{ "bcoid": "GLY_000095", "title": "Human UniProtKB Xref CAZy", "description": "The Human UniprotKB Xref CAZy contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_cazy.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Cazy", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q99519-1...", "protein_xref..." ], [ "Q00973-1...", "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" } ], [ "Q99519-1", "protein_xref_cazy", "GH33", "Glycoside Hydrolase Family 33" ], [ "Q00973-1", "protein_xref_cazy", "GT12", "Glycosyltransferase Family 12" ], [ "Q9UEF7-1", "protein_xref_cazy", "GH1", "Glycoside Hydrolase Family 1" ], [ "Q9H7J1-1", "protein_xref_cazy", "CBM21", "Carbohydrate-Binding Module Family 21" ], [ "Q86X52-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q86X52-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "O95210-1", "protein_xref_cazy", "CBM20", "Carbohydrate-Binding Module Family 20" ], [ "Q9Y644-1", "protein_xref_cazy", "GT31", "Glycosyltransferase Family 31" ], [ "Q6UWU2-1", "protein_xref_cazy", "GH35", "Glycoside Hydrolase Family 35" ], [ "Q6NUS8-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q14165-1", "protein_xref_cazy", "CBM57", "Carbohydrate-Binding Module Family 57" ], [ "Q11201-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q11203-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "P61626-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "Q12794-1", "protein_xref_cazy", "GH56", "Glycoside Hydrolase Family 56" ], [ "P22310-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q8TET4-1", "protein_xref_cazy", "GH31", "Glycoside Hydrolase Family 31" ], [ "O75795-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "O60656-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q7Z4W2-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "Q09327-1", "protein_xref_cazy", "GT17", "Glycosyltransferase Family 17" ], [ "Q09328-1", "protein_xref_cazy", "GT18", "Glycosyltransferase Family 18" ], [ "Q9H3S5-1", "protein_xref_cazy", "GT50", "Glycosyltransferase Family 50" ], [ "O60762-1", "protein_xref_cazy", "GT2", "Glycosyltransferase Family 2" ], [ "Q9P109-1", "protein_xref_cazy", "GT14", "Glycosyltransferase Family 14" ], [ "Q2TAA5-1", "protein_xref_cazy", "GT4", "Glycosyltransferase Family 4" ], [ "Q96KX0-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "Q96QH8-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "O75951-1", "protein_xref_cazy", "GH22", "Glycoside Hydrolase Family 22" ], [ "Q9HCG7-1", "protein_xref_cazy", "GH116", "Glycoside Hydrolase Family 116" ], [ "Q92685-1", "protein_xref_cazy", "GT58", "Glycosyltransferase Family 58" ], [ "Q92611-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q9Y2G5-3", "protein_xref_cazy", "GT68", "Glycosyltransferase Family 68" ], [ "Q6P4F1-1", "protein_xref_cazy", "GT10", "Glycosyltransferase Family 10" ], [ "Q96JF0-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "P16662-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q8NFI3-1", "protein_xref_cazy", "GH85", "Glycoside Hydrolase Family 85" ], [ "O60909-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q9H6U8-1", "protein_xref_cazy", "GT22", "Glycosyltransferase Family 22" ], [ "A0PJZ3-1", "protein_xref_cazy", "GT8", "Glycosyltransferase Family 8" ], [ "Q9Y231-1", "protein_xref_cazy", "GT10", "Glycosyltransferase Family 10" ], [ "Q9Y6A1-1", "protein_xref_cazy", "GT39", "Glycosyltransferase Family 39" ], [ "Q9NPC4-1", "protein_xref_cazy", "GT32", "Glycosyltransferase Family 32" ], [ "Q9NTJ4-1", "protein_xref_cazy", "GH38", "Glycoside Hydrolase Family 38" ], [ "Q9UBV7-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "P04062-1", "protein_xref_cazy", "GH30", "Glycoside Hydrolase Family 30" ], [ "Q68DE3-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q92839-1", "protein_xref_cazy", "GT2", "Glycosyltransferase Family 2" ], [ "Q13231-1", "protein_xref_cazy", "CBM14", "Carbohydrate-Binding Module Family 14" ], [ "Q13231-1", "protein_xref_cazy", "GH18", "Glycoside Hydrolase Family 18" ], [ "P21217-1", "protein_xref_cazy", "GT10", "Glycosyltransferase Family 10" ], [ "Q6UW63-1", "protein_xref_cazy", "GT90", "Glycosyltransferase Family 90" ], [ "Q8NBJ5-1", "protein_xref_cazy", "GT25", "Glycosyltransferase Family 25" ], [ "P61647-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "P38567-1", "protein_xref_cazy", "GH56", "Glycoside Hydrolase Family 56" ], [ "O15488-1", "protein_xref_cazy", "GT8", "Glycosyltransferase Family 8" ], [ "P0DUB6-1", "protein_xref_cazy", "GH13", "Glycoside Hydrolase Family 13" ], [ "O43909-1", "protein_xref_cazy", "GT47", "Glycosyltransferase Family 47" ], [ "O43909-1", "protein_xref_cazy", "GT64", "Glycosyltransferase Family 64" ], [ "Q6L9W6-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "P04746-1", "protein_xref_cazy", "GH13", "Glycoside Hydrolase Family 13" ], [ "Q5T4B2-1", "protein_xref_cazy", "GT25", "Glycosyltransferase Family 25" ], [ "P35573-1", "protein_xref_cazy", "GH133", "Glycoside Hydrolase Family 133" ], [ "P35573-1", "protein_xref_cazy", "GH13", "Glycoside Hydrolase Family 13" ], [ "Q6ZNI0-1", "protein_xref_cazy", "GT14", "Glycosyltransferase Family 14" ], [ "Q10981-1", "protein_xref_cazy", "GT11", "Glycosyltransferase Family 11" ], [ "Q6GMV1-1", "protein_xref_cazy", "GT33", "Glycosyltransferase Family 33" ], [ "P08236-1", "protein_xref_cazy", "GH2", "Glycoside Hydrolase Family 2" ], [ "Q9Y4K1-1", "protein_xref_cazy", "CBM13", "Carbohydrate-Binding Module Family 13" ], [ "Q9BZQ6-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q8NHY0-1", "protein_xref_cazy", "GT12", "Glycosyltransferase Family 12" ], [ "P54840-1", "protein_xref_cazy", "GT3", "Glycosyltransferase Family 3" ], [ "O15466-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q8TDX6-1", "protein_xref_cazy", "GT7", "Glycosyltransferase Family 7" ], [ "Q9H227-1", "protein_xref_cazy", "GH1", "Glycoside Hydrolase Family 1" ], [ "O00219-1", "protein_xref_cazy", "GT2", "Glycosyltransferase Family 2" ], [ "Q9HAW8-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q3V5L5-1", "protein_xref_cazy", "GT18", "Glycosyltransferase Family 18" ], [ "O75310-1", "protein_xref_cazy", "GT1", "Glycosyltransferase Family 1" ], [ "Q16842-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "Q13724-1", "protein_xref_cazy", "GH63", "Glycoside Hydrolase Family 63" ], [ "Q9H4F1-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ], [ "O60476-1", "protein_xref_cazy", "GH47", "Glycoside Hydrolase Family 47" ], [ "Q92187-1", "protein_xref_cazy", "GT29", "Glycosyltransferase Family 29" ] ] }, "readme": "Name\n - Human UniProtKB Xref CAZy\n\nVersion\n - 1.9.9\n\nCreated on\n - 2019-03-15T12:05:44.324142\n\nModified on\n - 2020-04-10T11:32:58.654843\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@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 Human UniprotKB Xref CAZy contains human [taxid:9606] 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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_xref_cazy.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.csv\n Name: human_protein_xref_cazy.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"1\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"1\"\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"1\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"1\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"1\"\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: \"1\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.9.9/reviewed/human_protein_xref_cazy.csv" }