{ "bcoid": "GLY_000276", "title": "Rat UniProtKB Xref RefSeq", "description": "The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced ...", "filename": "rat_protein_xref_refseq.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Refseq cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q5RJK9-1...", "protein_xref..." ], [ "Q5RJK9-1...", "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" } ], [ "Q5RJK9-1", "protein_xref_refseq", "NP_001008331.1", "" ], [ "Q5RJK9-1", "protein_xref_refseq", "NP_001008331", "" ], [ "Q5RJK8-1", "protein_xref_refseq", "NP_001011906.1", "" ], [ "Q5RJK8-1", "protein_xref_refseq", "NP_001011906", "" ], [ "D3ZB44-1", "protein_xref_refseq", "XP_006223048.1", "" ], [ "D3ZB44-1", "protein_xref_refseq", "XP_006223048", "" ], [ "Q5RJK0-1", "protein_xref_refseq", "NP_001008359.1", "" ], [ "Q5RJK0-1", "protein_xref_refseq", "NP_001008359", "" ], [ "Q5RJK3-1", "protein_xref_refseq", "NP_001013108.1", "" ], [ "Q5RJK3-1", "protein_xref_refseq", "NP_001013108", "" ], [ "P30349-1", "protein_xref_refseq", "NP_001025202.1", "" ], [ "P30349-1", "protein_xref_refseq", "NP_001025202", "" ], [ "Q5RJK5-1", "protein_xref_refseq", "NP_001008314.2", "" ], [ "Q5RJK5-1", "protein_xref_refseq", "NP_001008314", "" ], [ "D3ZB48-1", "protein_xref_refseq", "NP_001101416.1", "" ], [ "D3ZB48-1", "protein_xref_refseq", "NP_001101416", "" ], [ "Q5RJK6-1", "protein_xref_refseq", "NP_001012131.1", "" ], [ "Q5RJK6-1", "protein_xref_refseq", "NP_001012131", "" ], [ "Q6MG55-1", "protein_xref_refseq", "NP_997696.1", "" ], [ "Q6MG55-1", "protein_xref_refseq", "NP_997696", "" ], [ "Q6MG56-1", "protein_xref_refseq", "NP_001003691.1", "" ], [ "Q6MG56-1", "protein_xref_refseq", "NP_001003691", "" ], [ "A0A0G2K0H3-1", "protein_xref_refseq", "XP_017448147.1", "" ], [ "A0A0G2K0H3-1", "protein_xref_refseq", "XP_017448147", "" ], [ "Q5XIH0-1", "protein_xref_refseq", "NP_001014107.1", "" ], [ "Q5XIH0-1", "protein_xref_refseq", "NP_001014107", "" ], [ "Q6MG51-1", "protein_xref_refseq", "NP_001003975.1", "" ], [ "Q6MG51-1", "protein_xref_refseq", "NP_001003975", "" ], [ "F1M2W7-1", "protein_xref_refseq", "NP_001100387.1", "" ], [ "F1M2W7-1", "protein_xref_refseq", "NP_001100387", "" ], [ "Q6MG53-1", "protein_xref_refseq", "NP_001001934.1", "" ], [ "Q6MG53-1", "protein_xref_refseq", "NP_001001934", "" ], [ "D4AAV0-1", "protein_xref_refseq", "NP_001102329.1", "" ], [ "D4AAV0-1", "protein_xref_refseq", "NP_001102329", "" ], [ "P20961-1", "protein_xref_refseq", "NP_036752.1", "" ], [ "P20961-1", "protein_xref_refseq", "NP_036752", "" ], [ "Q6MG59-1", "protein_xref_refseq", "NP_001003976.1", "" ], [ "Q6MG59-1", "protein_xref_refseq", "NP_001003976", "" ], [ "Q4KLP0-1", "protein_xref_refseq", "NP_001020891.1", "" ], [ "Q4KLP0-1", "protein_xref_refseq", "NP_001020891", "" ], [ "M0RAP6-1", "protein_xref_refseq", "XP_002725195.1", "" ], [ "M0RAP6-1", "protein_xref_refseq", "XP_002725195", "" ], [ "M0RAP5-1", "protein_xref_refseq", "NP_001258102.1", "" ], [ "M0RAP5-1", "protein_xref_refseq", "NP_001258102", "" ], [ "A0A0G2JVG8-1", "protein_xref_refseq", "NP_001000969.1", "" ], [ "A0A0G2JVG8-1", "protein_xref_refseq", "NP_001000969", "" ], [ "F1M1W4-1", "protein_xref_refseq", "NP_001101860.2", "" ], [ "F1M1W4-1", "protein_xref_refseq", "NP_001101860", "" ], [ "P34997-1", "protein_xref_refseq", "NP_445755.1", "" ], [ "P34997-1", "protein_xref_refseq", "NP_445755", "" ], [ "Q9WUD9-1", "protein_xref_refseq", "NP_114183.1", "" ], [ "Q9WUD9-1", "protein_xref_refseq", "NP_114183", "" ], [ "Q8R553-1", "protein_xref_refseq", "NP_599203.1", "" ], [ "Q8R553-1", "protein_xref_refseq", "NP_599203", "" ], [ "Q925Q4-1", "protein_xref_refseq", "NP_598303.1", "" ], [ "Q925Q4-1", "protein_xref_refseq", "NP_598303", "" ], [ "Q9QX69-1", "protein_xref_refseq", "NP_446175.1", "" ], [ "Q9QX69-1", "protein_xref_refseq", "NP_446175", "" ], [ "P30348-1", "protein_xref_refseq", "NP_446099.1", "" ], [ "P30348-1", "protein_xref_refseq", "NP_446099", "" ], [ "Q9WUD2-1", "protein_xref_refseq", "NP_001257726.1", "" ], [ "Q9WUD2-1", "protein_xref_refseq", "NP_001257726", "" ], [ "A0A0G2JUK9-1", "protein_xref_refseq", "NP_001000297.1", "" ], [ "A0A0G2JUK9-1", "protein_xref_refseq", "NP_001000297", "" ], [ "D3ZLV0-1", "protein_xref_refseq", "NP_001000397.1", "" ], [ "D3ZLV0-1", "protein_xref_refseq", "NP_001000397", "" ], [ "D3ZLV5-1", "protein_xref_refseq", "NP_001102138.1", "" ], [ "D3ZLV5-1", "protein_xref_refseq", "NP_001102138", "" ], [ "Q8VHI8-1", "protein_xref_refseq", "NP_543173.1", "" ], [ "Q8VHI8-1", "protein_xref_refseq", "NP_543173", "" ], [ "D3ZLV9-1", "protein_xref_refseq", "NP_001127976.1", "" ], [ "D3ZLV9-1", "protein_xref_refseq", "NP_001127976", "" ], [ "A0A096MJY4-1", "protein_xref_refseq", "XP_006224017.1", "" ], [ "A0A096MJY4-1", "protein_xref_refseq", "XP_006224017", "" ], [ "O88181-1", "protein_xref_refseq", "NP_075245.1", "" ], [ "O88181-1", "protein_xref_refseq", "NP_075245", "" ], [ "A0A096MJY1-1", "protein_xref_refseq", "XP_001077762.3", "" ], [ "A0A096MJY1-1", "protein_xref_refseq", "XP_001077762", "" ], [ "Q2KMM2-1", "protein_xref_refseq", "NP_001034467.1", "" ], [ "Q2KMM2-1", "protein_xref_refseq", "NP_001034467", "" ], [ "Q2KN99-1", "protein_xref_refseq", "NP_001034544.1", "" ], [ "Q2KN99-1", "protein_xref_refseq", "NP_001034544", "" ], [ "D4A838-1", "protein_xref_refseq", "NP_001000505.1", "" ], [ "D4A838-1", "protein_xref_refseq", "NP_001000505", "" ] ] }, "readme": "Name\n - Rat UniProtKB Xref RefSeq\n\nVersion\n - 1.8.24\n\nCreated on\n - 2019-09-06T14:06:39.002473\n\nModified on\n - 2020-04-10T12:10:48.820805\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 Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein.\n\nDescription Domain\n Keywords\n - protein accessions\n - RefSeq\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq 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-rattus-norvegicus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_xref_refseq.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_refseq.csv\n Name: rat_protein_xref_refseq.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_refseq.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/rat_protein_xref_refseq.csv" }