{ "bcoid": "GLY_000341", "title": "Glycan Species ", "description": "The dataset provides species annotation for the associated glycan (GlyTouCan Accession) generated from ...", "filename": "glycan_species.csv", "filetype": "csv", "categories": { "molecule": "Glycan", "tags": "NCBI TaxID", "status": "Reviewed", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "G22196LK...", "..." ], [ "G22196LK...", "..." ] ], "headers": [ "glytoucan_ac...", "tax_id..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "glytoucan_ac" }, { "type": "string", "label": "tax_id" }, { "type": "string", "label": "tax_name" }, { "type": "string", "label": "annotation_category" }, { "type": "string", "label": "source" }, { "type": "string", "label": "source_id" }, { "type": "string", "label": "original_source_id" }, { "type": "string", "label": "xref_key" } ], [ "G22196LK", "", "Mus musculus", "Subsumption", "Subsumption", "via G40786FB", "", "glycan_xref_subsumption" ], [ "G22196LK", "", "Homo sapiens", "Subsumption", "Subsumption", "via G45700OA", "", "glycan_xref_subsumption" ], [ "G71280GW", "", "Homo sapiens", "Subsumption", "Subsumption", "via G33188UJ", "", "glycan_xref_subsumption" ], [ "G71280GW", "", "Homo sapiens", "Subsumption", "Subsumption", "via G34252AT", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G25520XG", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Mus musculus", "Subsumption", "Subsumption", "via G25520XG", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Mus musculus", "Subsumption", "Subsumption", "via G58517TJ", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G01378OV", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G08577PR", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G09650BK", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G12604EW", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G13583BZ", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G20218ZS", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G22859OA", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G23681NU", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G23901NY", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G25520XG", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G28723UT", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G29228MX", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G33262YZ", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G38753OV", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G42832NT", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G45187EI", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G48458AB", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G50499BR", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G52038JM", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G58517TJ", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G60468EV", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G61627IG", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G61792ET", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G74325TG", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G93141AZ", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G96861IW", "", "glycan_xref_subsumption" ], [ "G91636VS", "", "Homo sapiens", "Subsumption", "Subsumption", "via G98132BH", "", "glycan_xref_subsumption" ], [ "G87581UC", "", "Homo sapiens", "Subsumption", "Subsumption", "via G48178AY", "", "glycan_xref_subsumption" ], [ "G79026TT", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G20991HR", "", "glycan_xref_subsumption" ], [ "G79026TT", "", "Homo sapiens", "Subsumption", "Subsumption", "via G20352YV", "", "glycan_xref_subsumption" ], [ "G33734YD", "9606", "Homo sapiens", "Direct", "UniCarbKB", "3413", "", "glycan_xref_unicarbkb" ], [ "G30001EY", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G72557NR", "", "glycan_xref_subsumption" ], [ "G87573HF", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G62167DK", "", "glycan_xref_subsumption" ], [ "G87573HF", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G64239KZ", "", "glycan_xref_subsumption" ], [ "G87573HF", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G66875SM", "", "glycan_xref_subsumption" ], [ "G87573HF", "", "Homo sapiens", "Subsumption", "Subsumption", "via G62167DK", "", "glycan_xref_subsumption" ], [ "G87573HF", "", "Homo sapiens", "Subsumption", "Subsumption", "via G66875SM", "", "glycan_xref_subsumption" ], [ "G96934US", "", "Homo sapiens", "Subsumption", "Subsumption", "via G08465VN", "", "glycan_xref_subsumption" ], [ "G96934US", "", "Homo sapiens", "Subsumption", "Subsumption", "via G09859LE", "", "glycan_xref_subsumption" ], [ "G09173AD", "", "Homo sapiens", "Subsumption", "Subsumption", "via G60542VK", "", "glycan_xref_subsumption" ], [ "G59345UT", "", "Homo sapiens", "Subsumption", "Subsumption", "via G16150CJ", "", "glycan_xref_subsumption" ], [ "G24634JN", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G94543DB", "", "glycan_xref_subsumption" ], [ "G24634JN", "", "Mus musculus", "Subsumption", "Subsumption", "via G40012WS", "", "glycan_xref_subsumption" ], [ "G24634JN", "", "Homo sapiens", "Subsumption", "Subsumption", "via G03984TW", "", "glycan_xref_subsumption" ], [ "G24634JN", "", "Homo sapiens", "Subsumption", "Subsumption", "via G30939HN", "", "glycan_xref_subsumption" ], [ "G24634JN", "", "Homo sapiens", "Subsumption", "Subsumption", "via G38349VC", "", "glycan_xref_subsumption" ], [ "G12417OE", "", "Homo sapiens", "Subsumption", "Subsumption", "via G96063MG", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G35879BG", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G38710SX", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G70647TI", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Mus musculus", "Subsumption", "Subsumption", "via G23347CS", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Mus musculus", "Subsumption", "Subsumption", "via G70647TI", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G04676YO", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G23347CS", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G34797BZ", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G35879BG", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G70647TI", "", "glycan_xref_subsumption" ], [ "G39632CM", "", "Homo sapiens", "Subsumption", "Subsumption", "via G96709CX", "", "glycan_xref_subsumption" ], [ "G24823MG", "", "Homo sapiens", "Subsumption", "Subsumption", "via G89877QI", "", "glycan_xref_subsumption" ], [ "G18574CV", "", "Mus musculus", "Subsumption", "Subsumption", "via G01614ZM", "", "glycan_xref_subsumption" ], [ "G18574CV", "", "Homo sapiens", "Subsumption", "Subsumption", "via G01614ZM", "", "glycan_xref_subsumption" ], [ "G18574CV", "", "Homo sapiens", "Subsumption", "Subsumption", "via G63110FE", "", "glycan_xref_subsumption" ], [ "G80375GX", "", "Homo sapiens", "Subsumption", "Subsumption", "via G19889ZI", "", "glycan_xref_subsumption" ], [ "G17593CN", "", "Mus musculus", "Subsumption", "Subsumption", "via G60230OQ", "", "glycan_xref_subsumption" ], [ "G17593CN", "", "Mus musculus", "Subsumption", "Subsumption", "via G97489LK", "", "glycan_xref_subsumption" ], [ "G99580PT", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G01767JJ", "", "glycan_xref_subsumption" ], [ "G99580PT", "10090", "Mus musculus", "Direct", "GlyTouCan", "G99580PT", "", "glycan_xref_glytoucan" ], [ "G99580PT", "", "Homo sapiens", "Subsumption", "Subsumption", "via G01767JJ", "", "glycan_xref_subsumption" ], [ "G99580PT", "", "Homo sapiens", "Subsumption", "Subsumption", "via G83513YI", "", "glycan_xref_subsumption" ], [ "G83716SQ", "9606", "Homo sapiens", "Direct", "GlyTouCan", "G83716SQ", "", "glycan_xref_glytoucan" ], [ "G60365DR", "9606", "Homo sapiens", "Direct", "GlyTouCan", "G60365DR", "", "glycan_xref_glytoucan" ], [ "G38979OV", "9606", "Homo sapiens", "Direct", "GlyTouCan", "G38979OV", "", "glycan_xref_glytoucan" ], [ "G72011DH", "", "Rattus norvegicus", "Subsumption", "Subsumption", "via G48648VZ", "", "glycan_xref_subsumption" ], [ "G72011DH", "", "Mus musculus", "Subsumption", "Subsumption", "via G42295MA", "", "glycan_xref_subsumption" ], [ "G72011DH", "", "Homo sapiens", "Subsumption", "Subsumption", "via G29884LW", "", "glycan_xref_subsumption" ], [ "G72011DH", "", "Homo sapiens", "Subsumption", "Subsumption", "via G33947BV", "", "glycan_xref_subsumption" ], [ "G72011DH", "", "Homo sapiens", "Subsumption", "Subsumption", "via G42295MA", "", "glycan_xref_subsumption" ] ] }, "readme": "Name\n - Glycan Species \n\nVersion\n - 1.5.27\n\nCreated on\n - 2020-03-02T13:55:30.488616\n\nModified on\n - 2020-05-01T15:18:01.598729\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 species annotation for the associated glycan (GlyTouCan Accession) generated from direct TaxID annotation and/or inferred via subsumption. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy. Currently, species annotated generated through \"direct\" i.e TaxID annotation are utilized.\n\nDescription Domain\n Keywords\n - Glycan\n - GlyTouCan Accession\n - NCBI TaxID\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 acession 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: species.tsv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/source/species.tsv\n Output Subdomain\n Name: glycan_species.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/glycan_species.csv\n Name: glycan_species.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/glycan_species.stat.csv\n\nFields\n Name: \"original_source_id\"\n Description: \"Original source id of the species annoation for the glycan. This columns contains values where the source id is not a valid database id.\"\n Unique Values: \"212\"\n Name: \"source\"\n Description: \"Source database or method of the species annotation of the glycan\"\n Unique Values: \"3\"\n Name: \"tax_name\"\n Description: \"NCBI Taxonomy name\"\n Unique Values: \"5\"\n Name: \"annotation_category\"\n Description: \"Species annotation category of the glycan. Category could be either direct or subsumption\"\n Unique Values: \"2\"\n Name: \"source_id\"\n Description: \"source database id of the species annoation for the glycan.\"\n Unique Values: \"9630\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"14411\"\n Name: \"xref_key\"\n Description: \"\"\n Unique Values: \"4\"\n Name: \"tax_id\"\n Description: \"NCBI Taxonomic identifier annotated to the glycan\"\n Unique Values: \"6\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/glycan_species.csv" }