{ "bcoid": "GLY_000096", "title": "Mouse UniProtKB Xref CAZy", "description": "The Mouse UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced ...", "filename": "mouse_protein_xref_cazy.csv", "filetype": "csv", "categories": { "species": [ "Mus musculus" ], "molecule": [ "Protein" ], "tag": [ "Cazy cross-references" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P70419-1...", "protein_xref..." ], [ "P70419-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_label" } ], [ "P70419-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "P70419-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "O08912-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "O08912-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "Q80W26-1", "protein_xref_cazy", "GH18", "Glycoside Hydrolase Family 18" ], [ "Q7TPN3-1", "protein_xref_cazy", "GT76", "Glycosyltransferase Family 76" ], [ "P97402-1", "protein_xref_cazy", "GT14", "Glycosyltransferase Family 14" ], [ "Q920V1-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q64435-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q3UGP8-1", "protein_xref_cazy", "GT59", "Glycosyltransferase Family 59" ], [ "Q9R2B6-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q2HXL6-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q8K1F9-1", "protein_xref_cazy", "GH1", "Glycoside Hydrolase Family 1" ], [ "Q8BJQ9-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q09324-1", "protein_xref_cazy", "GT14", "Glycosyltransferase Family 14" ], [ "Q6PB93-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "Q6PB93-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "Q9JMK0-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q6ZQ11-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q6ZQ11-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q91W89-1", "protein_xref_cazy", "GH38", "Glycoside Hydrolase Family 38" ], [ "Q8BTP0-1", "protein_xref_cazy", "GT22", "Glycosyltransferase Family 22" ], [ "Q8BHC9-1", "protein_xref_cazy", "GT10", "Glycosyltransferase Family 10" ], [ "O09160-1", "protein_xref_cazy", "GT11", "Glycosyltransferase Family 11" ], [ "Q9Z0F0-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q8R087-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q8R084-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q8K0J2-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q8BW56-1", "protein_xref_cazy", "GT4", "Glycosyltransferase Family 4" ], [ "Q91X88-1", "protein_xref_cazy", "GT13", "Glycosyltransferase Family 13" ], [ "O35632-1", "protein_xref_cazy", "GH56", "Glycoside Hydrolase Family 56" ], [ "Q9D2N8-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "Q9D2N8-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "Q7TMB3-1", "protein_xref_cazy", "CBM21", "Carbohydrate-Binding Module Family 21" ], [ "Q6P5E4-1", "protein_xref_cazy", "GT24", "Glycosyltransferase Family 24" ], [ "P54818-1", "protein_xref_cazy", "GH59", "Glycoside Hydrolase Family 59" ], [ "O09008-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "O09009-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q8VCN3-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "O35082-1", "protein_xref_cazy", "GH1", "Glycoside Hydrolase Family 1" ], [ "Q80X89-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q80W49-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "A3KGW5-1", "protein_xref_cazy", "GT25", "Glycosyltransferase Family 25" ], [ "Q9D306-1", "protein_xref_cazy", "GT54", "Glycosyltransferase Family 54" ], [ "Q8BJT9-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "A4FUP9-1", "protein_xref_cazy", "GT4", "Glycosyltransferase Family 4" ], [ "Q9DB25-1", "protein_xref_cazy", "GT2", "Glycosyltransferase Family 2" ], [ "Q8BRK9-1", "protein_xref_cazy", "GH38", "Glycoside Hydrolase Family 38" ], [ "Q8BG28-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "A6H684-1", "protein_xref_cazy", "GT54", "Glycosyltransferase Family 54" ], [ "P20060-1", "protein_xref_cazy", "GH20", "Glycoside Hydrolase Family 20" ], [ "Q9DA11-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "P17897-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "P48441-1", "protein_xref_cazy", "GH39", "Glycoside Hydrolase Family 39" ], [ "Q3U129-1", "protein_xref_cazy", "GT2", "Glycosyltransferase Family 2" ], [ "P27808-1", "protein_xref_cazy", "GT13", "Glycosyltransferase Family 13" ], [ "P12265-1", "protein_xref_cazy", "GH2", "Glycoside Hydrolase Family 2" ], [ "A0A571BF69-1", "protein_xref_cazy", "GH31", "Glycoside Hydrolase Family 31" ], [ "Q8VDI9-1", "protein_xref_cazy", "GT22", "Glycosyltransferase Family 22" ], [ "Q7TT15-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "Q7TT15-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "Q8CF93-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "Q8CF93-1", "protein_xref_cazy", "GT27", "Glycosyltransferase Family 27" ], [ "Q6NSU3-1", "protein_xref_cazy", "GT8", "Glycosyltransferase Family 8" ], [ "Q9CPX3-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "Q812G0-1", "protein_xref_cazy", "GT54", "Glycosyltransferase Family 54" ], [ "P39098-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q3TZM9-1", "protein_xref_cazy", "GT4", "Glycosyltransferase Family 4" ], [ "Q6ZQM8-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q11204-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "P23336-1", "protein_xref_cazy", "GT6", "Glycosyltransferase Family 6" ], [ "Q64685-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q64687-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q64689-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q8BGQ4-1", "protein_xref_cazy", "GT39", "Glycosyltransferase Family 39" ], [ "P12265-1", "protein_xref_cazy", "GH2", "Glycoside Hydrolase Family 2" ], [ "P97353-1", "protein_xref_cazy", "GT11", "Glycosyltransferase Family 11" ], [ "P70691-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "P48441-1", "protein_xref_cazy", "GH39", "Glycoside Hydrolase Family 39" ], [ "Q14BT6-1", "protein_xref_cazy", "GT32", "Glycosyltransferase Family 32" ], [ "Q5XPT3-1", "protein_xref_cazy", "GT8", "Glycosyltransferase Family 8" ], [ "Q5XPT3-1", "protein_xref_cazy", "GT49", "Glycosyltransferase Family 49" ], [ "P17717-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q8K2I4-1", "protein_xref_cazy", "GH2", "Glycoside Hydrolase Family 2" ] ] }, "readme": "Name\n - Mouse UniProtKB Xref CAZy\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2019-03-15T12:05:44.324142\n\nModified on\n - 2022-09-26T08:48:18.848605\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Mouse UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates\n\nDescription Domain\n Keywords\n - carbohydrate family\n - CAZy\n - glycosyltransferase\n - glycohydrolase\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-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: uniprot-proteome-mus-musculus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-mus-musculus.nt\n Output Subdomain\n Name: mouse_protein_xref_cazy.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cazy.csv\n Name: mouse_protein_xref_cazy.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_xref_cazy.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"284\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"77\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"77\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/mouse_protein_xref_cazy.csv" }