{ "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": [ [ "Q0HA29-1...", "protein_xref..." ], [ "A0A0G2JVG6-1...", "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" } ], [ "Q0HA29-1", "protein_xref_cdd", "cd09286", "NMNAT_Eukarya" ], [ "A0A0G2JVG6-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "A0A0G2K069-1", "protein_xref_cdd", "cd00110", "LamG" ], [ "O35152-1", "protein_xref_cdd", "cd15853", "SNARE_Bet1" ], [ "O35158-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "Q9QYH1-1", "protein_xref_cdd", "cd12034", "SH3_MPP4" ], [ "D4A4W8-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "D4A4W2-1", "protein_xref_cdd", "cd13132", "MATE_eukaryotic" ], [ "D4A4W6-1", "protein_xref_cdd", "cd12242", "RRM_SLIRP" ], [ "P01230-1", "protein_xref_cdd", "cd00069", "GHB_like" ], [ "Q9JHY7-1", "protein_xref_cdd", "cd00022", "BIR" ], [ "Q9WU49-1", "protein_xref_cdd", "cd04458", "CSP_CDS" ], [ "P30277-1", "protein_xref_cdd", "cd00043", "CYCLIN" ], [ "F7FHL6-1", "protein_xref_cdd", "cd16663", "RING-Ubox_PPIL2" ], [ "Q05474-1", "protein_xref_cdd", "cd01793", "Ubl_FUBI" ], [ "Q5XI22-1", "protein_xref_cdd", "cd00751", "thiolase" ], [ "P83748-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ], [ "E9PTQ3-1", "protein_xref_cdd", "cd04269", "ZnMc_adamalysin_II_like" ], [ "P84083-1", "protein_xref_cdd", "cd04150", "Arf1_5_like" ], [ "A0A8I5ZRF2-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "A0A8I6A0U5-1", "protein_xref_cdd", "cd01459", "vWA_copine_like" ], [ "A0A8I6A0U5-1", "protein_xref_cdd", "cd04047", "C2B_Copine" ], [ "Q62952-1", "protein_xref_cdd", "cd01314", "D-HYD" ], [ "A0A8I6GKG1-1", "protein_xref_cdd", "cd01718", "Sm_E" ], [ "O88553-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "P09875-1", "protein_xref_cdd", "cd03784", "GT1_Gtf-like" ], [ "A0A8I5ZPP3-1", "protein_xref_cdd", "cd07936", "SCAN" ], [ "A0A8I5ZPP3-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "G3V723-1", "protein_xref_cdd", "cd08662", "M13" ], [ "D3ZCS4-1", "protein_xref_cdd", "cd00014", "CH" ], [ "D3ZCS4-1", "protein_xref_cdd", "cd00201", "WW" ], [ "D3ZCS9-1", "protein_xref_cdd", "cd05822", "TLP_HIUase" ], [ "Q64535-1", "protein_xref_cdd", "cd00371", "HMA" ], [ "A0A0G2KAH3-1", "protein_xref_cdd", "cd00182", "TBOX" ], [ "D3ZXJ0-1", "protein_xref_cdd", "cd00094", "HX" ], [ "D3ZXJ0-1", "protein_xref_cdd", "cd04278", "ZnMc_MMP" ], [ "D3ZB41-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "D9I2F9-1", "protein_xref_cdd", "cd08330", "CARD_ASC_NALP1" ], [ "F1LP13-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "F1LP13-1", "protein_xref_cdd", "cd03122", "alpha_CARP_receptor_like" ], [ "A0A0G2JVZ2-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P81377-1", "protein_xref_cdd", "cd00038", "CAP_ED" ], [ "Q63184-1", "protein_xref_cdd", "cd19903", "DSRM_EIF2AK2_rpt1" ], [ "Q6AYA4-1", "protein_xref_cdd", "cd00161", "RICIN" ], [ "Q6AYA4-1", "protein_xref_cdd", "cd02510", "pp-GalNAc-T" ], [ "P14046-1", "protein_xref_cdd", "cd02897", "A2M_2" ], [ "A0A8I5ZR91-1", "protein_xref_cdd", "cd16023", "GPI_EPT_3" ], [ "D3ZT68-1", "protein_xref_cdd", "cd01175", "IPT_COE" ], [ "D3ZT68-1", "protein_xref_cdd", "cd11606", "COE_DBD" ], [ "Q9EPW1-1", "protein_xref_cdd", "cd00130", "PAS" ], [ "D4AE81-1", "protein_xref_cdd", "cd00160", "RhoGEF" ], [ "D4AE81-1", "protein_xref_cdd", "cd13243", "PH_PLEKHG1_G2_G3" ], [ "D4AE82-1", "protein_xref_cdd", "cd00201", "WW" ], [ "Q1M168-1", "protein_xref_cdd", "cd00170", "SEC14" ], [ "A0A0G2JXN2-1", "protein_xref_cdd", "cd12895", "SPRY_PRY_TRIM46" ], [ "A0A0G2JXN2-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "E9PSY0-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "F1M348-1", "protein_xref_cdd", "cd00190", "Tryp_SPc" ], [ "A0A8I6ADY1-1", "protein_xref_cdd", "cd00042", "CY" ], [ "P21575-1", "protein_xref_cdd", "cd08771", "DLP_1" ], [ "P21775-1", "protein_xref_cdd", "cd00751", "thiolase" ], [ "O88302-1", "protein_xref_cdd", "cd00066", "G-alpha" ], [ "Q64604-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "A0A0G2JV12-1", "protein_xref_cdd", "cd00247", "Endostatin-like" ], [ "A0A0G2JV16-1", "protein_xref_cdd", "cd08697", "C2_Dock-D" ], [ "F1LVJ0-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "A0A8I5ZSG2-1", "protein_xref_cdd", "cd15578", "PHD1_MTF2" ], [ "A0A8I5ZSG2-1", "protein_xref_cdd", "cd15580", "PHD2_MTF2" ], [ "A0A8I5ZSG2-1", "protein_xref_cdd", "cd04508", "TUDOR" ], [ "Q6IN33-1", "protein_xref_cdd", "cd12708", "RRM_RCAN1" ], [ "A0A8J8XEJ8-1", "protein_xref_cdd", "cd14947", "NBR1_like" ], [ "A0A8J8XEJ8-1", "protein_xref_cdd", "cd14349", "UBA_CF106" ], [ "M0R835-1", "protein_xref_cdd", "cd12241", "RRM_SF3B14" ], [ "Q5U2Y3-1", "protein_xref_cdd", "cd12033", "SH3_MPP7" ], [ "P35434-1", "protein_xref_cdd", "cd12152", "F1-ATPase_delta" ], [ "Q812E8-1", "protein_xref_cdd", "cd00553", "NAD_synthase" ], [ "Q63285-1", "protein_xref_cdd", "cd12465", "RRM_UHMK1" ], [ "Q9QZR6-1", "protein_xref_cdd", "cd01850", "CDC_Septin" ], [ "D3ZEJ0-1", "protein_xref_cdd", "cd19196", "PR-SET_PRDM12" ], [ "D3ZEJ6-1", "protein_xref_cdd", "cd03729", "SOCS_ASB13" ], [ "Q62844-1", "protein_xref_cdd", "cd12006", "SH3_Fyn_Yrk" ], [ "Q62735-1", "protein_xref_cdd", "cd06936", "NR_LBD_Fxr" ], [ "P40329-1", "protein_xref_cdd", "cd00671", "ArgRS_core" ], [ "Q792H5-1", "protein_xref_cdd", "cd12631", "RRM1_CELF1_2_Bruno" ] ] }, "readme": "Name\n - Rat UniProtKB Xref CDD\n\nVersion\n - v-2.0.3\n\nCreated on\n - 2019-09-06T14:06:38.961924\n\nModified on\n - 2022-09-26T09:04:47.933127\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/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-rattus-norvegicus.nt\n URI: /data/shared/glyds/downloads/ebi/2022_05/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_xref_cdd.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_xref_cdd.csv\n Name: rat_protein_xref_cdd.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_xref_cdd.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"5089\"\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: \"2220\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"2220\"", "downloadurl": "/ln2data/releases/data/v-2.0.3/reviewed/rat_protein_xref_cdd.csv" }