{ "bcoid": "GLY_000143", "title": "Human Protein Glycosylation (Literature)", "description": "The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed ...", "filename": "human_proteoform_glycosylation_sites_literature.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Proteoform", "tags": "UniCarbKB publications", "status": "Reviewed", "file_type": "csv", "scope": "external" }, "minitable": { "content": [ [ "O60911-1...", "n-linked..." ], [ "Q08174-1...", "n-linked..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "evidence" } ], [ "O60911-1", "n-linked", "", "Asn", "221", "23090970" ], [ "Q08174-1", "n-linked", "", "Asn", "305", "23090970" ], [ "Q08174-1", "n-linked", "", "Asn", "305", "23090970" ], [ "Q08174-1", "n-linked", "", "Asn", "305", "23090970" ], [ "P01137-1", "n-linked", "", "Asn", "136", "23090970" ], [ "P01137-1", "n-linked", "", "Asn", "176", "23090970" ], [ "O95858-1", "n-linked", "", "Asn", "189", "23090970" ], [ "Q06828-1", "n-linked", "", "Asn", "166", "23090970" ], [ "A6NKQ9-1", "n-linked", "", "Asn", "63", "23090970" ], [ "A6NKQ9-1", "n-linked", "", "Asn", "63", "23090970" ], [ "A6NKQ9-1", "n-linked", "", "Asn", "63", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "931", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "931", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "869", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "869", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "515", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "515", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "862", "23090970" ], [ "Q9Y4L1-1", "n-linked", "", "Asn", "862", "23090970" ], [ "Q9Y5Y6-1", "n-linked", "", "Asn", "772", "23090970" ], [ "P50851-1", "n-linked", "", "Asn", "851", "23090970" ], [ "Q9UM47-1", "n-linked", "", "Asn", "851", "23090970" ], [ "P50851-1", "n-linked", "", "Asn", "851", "23090970" ], [ "P50851-1", "n-linked", "", "Asn", "851", "23090970" ], [ "P50895-1", "n-linked", "", "Asn", "439", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "P42892-1", "n-linked", "", "Asn", "166", "23090970" ], [ "Q9UBP4-1", "n-linked", "", "Asn", "204", "23090970" ], [ "Q9UBR2-1", "n-linked", "", "Asn", "184", "23090970" ], [ "Q9UBX1-1", "n-linked", "", "Asn", "195", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "241", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "241", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "241", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "241", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "95", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "95", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "95", "23090970" ], [ "Q16620-1", "n-linked", "", "Asn", "95", "23090970" ], [ "Q15223-1", "n-linked", "", "Asn", "202", "23090970" ], [ "Q15223-1", "n-linked", "", "Asn", "202", "23090970" ], [ "Q15223-1", "n-linked", "", "Asn", "202", "23090970" ], [ "Q15223-1", "n-linked", "", "Asn", "202", "23090970" ], [ "P11117-1", "n-linked", "", "Asn", "167", "23090970" ], [ "P11117-1", "n-linked", "", "Asn", "167", "23090970" ], [ "P11117-1", "n-linked", "", "Asn", "92", "23090970" ], [ "P11117-1", "n-linked", "", "Asn", "92", "23090970" ], [ "P11117-1", "n-linked", "", "Asn", "92", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "101", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "101", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "101", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "113", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "113", "23090970" ], [ "Q9BY67-1", "n-linked", "", "Asn", "113", "23090970" ], [ "P11169-1", "n-linked", "", "Asn", "43", "23090970" ], [ "Q16769-1", "n-linked", "", "Asn", "49", "23090970" ], [ "Q16769-1", "n-linked", "", "Asn", "49", "23090970" ], [ "O95274-1", "n-linked", "", "Asn", "118", "23090970" ], [ "O95274-1", "n-linked", "", "Asn", "163", "23090970" ], [ "O75509-1", "n-linked", "", "Asn", "82", "23090970" ], [ "Q16853-1", "n-linked", "", "Asn", "618", "23090970" ], [ "Q16853-1", "n-linked", "", "Asn", "592", "23090970" ], [ "P01833-1", "n-linked", "", "Asn", "469", "23090970" ], [ "P01833-1", "n-linked", "", "Asn", "499", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q31612-1", "n-linked", "", "Asn", "110", "23090970" ], [ "Q9Y5C1-1", "n-linked", "", "Asn", "296", "23090970" ], [ "Q8WWI5-1", "n-linked", "", "Asn", "135", "23090970" ], [ "Q8WWI5-1", "n-linked", "", "Asn", "135", "23090970" ], [ "Q8WWI5-1", "n-linked", "", "Asn", "135", "23090970" ], [ "Q8WWI5-1", "n-linked", "", "Asn", "135", "23090970" ], [ "P52797-1", "n-linked", "", "Asn", "38", "23090970" ], [ "P52797-1", "n-linked", "", "Asn", "100", "23090970" ], [ "P52798-1", "n-linked", "", "Asn", "33", "23090970" ], [ "P52798-1", "n-linked", "", "Asn", "33", "23090970" ], [ "P52798-1", "n-linked", "", "Asn", "33", "23090970" ], [ "P52799-1", "n-linked", "", "Asn", "139", "23090970" ] ] }, "readme": "Name\n - Human Protein Glycosylation (Literature)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-06-14T14:54:26.195339\n\nModified on\n - 2019-09-12T16:37:13.572422\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu]\n\nAuthors\n - \n\nChecksum\n - \n\nUsability Domain\n - The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Wi?niewski, J. R., & Mann, M. (2012). Quantification of theN-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\"). 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\n - literature\n - publications\n\n Pipeline Steps\n - Step-1: The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files.\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: glycosylation_sites_24190977_s5.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/glycosylation_sites_24190977_s5.csv\n Name: glycosylation_sites_23090970_s5.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/glycosylation_sites_23090970_s5.csv\n Name: glycosylation_sites_23090970_s2.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/glycosylation_sites_23090970_s2.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_literature.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_literature.csv\n Name: human_proteoform_glycosylation_sites_literature.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_literature.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: \"1340\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1045\"\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: \"2\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_literature.csv" }