{ "bcoid": "GLY_000234", "title": "Rat UniProtKB Xref CDD", "description": "The Rat UniProtKB Xref CDD contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...", "filename": "rat_protein_xref_cdd.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Cdd cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q5RJK9-1...", "protein_xref..." ], [ "D3ZG10-1...", "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_cdd", "cd07032", "RNAP_I_II_AC40" ], [ "D3ZG10-1", "protein_xref_cdd", "cd11950", "SH3_GRAP2_C" ], [ "D3ZB44-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "P30349-1", "protein_xref_cdd", "cd09599", "M1_LTA4H" ], [ "A0A0G2K0H3-1", "protein_xref_cdd", "cd00112", "LDLa" ], [ "D4AAV0-1", "protein_xref_cdd", "cd00103", "IRF" ], [ "M0R5G5-1", "protein_xref_cdd", "cd01752", "PLAT_polycystin" ], [ "Q9QX69-1", "protein_xref_cdd", "cd04794", "euk_LANCL" ], [ "P30348-1", "protein_xref_cdd", "cd00273", "Chemokine_CXC" ], [ "A0A096MJY8-1", "protein_xref_cdd", "cd00751", "thiolase" ], [ "A0A096MJY4-1", "protein_xref_cdd", "cd00265", "MADS_MEF2_like" ], [ "O88181-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "Q2KN99-1", "protein_xref_cdd", "cd00014", "CH" ], [ "O55043-1", "protein_xref_cdd", "cd00160", "RhoGEF" ], [ "O55043-1", "protein_xref_cdd", "cd12061", "SH3_betaPIX" ], [ "A0A0G2K5R6-1", "protein_xref_cdd", "cd03593", "CLECT_NK_receptors_like" ], [ "D4A830-1", "protein_xref_cdd", "cd00412", "pyrophosphatase" ], [ "D4A834-1", "protein_xref_cdd", "cd03598", "CLECT_EMBP_like" ], [ "M0R6T1-1", "protein_xref_cdd", "cd01310", "TatD_DNAse" ], [ "P01946-1", "protein_xref_cdd", "cd08927", "Hb-alpha_like" ], [ "P20646-1", "protein_xref_cdd", "cd07061", "HP_HAP_like" ], [ "Q5BK10-1", "protein_xref_cdd", "cd00044", "CysPc" ], [ "O35152-1", "protein_xref_cdd", "cd15853", "SNARE_Bet1" ], [ "P48965-1", "protein_xref_cdd", "cd01530", "Cdc25" ], [ "P48966-1", "protein_xref_cdd", "cd01530", "Cdc25" ], [ "P48961-1", "protein_xref_cdd", "cd00043", "CYCLIN" ], [ "O35158-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "M0R7U1-1", "protein_xref_cdd", "cd01428", "ADK" ], [ "Q9QYH1-1", "protein_xref_cdd", "cd12034", "SH3_MPP4" ], [ "D4A4W8-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "D4A4W6-1", "protein_xref_cdd", "cd12242", "RRM_SLIRP" ], [ "P63076-1", "protein_xref_cdd", "cd00058", "FGF" ], [ "M0R9X4-1", "protein_xref_cdd", "cd00167", "SANT" ], [ "M0R9X4-1", "protein_xref_cdd", "cd02341", "ZZ_ZZZ3" ], [ "D3ZVN9-1", "protein_xref_cdd", "cd06224", "REM" ], [ "D3ZVN9-1", "protein_xref_cdd", "cd00155", "RasGEF" ], [ "D3ZDS8-1", "protein_xref_cdd", "cd00085", "HNHc" ], [ "P39020-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "Q2VWP9-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "D4AEG2-1", "protein_xref_cdd", "cd04107", "Rab32_Rab38" ], [ "M0RBX2-1", "protein_xref_cdd", "cd09587", "SAM_HARP" ], [ "M0RBX4-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "A0A0G2JZ70-1", "protein_xref_cdd", "cd07981", "TAF12" ], [ "P62804-1", "protein_xref_cdd", "cd00076", "H4" ], [ "Q5I2P1-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "P24135-1", "protein_xref_cdd", "cd09932", "SH2_C-SH2_PLC_gamma_like" ], [ "P24135-1", "protein_xref_cdd", "cd10341", "SH2_N-SH2_PLC_gamma_like" ], [ "P24135-1", "protein_xref_cdd", "cd11969", "SH3_PLCgamma2" ], [ "D3ZLN7-1", "protein_xref_cdd", "cd04750", "Commd2" ], [ "P61227-1", "protein_xref_cdd", "cd04176", "Rap2" ], [ "Q08290-1", "protein_xref_cdd", "cd00014", "CH" ], [ "Q9QZH2-1", "protein_xref_cdd", "cd16496", "RING-HC_BARD1" ], [ "P01230-1", "protein_xref_cdd", "cd00069", "GHB_like" ], [ "B1WBV2-1", "protein_xref_cdd", "cd07446", "CRD_SFRP2" ], [ "B1WBV4-1", "protein_xref_cdd", "cd01218", "PH_Phafin2-like" ], [ "P22273-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "Q09167-1", "protein_xref_cdd", "cd12337", "RRM1_SRSF4_like" ], [ "P18590-1", "protein_xref_cdd", "cd08771", "DLP_1" ], [ "D3Z8C9-1", "protein_xref_cdd", "cd00077", "HDc" ], [ "D3ZC98-1", "protein_xref_cdd", "cd00043", "CYCLIN" ], [ "M0R5G2-1", "protein_xref_cdd", "cd11677", "Gemin7" ], [ "D4A7X9-1", "protein_xref_cdd", "cd01378", "MYSc_Myo1" ], [ "D4A7X9-1", "protein_xref_cdd", "cd11827", "SH3_MyoIe_If_like" ], [ "Q9JHY7-1", "protein_xref_cdd", "cd00022", "BIR" ], [ "A0A0G2JUC9-1", "protein_xref_cdd", "cd00078", "HECTc" ], [ "A0A0G2JUC9-1", "protein_xref_cdd", "cd08664", "APC10-HERC2" ], [ "A0A0G2JUC9-1", "protein_xref_cdd", "cd02344", "ZZ_HERC2" ], [ "D3ZXV0-1", "protein_xref_cdd", "cd00195", "UBCc" ], [ "D3ZV50-1", "protein_xref_cdd", "cd00165", "S4" ], [ "P23358-1", "protein_xref_cdd", "cd00349", "Ribosomal_L11" ], [ "Q4TU78-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P84817-1", "protein_xref_cdd", "cd12212", "Fis1" ], [ "O08629-1", "protein_xref_cdd", "cd00021", "BBOX" ], [ "O08629-1", "protein_xref_cdd", "cd16765", "RING-HC_TIF1beta" ], [ "O08628-1", "protein_xref_cdd", "cd03576", "NTR_PCOLCE" ], [ "O08628-1", "protein_xref_cdd", "cd00041", "CUB" ], [ "F1LW16-1", "protein_xref_cdd", "cd17999", "DEXHc_Mot1" ], [ "Q02765-1", "protein_xref_cdd", "cd02248", "Peptidase_C1A" ], [ "F7FKH2-1", "protein_xref_cdd", "cd05841", "BS69_related" ], [ "P06866-1", "protein_xref_cdd", "cd00033", "CCP" ], [ "P06866-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ], [ "P85845-1", "protein_xref_cdd", "cd00257", "Fascin" ], [ "P83645-1", "protein_xref_cdd", "cd00340", "GSH_Peroxidase" ], [ "O88182-1", "protein_xref_cdd", "cd00058", "FGF" ] ] }, "readme": "Name\n - Rat UniProtKB Xref CDD\n\nVersion\n - 1.8.25\n\nCreated on\n - 2019-09-06T14:06:38.961924\n\nModified on\n - 2020-04-10T11:55:22.166613\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 UniProtKB Xref CDD contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CDD 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 - The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins.\n\nDescription Domain\n Keywords\n - protein domains\n - CDD\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to CDD 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-1.8.25/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_xref_cdd.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_xref_cdd.csv\n Name: rat_protein_xref_cdd.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_xref_cdd.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-1.8.25/reviewed/rat_protein_xref_cdd.csv" }