xref_automatic_literature_mining", "22766194", "NFS", "NXS" ], [ "P08473-1", "628", "Asn", "", "N-linked", "protein_xref_pubmed", "22766194", "protein_xref_automatic_literature_mining", "22766194", "NFS", "NXS" ], [ "P08842-1", "259", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "2668275", "protein_xref_automatic_literature_mining", "2668275", "NLT", "NXT" ], [ "P08842-1", "259", "Asn", "", "N-linked", "protein_xref_pubmed", "2668275", "protein_xref_automatic_literature_mining", "2668275", "NLT", "NXT" ], [ "P08842-1", "47", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "2668275", "protein_xref_automatic_literature_mining", "2668275", "NKT", "NXT" ], [ "P08842-1", "47", "Asn", "", "N-linked", "protein_xref_pubmed", "2668275", "protein_xref_automatic_literature_mining", "2668275", "NKT", "NXT" ], [ "P11279-1", "183", "Ser", "", "O-linked", "protein_xref_automatic_literature_mining", "8323299", "protein_xref_automatic_literature_mining", "8323299", "", "" ], [ "P11279-1", "183", "Ser", "", "O-linked", "protein_xref_pubmed", "8323299", "protein_xref_automatic_literature_mining", "8323299", "", "" ], [ "P13497-1", "142", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NFT", "NXT" ], [ "P13497-1", "142", "Asn", "", "N-linked", "protein_xref_pubmed", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NFT", "NXT" ], [ "P13497-1", "332", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NFS", "NXS" ], [ "P13497-1", "332", "Asn", "", "N-linked", "protein_xref_pubmed", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NFS", "NXS" ], [ "P13497-1", "599", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NGS", "NXS" ], [ "P13497-1", "599", "Asn", "", "N-linked", "protein_xref_pubmed", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NGS", "NXS" ], [ "P13497-1", "91", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NTS", "NXS" ], [ "P13497-1", "91", "Asn", "", "N-linked", "protein_xref_pubmed", "12218058", "protein_xref_automatic_literature_mining", "12218058", "NTS", "NXS" ], [ "P15382-1", "5", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "21669976", "protein_xref_automatic_literature_mining", "21669976", "NTT", "NXT" ], [ "P15382-1", "5", "Asn", "", "N-linked", "protein_xref_pubmed", "21669976", "protein_xref_automatic_literature_mining", "21669976", "NTT", "NXT" ], [ "P15382-1", "7", "Thr", "", "O-linked", "protein_xref_automatic_literature_mining", "21669976", "protein_xref_automatic_literature_mining", "21669976", "", "" ], [ "P15382-1", "7", "Thr", "", "O-linked", "protein_xref_pubmed", "21669976", "protein_xref_automatic_literature_mining", "21669976", "", "" ], [ "P16422-1", "198", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "18508581", "protein_xref_automatic_literature_mining", "18508581", "NSS", "NXS" ], [ "P16422-1", "198", "Asn", "", "N-linked", "protein_xref_pubmed", "18508581", "protein_xref_automatic_literature_mining", "18508581", "NSS", "NXS" ], [ "P19634-1", "75", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "8068684", "protein_xref_automatic_literature_mining", "8068684", "NHS", "NXS" ], [ "P19634-1", "75", "Asn", "", "N-linked", "protein_xref_pubmed", "8068684", "protein_xref_automatic_literature_mining", "8068684", "NHS", "NXS" ], [ "P20827-1", "26", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "23661698", "protein_xref_automatic_literature_mining", "23661698", "NSS", "NXS" ], [ "P20827-1", "26", "Asn", "", "N-linked", "protein_xref_pubmed", "23661698", "protein_xref_automatic_literature_mining", "23661698", "NSS", "NXS" ], [ "P20916-1", "106", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "7505568", "protein_xref_automatic_literature_mining", "7505568", "NVS", "NXS" ], [ "P20916-1", "106", "Asn", "", "N-linked", "protein_xref_pubmed", "7505568", "protein_xref_automatic_literature_mining", "7505568", "NVS", "NXS" ], [ "P22760-1", "282", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "24125761", "protein_xref_automatic_literature_mining", "24125761", "NWS", "NXS" ], [ "P22760-1", "282", "Asn", "", "N-linked", "protein_xref_pubmed", "24125761", "protein_xref_automatic_literature_mining", "24125761", "NWS", "NXS" ], [ "P22760-1", "78", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "24125761", "protein_xref_automatic_literature_mining", "24125761", "NVT", "NXT" ], [ "P22760-1", "78", "Asn", "", "N-linked", "protein_xref_pubmed", "24125761", "protein_xref_automatic_literature_mining", "24125761", "NVT", "NXT" ], [ "P25103-1", "14", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "17563389", "protein_xref_automatic_literature_mining", "17563389", "NIS", "NXS" ], [ "P25103-1", "14", "Asn", "", "N-linked", "protein_xref_pubmed", "17563389", "protein_xref_automatic_literature_mining", "17563389", "NIS", "NXS" ], [ "P25103-1", "18", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "17563389", "protein_xref_automatic_literature_mining", "17563389", "NTS", "NXS" ], [ "P25103-1", "18", "Asn", "", "N-linked", "protein_xref_pubmed", "17563389", "protein_xref_automatic_literature_mining", "17563389", "NTS", "NXS" ], [ "P25116-1", "250", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "21550978", "protein_xref_automatic_literature_mining", "21550978", "NIT", "NXT" ], [ "P25116-1", "250", "Asn", "", "N-linked", "protein_xref_pubmed", "21550978", "protein_xref_automatic_literature_mining", "21550978", "NIT", "NXT" ], [ "P29965-1", "240", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "11676606", "protein_xref_automatic_literature_mining", "11676606", "NVT", "NXT" ], [ "P29965-1", "240", "Asn", "", "N-linked", "protein_xref_pubmed", "11676606", "protein_xref_automatic_literature_mining", "11676606", "NVT", "NXT" ], [ "P33527-1", "1006", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NGT", "NXT" ], [ "P33527-1", "1006", "Asn", "", "N-linked", "protein_xref_pubmed", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NGT", "NXT" ], [ "P33527-1", "19", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NVT", "NXT" ], [ "P33527-1", "19", "Asn", "", "N-linked", "protein_xref_pubmed", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NVT", "NXT" ], [ "P33527-1", "23", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NTS", "NXS" ], [ "P33527-1", "23", "Asn", "", "N-linked", "protein_xref_pubmed", "9295302", "protein_xref_automatic_literature_mining", "9295302", "NTS", "NXS" ], [ "P34998-1", "38", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NIS", "NXS" ], [ "P34998-1", "38", "Asn", "", "N-linked", "protein_xref_pubmed", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NIS", "NXS" ], [ "P34998-1", "45", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NAS", "NXS" ], [ "P34998-1", "45", "Asn", "", "N-linked", "protein_xref_pubmed", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NAS", "NXS" ], [ "P34998-1", "78", "Asn", "", "N-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NTT", "NXT" ], [ "P34998-1", "78", "Asn", "", "N-linked", "protein_xref_pubmed", "11595658", "protein_xref_automatic_literature_mining", "11595658", "NTT", "NXT" ] ] }, "readme": "Name\n - Human Glycosylation Sites [Automatic Literature Mining]\n\nVersion\n - 1.8.25\n\nCreated on\n - 2020-04-20T16:47:37.482643\n\nModified on\n - 2020-04-30T10:37:24.842264\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu]\n\nAuthors\n - Rahi Navelkar [rsn13@gwu.edu], Vijay Shanker [vijay@udel.edu], Karen Ross [ker25@georgetown.edu], Xavier Holmes [xavierh@email.gwu.edu]\n\nChecksum\n - \n\nUsability Domain\n - List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - GlyTouCan\n - Automatic Literature Mining\n\n Pipeline Steps\n - Step-1: The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the uniprotkb accessions to uniprotkb canonical accessions. 2. Validate the \"amino_acid\" and \"glycosylation_site\" with the .fasta sequence. 3. Add new column: Evidence with 2 values: Automatic literature Mining | GLYDS000481 (split into 2 rows)4.change column headers: uniprotkb_ac to uniprotkb_canonical_ac\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: proteoform_glycosylation_sites_literature_mining.csv\n URI: https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_literature_mining.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv\n Name: human_proteoform_glycosylation_sites_literature_mining.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv" }