{ "bcoid": "GLY_000668", "title": "Fruitfly UniProtKB Xref PANTHER", "description": "The Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced ...", "filename": "fruitfly_protein_xref_panther.csv", "filetype": "csv", "categories": { "species": "Drosophila melanogaster", "molecule": "Protein", "tags": "Panther cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P40796-1...", "protein_xref..." ], [ "P40792-1...", "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" } ], [ "P40796-1", "protein_xref_panther", "PTHR22792", "PTHR22792" ], [ "P40792-1", "protein_xref_panther", "PTHR24072", "PTHR24072" ], [ "P40793-1", "protein_xref_panther", "PTHR24072", "PTHR24072" ], [ "P40798-1", "protein_xref_panther", "PTHR12360", "PTHR12360" ], [ "P08841-1", "protein_xref_panther", "PTHR11588", "PTHR11588" ], [ "Q9VE87-1", "protein_xref_panther", "PTHR23035", "PTHR23035" ], [ "P05389-1", "protein_xref_panther", "PTHR21141", "PTHR21141" ], [ "P04388-1", "protein_xref_panther", "PTHR24070", "PTHR24070" ], [ "A1ZB42-1", "protein_xref_panther", "PTHR20844", "PTHR20844" ], [ "Q9VYT1-1", "protein_xref_panther", "PTHR31634", "PTHR31634" ], [ "Q9VLI9-1", "protein_xref_panther", "PTHR23249", "PTHR23249" ], [ "Q9VLI6-1", "protein_xref_panther", "PTHR11465", "PTHR11465" ], [ "Q95RA8-1", "protein_xref_panther", "PTHR22599", "PTHR22599" ], [ "Q27869-1", "protein_xref_panther", "PTHR11579", "PTHR11579" ], [ "E1JH39-1", "protein_xref_panther", "PTHR14625", "PTHR14625" ], [ "M9PEM2-1", "protein_xref_panther", "PTHR22774", "PTHR22774" ], [ "Q95R35-1", "protein_xref_panther", "PTHR11963", "PTHR11963" ], [ "Q9VME8-1", "protein_xref_panther", "PTHR11690", "PTHR11690" ], [ "Q9VME9-1", "protein_xref_panther", "PTHR11690", "PTHR11690" ], [ "Q9VME2-1", "protein_xref_panther", "PTHR11733", "PTHR11733" ], [ "Q9VME3-1", "protein_xref_panther", "PTHR11733", "PTHR11733" ], [ "Q9VVS2-1", "protein_xref_panther", "PTHR11224:SF38", "PTHR11224:SF38" ], [ "Q9VVS2-1", "protein_xref_panther", "PTHR11224", "PTHR11224" ], [ "Q9VZZ6-1", "protein_xref_panther", "PTHR21660", "PTHR21660" ], [ "A1ZAX1-1", "protein_xref_panther", "PTHR13937", "PTHR13937" ], [ "P17336-1", "protein_xref_panther", "PTHR11465", "PTHR11465" ], [ "A0A0B4KFC9-1", "protein_xref_panther", "PTHR12147", "PTHR12147" ], [ "P56079-1", "protein_xref_panther", "PTHR13773", "PTHR13773" ], [ "Q9VWS0-1", "protein_xref_panther", "PTHR10333:SF99", "PTHR10333:SF99" ], [ "Q9VWS0-1", "protein_xref_panther", "PTHR10333", "PTHR10333" ], [ "Q9VWS2-1", "protein_xref_panther", "PTHR21527", "PTHR21527" ], [ "Q9VWS3-1", "protein_xref_panther", "PTHR15746", "PTHR15746" ], [ "G4LU05-1", "protein_xref_panther", "PTHR45645:SF22", "PTHR45645:SF22" ], [ "Q8SYY6-1", "protein_xref_panther", "PTHR15601", "PTHR15601" ], [ "Q9Y137-1", "protein_xref_panther", "PTHR12563", "PTHR12563" ], [ "P48554-1", "protein_xref_panther", "PTHR24072", "PTHR24072" ], [ "P48555-1", "protein_xref_panther", "PTHR24070", "PTHR24070" ], [ "A0A0B4JDC9-1", "protein_xref_panther", "PTHR14234", "PTHR14234" ], [ "Q9W277-1", "protein_xref_panther", "PTHR11099", "PTHR11099" ], [ "Q9VGU5-1", "protein_xref_panther", "PTHR23184", "PTHR23184" ], [ "Q9VUR3-1", "protein_xref_panther", "PTHR13438", "PTHR13438" ], [ "Q9V969-1", "protein_xref_panther", "PTHR21143", "PTHR21143" ], [ "Q9V968-1", "protein_xref_panther", "PTHR12377", "PTHR12377" ], [ "Q9VUR2-1", "protein_xref_panther", "PTHR14150", "PTHR14150" ], [ "P11996-1", "protein_xref_panther", "PTHR11511", "PTHR11511" ], [ "P11997-1", "protein_xref_panther", "PTHR11511", "PTHR11511" ], [ "P11995-1", "protein_xref_panther", "PTHR11511", "PTHR11511" ], [ "A1Z8T6-1", "protein_xref_panther", "PTHR21439", "PTHR21439" ], [ "A1Z8T9-1", "protein_xref_panther", "PTHR11886", "PTHR11886" ], [ "A1ZAI5-1", "protein_xref_panther", "PTHR11011", "PTHR11011" ], [ "A1ZAI1-1", "protein_xref_panther", "PTHR13205", "PTHR13205" ], [ "A1ZAI1-1", "protein_xref_panther", "PTHR13205:SF15", "PTHR13205:SF15" ], [ "A1ZAI3-1", "protein_xref_panther", "PTHR11011", "PTHR11011" ], [ "Q8IR55-1", "protein_xref_panther", "PTHR18902:SF26", "PTHR18902:SF26" ], [ "O61492-1", "protein_xref_panther", "PTHR13806", "PTHR13806" ], [ "Q9VXY2-1", "protein_xref_panther", "PTHR13008", "PTHR13008" ], [ "P07487-1", "protein_xref_panther", "PTHR10836", "PTHR10836" ], [ "P27619-1", "protein_xref_panther", "PTHR11566", "PTHR11566" ], [ "P27619-1", "protein_xref_panther", "PTHR11566:SF32", "PTHR11566:SF32" ], [ "Q01583-4", "protein_xref_panther", "PTHR11255", "PTHR11255" ], [ "M9PDV2-1", "protein_xref_panther", "PTHR19282", "PTHR19282" ], [ "Q9W0E3-1", "protein_xref_panther", "PTHR13179", "PTHR13179" ], [ "A0A0C4DHA5-1", "protein_xref_panther", "PTHR12507", "PTHR12507" ], [ "A1Z9R1-1", "protein_xref_panther", "PTHR22792", "PTHR22792" ], [ "Q9V727-1", "protein_xref_panther", "PTHR13578", "PTHR13578" ], [ "Q9V727-1", "protein_xref_panther", "PTHR13578:SF20", "PTHR13578:SF20" ], [ "Q9VTC2-1", "protein_xref_panther", "PTHR16230", "PTHR16230" ], [ "A0A0B4K6N4-1", "protein_xref_panther", "PTHR10901", "PTHR10901" ], [ "A0A0B4K6N4-1", "protein_xref_panther", "PTHR10901:SF6", "PTHR10901:SF6" ], [ "Q04499-1", "protein_xref_panther", "PTHR13914", "PTHR13914" ], [ "Q9VST7-1", "protein_xref_panther", "PTHR20933", "PTHR20933" ], [ "Q24173-1", "protein_xref_panther", "PTHR11774", "PTHR11774" ], [ "Q9VKQ9-1", "protein_xref_panther", "PTHR23356", "PTHR23356" ], [ "Q9VKQ5-1", "protein_xref_panther", "PTHR16188", "PTHR16188" ], [ "A0A0B4K7J3-1", "protein_xref_panther", "PTHR23255", "PTHR23255" ], [ "A1ZBY3-1", "protein_xref_panther", "PTHR23279", "PTHR23279" ], [ "Q7KUN6-1", "protein_xref_panther", "PTHR20934", "PTHR20934" ], [ "A0A0B4KFS5-1", "protein_xref_panther", "PTHR12366", "PTHR12366" ], [ "B7YZL3-1", "protein_xref_panther", "PTHR21119", "PTHR21119" ], [ "Q9VE04-1", "protein_xref_panther", "PTHR34095", "PTHR34095" ], [ "A0A0B4K8B1-1", "protein_xref_panther", "PTHR11610", "PTHR11610" ], [ "Q9W1G4-1", "protein_xref_panther", "PTHR19863", "PTHR19863" ], [ "Q9W1G7-1", "protein_xref_panther", "PTHR11875", "PTHR11875" ], [ "A0A0B4LGD3-1", "protein_xref_panther", "PTHR11827:SF66", "PTHR11827:SF66" ] ] }, "readme": "Name\n - Fruitfly UniProtKB Xref PANTHER\n\nVersion\n - v-x.x.x\n\nCreated on\n - 2022-08-31T13:34:27.210052\n\nModified on\n - 2022-08-31T13:34:44.312588\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@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 Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products.\n\nDescription Domain\n Keywords\n - protein family\n - PANTHER\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER 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-drosophila-melanogaster.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2022_03/uniprot-proteome-drosophila-melanogaster.nt\n Output Subdomain\n Name: fruitfly_protein_xref_panther.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.csv\n Name: fruitfly_protein_xref_panther.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"5118\"\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: \"3156\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"3156\"", "downloadurl": "/ln2data/releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_panther.csv" }