{ "bcoid": "GLY_000305", "title": "Glycan Xref PubChem", "description": "The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated ...", "filename": "glycan_xref_pubchem.csv", "filetype": "csv", "categories": { "molecule": "Glycan", "tags": "PubChem", "status": "Reviewed", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "G00023MO...", "91846235..." ], [ "G00023MO...", "252277270..." ] ], "headers": [ "glytoucan_ac...", "xref_id..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "glytoucan_ac" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_key" } ], [ "G00023MO", "91846235", "glycan_xref_pubchem_compound" ], [ "G00023MO", "252277270", "glycan_xref_pubchem_substance" ], [ "G00024MO", "11375554", "glycan_xref_pubchem_compound" ], [ "G00024MO", "252288623", "glycan_xref_pubchem_substance" ], [ "G00025AJ", "91857678", "glycan_xref_pubchem_compound" ], [ "G00025AJ", "252290930", "glycan_xref_pubchem_substance" ], [ "G00025MO", "5288428", "glycan_xref_pubchem_compound" ], [ "G00025MO", "252293186", "glycan_xref_pubchem_substance" ], [ "G00027MO", "91859643", "glycan_xref_pubchem_compound" ], [ "G00027MO", "252293273", "glycan_xref_pubchem_substance" ], [ "G00031MO", "5288347", "glycan_xref_pubchem_compound" ], [ "G00031MO", "252294787", "glycan_xref_pubchem_substance" ], [ "G00033MO", "52921656", "glycan_xref_pubchem_compound" ], [ "G00033MO", "252289141", "glycan_xref_pubchem_substance" ], [ "G00035MO", "25061208", "glycan_xref_pubchem_compound" ], [ "G00035MO", "252285840", "glycan_xref_pubchem_substance" ], [ "G00037MO", "25229562", "glycan_xref_pubchem_compound" ], [ "G00037MO", "252279040", "glycan_xref_pubchem_substance" ], [ "G00039MO", "91853465", "glycan_xref_pubchem_compound" ], [ "G00039MO", "252285892", "glycan_xref_pubchem_substance" ], [ "G00041MO", "56611864", "glycan_xref_pubchem_compound" ], [ "G00041MO", "252296995", "glycan_xref_pubchem_substance" ], [ "G00043MO", "91846113", "glycan_xref_pubchem_compound" ], [ "G00043MO", "252277123", "glycan_xref_pubchem_substance" ], [ "G00047MO", "22806751", "glycan_xref_pubchem_compound" ], [ "G00047MO", "252282939", "glycan_xref_pubchem_substance" ], [ "G00048MO", "45480569", "glycan_xref_pubchem_compound" ], [ "G00048MO", "252279306", "glycan_xref_pubchem_substance" ], [ "G00049MO", "5279514", "glycan_xref_pubchem_compound" ], [ "G00049MO", "252287332", "glycan_xref_pubchem_substance" ], [ "G00050MO", "70678645", "glycan_xref_pubchem_compound" ], [ "G00050MO", "252285322", "glycan_xref_pubchem_substance" ], [ "G00051MO", "44611539", "glycan_xref_pubchem_compound" ], [ "G00051MO", "252296557", "glycan_xref_pubchem_substance" ], [ "G00052MO", "45266908", "glycan_xref_pubchem_compound" ], [ "G00052MO", "252284113", "glycan_xref_pubchem_substance" ], [ "G00053MO", "53356732", "glycan_xref_pubchem_compound" ], [ "G00053MO", "252276065", "glycan_xref_pubchem_substance" ], [ "G00054MO", "44456859", "glycan_xref_pubchem_compound" ], [ "G00054MO", "252277227", "glycan_xref_pubchem_substance" ], [ "G00055MO", "439271", "glycan_xref_pubchem_compound" ], [ "G00055MO", "252296420", "glycan_xref_pubchem_substance" ], [ "G00056MO", "10177989", "glycan_xref_pubchem_compound" ], [ "G00056MO", "252278809", "glycan_xref_pubchem_substance" ], [ "G00057MO", "44611452", "glycan_xref_pubchem_compound" ], [ "G00057MO", "252289075", "glycan_xref_pubchem_substance" ], [ "G00058MO", "25062237", "glycan_xref_pubchem_compound" ], [ "G00058MO", "252286874", "glycan_xref_pubchem_substance" ], [ "G00059MO", "5279515", "glycan_xref_pubchem_compound" ], [ "G00059MO", "252284581", "glycan_xref_pubchem_substance" ], [ "G00060MO", "91847704", "glycan_xref_pubchem_compound" ], [ "G00060MO", "252279056", "glycan_xref_pubchem_substance" ], [ "G00061MO", "5288889", "glycan_xref_pubchem_compound" ], [ "G00061MO", "252296009", "glycan_xref_pubchem_substance" ], [ "G00062MO", "91853425", "glycan_xref_pubchem_compound" ], [ "G00062MO", "252285844", "glycan_xref_pubchem_substance" ], [ "G00063MO", "91853411", "glycan_xref_pubchem_compound" ], [ "G00063MO", "252285826", "glycan_xref_pubchem_substance" ], [ "G00064MO", "91851548", "glycan_xref_pubchem_compound" ], [ "G00064MO", "252283591", "glycan_xref_pubchem_substance" ], [ "G00065MO", "44611401", "glycan_xref_pubchem_compound" ], [ "G00065MO", "252297063", "glycan_xref_pubchem_substance" ], [ "G00066MO", "49852448", "glycan_xref_pubchem_compound" ], [ "G00066MO", "252277739", "glycan_xref_pubchem_substance" ], [ "G00067MO", "91861847", "glycan_xref_pubchem_compound" ], [ "G00067MO", "252295919", "glycan_xref_pubchem_substance" ], [ "G00068MO", "5288275", "glycan_xref_pubchem_compound" ], [ "G00068MO", "252284680", "glycan_xref_pubchem_substance" ], [ "G00076PK", "9915394", "glycan_xref_pubchem_compound" ], [ "G00076PK", "252294294", "glycan_xref_pubchem_substance" ], [ "G00090SL", "91859395", "glycan_xref_pubchem_compound" ], [ "G00090SL", "252292981", "glycan_xref_pubchem_substance" ], [ "G00091RT", "5288738", "glycan_xref_pubchem_compound" ], [ "G00091RT", "252282782", "glycan_xref_pubchem_substance" ], [ "G00112IO", "91851800", "glycan_xref_pubchem_compound" ], [ "G00112IO", "252283898", "glycan_xref_pubchem_substance" ], [ "G00120QS", "91846337", "glycan_xref_pubchem_compound" ], [ "G00120QS", "252277397", "glycan_xref_pubchem_substance" ], [ "G00123JF", "11521105", "glycan_xref_pubchem_compound" ], [ "G00123JF", "252289905", "glycan_xref_pubchem_substance" ], [ "G00140XB", "91852120", "glycan_xref_pubchem_compound" ], [ "G00140XB", "252284282", "glycan_xref_pubchem_substance" ], [ "G00152LK", "5287768", "glycan_xref_pubchem_compound" ], [ "G00152LK", "252288265", "glycan_xref_pubchem_substance" ] ] }, "readme": "Name\n - Glycan Xref PubChem\n\nVersion\n - 1.8.24\n\nCreated on\n - 2019-11-14T11:47:20.058924\n\nModified on\n - 2020-05-01T15:15:26.085137\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - Nathan Edwards [nje5@georgetown.edu]\n\nChecksum\n - \n\nUsability Domain\n - The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov\n\nDescription Domain\n Keywords\n - Glycan\n - GlyTouCan Accession\n - PubChem\n - Cross-references\n - ID/Accession Mapping\n\n Pipeline Steps\n - Step-1: The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list.\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-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: pbch.tsv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/source/pbch.tsv\n Output Subdomain\n Name: glycan_xref_pubchem.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/glycan_xref_pubchem.csv\n Name: glycan_xref_pubchem.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/glycan_xref_pubchem.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-1.8.24/reviewed/glycan_xref_pubchem.csv" }