{ "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": [ [ "P02730-1...", "642..." ], [ "P02730-1...", "642..." ] ], "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" } ], [ "P02730-1", "642", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "10861210", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P02730-1", "642", "Asn", "", "n-linked", "protein_xref_pubmed", "10861210", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y6Y9-1", "26", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11544325", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y6Y9-1", "26", "Asn", "", "n-linked", "protein_xref_pubmed", "11544325", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y6Y9-1", "114", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11544325", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y6Y9-1", "114", "Asn", "", "n-linked", "protein_xref_pubmed", "11544325", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "78", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "78", "Asn", "", "n-linked", "protein_xref_pubmed", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "90", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "90", "Asn", "", "n-linked", "protein_xref_pubmed", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "38", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "38", "Asn", "", "n-linked", "protein_xref_pubmed", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "98", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "98", "Asn", "", "n-linked", "protein_xref_pubmed", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "45", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P34998-1", "45", "Asn", "", "n-linked", "protein_xref_pubmed", "11595658", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P29965-1", "240", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "11676606", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P29965-1", "240", "Asn", "", "n-linked", "protein_xref_pubmed", "11676606", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P01106-1", "58", "Thr", "", "o-linked", "protein_xref_automatic_literature_mining", "11904304", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P01106-1", "58", "Thr", "", "o-linked", "protein_xref_pubmed", "11904304", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "142", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "142", "Asn", "", "n-linked", "protein_xref_pubmed", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "91", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "91", "Asn", "", "n-linked", "protein_xref_pubmed", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "599", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "599", "Asn", "", "n-linked", "protein_xref_pubmed", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "332", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P13497-1", "332", "Asn", "", "n-linked", "protein_xref_pubmed", "12218058", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25103-1", "14", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "17563389", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25103-1", "14", "Asn", "", "n-linked", "protein_xref_pubmed", "17563389", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25103-1", "18", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "17563389", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25103-1", "18", "Asn", "", "n-linked", "protein_xref_pubmed", "17563389", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q04206-1", "352", "Thr", "", "o-linked", "protein_xref_automatic_literature_mining", "18988733", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q04206-1", "352", "Thr", "", "o-linked", "protein_xref_pubmed", "18988733", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q6PIU2-1", "270", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "19592704", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q6PIU2-1", "270", "Asn", "", "n-linked", "protein_xref_pubmed", "19592704", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q8TAV3-1", "177", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "20805301", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q8TAV3-1", "177", "Asn", "", "n-linked", "protein_xref_pubmed", "20805301", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25116-1", "250", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "21550978", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P25116-1", "250", "Asn", "", "n-linked", "protein_xref_pubmed", "21550978", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y4K0-1", "644", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "23319596", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9Y4K0-1", "644", "Asn", "", "n-linked", "protein_xref_pubmed", "23319596", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P20827-1", "26", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "23661698", "protein_xref_glygen_ds", "GLYDS000481" ], [ "P20827-1", "26", "Asn", "", "n-linked", "protein_xref_pubmed", "23661698", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q15043-1", "102", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "24927598", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q15043-1", "102", "Asn", "", "n-linked", "protein_xref_pubmed", "24927598", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q2MKA7-1", "137", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "27314333", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q2MKA7-1", "137", "Asn", "", "n-linked", "protein_xref_pubmed", "27314333", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9ULZ9-1", "318", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "28531887", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q9ULZ9-1", "318", "Asn", "", "n-linked", "protein_xref_pubmed", "28531887", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q96RD6-3", "86", "Asn", "", "n-linked", "protein_xref_automatic_literature_mining", "29932112", "protein_xref_glygen_ds", "GLYDS000481" ], [ "Q96RD6-3", "86", "Asn", "", "n-linked", "protein_xref_pubmed", "29932112", "protein_xref_glygen_ds", "GLYDS000481" ] ] }, "readme": "Name\n - Human Glycosylation Sites [Automatic Literature Mining]\n\nVersion\n - 1.5.36\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: \"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: \"17\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"25\"\n Name: \"xref_id\"\n Description: \"\"\n Unique Values: \"17\"\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: \"2\"\n Name: \"src_xref_key\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"1\"\n Name: \"xref_key\"\n Description: \"\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.5.36/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv" }