{ "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": [ [ "D3ZB44-1...", "protein_xref..." ], [ "D3ZXJ3-1...", "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" } ], [ "D3ZB44-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "D3ZXJ3-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "A0A096MJY8-1", "protein_xref_cdd", "cd00751", "thiolase" ], [ "Q9QYG8-1", "protein_xref_cdd", "cd02023", "UMPK" ], [ "A0A096MJY4-1", "protein_xref_cdd", "cd00265", "MADS_MEF2_like" ], [ "P01946-1", "protein_xref_cdd", "cd08927", "Hb-alpha-like" ], [ "Q63358-1", "protein_xref_cdd", "cd00029", "C1" ], [ "Q63358-1", "protein_xref_cdd", "cd01385", "MYSc_Myo9" ], [ "O35152-1", "protein_xref_cdd", "cd15853", "SNARE_Bet1" ], [ "A0A1W2Q6N1-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "O35158-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "Q9QYH1-1", "protein_xref_cdd", "cd12034", "SH3_MPP4" ], [ "D4A4W8-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "D4A4W6-1", "protein_xref_cdd", "cd12242", "RRM_SLIRP" ], [ "P21932-1", "protein_xref_cdd", "cd07302", "CHD" ], [ "A0A0G2K5E4-1", "protein_xref_cdd", "cd06257", "DnaJ" ], [ "A0A0G2K5E4-1", "protein_xref_cdd", "cd10719", "DnaJ_zf" ], [ "P12749-1", "protein_xref_cdd", "cd06089", "KOW_RPL26" ], [ "P39020-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P11980-1", "protein_xref_cdd", "cd00288", "Pyruvate_Kinase" ], [ "P28648-1", "protein_xref_cdd", "cd03166", "CD63_LEL" ], [ "P01230-1", "protein_xref_cdd", "cd00069", "GHB_like" ], [ "M0RB75-1", "protein_xref_cdd", "cd04508", "TUDOR" ], [ "Q9JHY7-1", "protein_xref_cdd", "cd00022", "BIR" ], [ "P33568-1", "protein_xref_cdd", "cd00043", "CYCLIN" ], [ "Q02874-1", "protein_xref_cdd", "cd00074", "H2A" ], [ "Q02874-1", "protein_xref_cdd", "cd02904", "Macro_H2A-like" ], [ "P08699-1", "protein_xref_cdd", "cd00070", "GLECT" ], [ "Q05474-1", "protein_xref_cdd", "cd01793", "Ubl_FUBI" ], [ "P54690-1", "protein_xref_cdd", "cd01557", "BCAT_beta_family" ], [ "P83748-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ], [ "Q02293-1", "protein_xref_cdd", "cd02893", "FTase" ], [ "Q460M5-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "D3ZSP1-1", "protein_xref_cdd", "cd01718", "Sm_E" ], [ "D3ZYL0-1", "protein_xref_cdd", "cd08777", "Death_RIP1" ], [ "Q6B4M5-1", "protein_xref_cdd", "cd06403", "PB1_Par6" ], [ "P09875-1", "protein_xref_cdd", "cd03784", "GT1_Gtf-like" ], [ "D3ZCS4-1", "protein_xref_cdd", "cd00014", "CH" ], [ "D3ZCS4-1", "protein_xref_cdd", "cd00201", "WW" ], [ "D3ZHE6-1", "protein_xref_cdd", "cd06088", "KOW_RPL14" ], [ "D3ZCS9-1", "protein_xref_cdd", "cd05822", "TLP_HIUase" ], [ "A0A0G2KAH3-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "D3ZXJ0-1", "protein_xref_cdd", "cd00094", "HX" ], [ "D3ZXJ0-1", "protein_xref_cdd", "cd04278", "ZnMc_MMP" ], [ "D3ZXJ3-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "Q62826-1", "protein_xref_cdd", "cd12661", "RRM3_hnRNPM" ], [ "F1M0R2-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "F1LP13-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "F1LP13-1", "protein_xref_cdd", "cd03122", "alpha_CARP_receptor_like" ], [ "A0A0G2JVZ2-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "B1WC31-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "A0A096MIV6-1", "protein_xref_cdd", "cd00161", "RICIN" ], [ "D4A433-1", "protein_xref_cdd", "cd00059", "FH" ], [ "Q6MFZ5-1", "protein_xref_cdd", "cd13745", "SPRY_PRY_TRIM39" ], [ "D3ZT68-1", "protein_xref_cdd", "cd01175", "IPT_COE" ], [ "D3ZT68-1", "protein_xref_cdd", "cd11606", "COE_DBD" ], [ "F1LY04-1", "protein_xref_cdd", "cd00029", "C1" ], [ "Q9EPW1-1", "protein_xref_cdd", "cd00130", "PAS" ], [ "Q641Z2-1", "protein_xref_cdd", "cd00170", "SEC14" ], [ "Q76LT8-1", "protein_xref_cdd", "cd02668", "Peptidase_C19L" ], [ "Q76LT8-1", "protein_xref_cdd", "cd01795", "Ubl_USP48" ], [ "D4AE81-1", "protein_xref_cdd", "cd00160", "RhoGEF" ], [ "D4AE81-1", "protein_xref_cdd", "cd13243", "PH_PLEKHG1_G2_G3" ], [ "D4AE82-1", "protein_xref_cdd", "cd00201", "WW" ], [ "Q5BJS7-1", "protein_xref_cdd", "cd01459", "vWA_copine_like" ], [ "Q5BJS7-1", "protein_xref_cdd", "cd04047", "C2B_Copine" ], [ "Q5I0M4-1", "protein_xref_cdd", "cd19108", "AKR_AKR1C1-35" ], [ "Q1M168-1", "protein_xref_cdd", "cd00170", "SEC14" ], [ "A0A0G2K7P1-1", "protein_xref_cdd", "cd18808", "SF1_C_Upf1" ], [ "A0A0G2K7P9-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "M0R9X4-1", "protein_xref_cdd", "cd00167", "SANT" ], [ "M0R9X4-1", "protein_xref_cdd", "cd02341", "ZZ_ZZZ3" ], [ "D4A0A3-1", "protein_xref_cdd", "cd00033", "CCP" ], [ "D4A0A3-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ], [ "D4A0A3-1", "protein_xref_cdd", "cd00041", "CUB" ], [ "Q91Z63-1", "protein_xref_cdd", "cd16759", "RING-HC_MuRF1" ], [ "A0A0G2JXN2-1", "protein_xref_cdd", "cd12895", "SPRY_PRY_TRIM46" ], [ "A0A0G2JXN2-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "D4A676-1", "protein_xref_cdd", "cd00446", "GrpE" ], [ "D3ZH30-1", "protein_xref_cdd", "cd07895", "Adenylation_mRNA_capping" ], [ "Q5BK35-1", "protein_xref_cdd", "cd00125", "PLA2c" ], [ "E9PSY0-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "P34067-1", "protein_xref_cdd", "cd03760", "proteasome_beta_type_4" ], [ "F1M348-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ] ] }, "readme": "Name\n - Rat UniProtKB Xref CDD\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-09-06T14:06:38.961924\n\nModified on\n - 2022-01-19T12:27:22.340998\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], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@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: rat_protein_masterlist.csv\n URI: https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/rat_protein_masterlist.csv\n Name: uniprot-proteome-rattus-norvegicus.nt\n URI: https://data.glygen.org//ln2downloads/ebi/2021_03/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_xref_cdd.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/rat_protein_xref_cdd.csv\n Name: rat_protein_xref_cdd.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/rat_protein_xref_cdd.stat.csv", "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/rat_protein_xref_cdd.csv" }