{ "bcoid": "GLY_000222", "title": "Rat Protein Recommended Names (UniProtKB)", "description": "The Rat Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for rat [taxid:10116] ...", "filename": "rat_protein_recnames.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Protein Recommended Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q5RJZ1-1...", "Regulator of..." ], [ "Q0HA29-1...", "Nicotinamide..." ] ], "headers": [ "uniprotkb_ca...", "recommended_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "recommended_name_full" }, { "type": "string", "label": "recommended_name_short" }, { "type": "string", "label": "ec_name" } ], [ "Q5RJZ1-1", "Regulator of telomere elongation helicase 1", "", "3.6.4.12" ], [ "Q0HA29-1", "Nicotinamide/nicotinic acid mononucleotide adenylyltransferase 2", "NMN/NaMN adenylyltransferase 2", "2.7.7.1" ], [ "Q0HA29-1", "Nicotinamide/nicotinic acid mononucleotide adenylyltransferase 2", "NMN/NaMN adenylyltransferase 2", "2.7.7.18" ], [ "P30938-1", "Somatostatin receptor type 5", "SS-5-R", "" ], [ "P30938-1", "Somatostatin receptor type 5", "SS5-R", "" ], [ "P30938-1", "Somatostatin receptor type 5", "SS5R", "" ], [ "A0A0G2JVG8-1", "Olfactory receptor", "", "" ], [ "Q99372-1", "Elastin", "", "" ], [ "Q07969-1", "Platelet glycoprotein 4", "", "" ], [ "Q9QYG8-1", "Uridine/cytidine kinase", "", "2.7.1.48" ], [ "A0A096MJY4-1", "Myocyte-specific enhancer factor 2C", "", "" ], [ "A0A0G2KA92-1", "DNA helicase", "", "3.6.4.12" ], [ "A0A0G2K4P4-1", "Basal body-orientation factor 1", "", "" ], [ "Q62949-1", "Cortistatin", "", "" ], [ "P01946-1", "Hemoglobin subunit alpha-1/2", "", "" ], [ "Q5M9G9-1", "FAST kinase domain-containing protein 4", "", "" ], [ "O35152-1", "BET1-like protein", "", "" ], [ "P30936-1", "Somatostatin receptor type 3", "SS-3-R", "" ], [ "P30936-1", "Somatostatin receptor type 3", "SS3-R", "" ], [ "P30936-1", "Somatostatin receptor type 3", "SS3R", "" ], [ "O35158-1", "Cell adhesion molecule-related/down-regulated by oncogenes", "", "" ], [ "P02761-1", "Major urinary protein", "MUP", "" ], [ "Q9QYH1-1", "MAGUK p55 subfamily member 4", "", "" ], [ "P02764-1", "Alpha-1-acid glycoprotein", "", "" ], [ "P02767-1", "Transthyretin", "", "" ], [ "D4A4W9-1", "60S ribosomal protein L34", "", "" ], [ "D4A4W0-1", "Olfactory receptor", "", "" ], [ "D4A4W2-1", "Multidrug and toxin extrusion protein", "", "" ], [ "D4A4W5-1", "Phospholipid-transporting ATPase", "", "7.6.2.1" ], [ "P21932-1", "Adenylate cyclase type 3", "", "4.6.1.1" ], [ "P39020-1", "Homeobox protein MOX-2", "", "" ], [ "P11980-1", "Pyruvate kinase", "", "2.7.1.40" ], [ "Q63544-1", "Gamma-synuclein", "", "" ], [ "P28648-1", "Tetraspanin", "", "" ], [ "P01237-1", "Prolactin", "PRL", "" ], [ "P01230-1", "Lutropin subunit beta", "Lutropin beta chain", "" ], [ "P09005-1", "Serine protease inhibitor 2.1", "SPI-2.1", "" ], [ "P09006-1", "Serine protease inhibitor A3N", "Serpin A3N", "" ], [ "M0RB75-1", "[Histone H3]-trimethyl-L-lysine(9) demethylase", "", "1.14.11.66" ], [ "Q9JHY8-1", "DNA ligase 1", "", "6.5.1.1" ], [ "Q9JHY1-1", "Junctional adhesion molecule A", "JAM-A", "" ], [ "Q9JHY2-1", "Sideroflexin-3", "", "" ], [ "Q9JHY7-1", "Baculoviral IAP repeat-containing protein 5", "", "" ], [ "P31646-1", "Transporter", "", "" ], [ "Q02874-1", "Core histone macro-H2A.1", "Histone macroH2A1", "" ], [ "Q02874-1", "Core histone macro-H2A.1", "mH2A1", "" ], [ "P08699-1", "Galectin-3", "Gal-3", "" ], [ "P56558-1", "O-GlcNAc transferase subunit p110", "", "2.4.1.255" ], [ "P08011-1", "Microsomal glutathione S-transferase 1", "Microsomal GST-1", "2.5.1.18" ], [ "Q05474-1", "Ubiquitin-like protein FUBI", "", "" ], [ "P54690-1", "Branched-chain-amino-acid aminotransferase", "", "2.6.1.42" ], [ "Q99JD4-1", "CLIP-associating protein 2", "", "" ], [ "Q99JD1-1", "Beta-defensin", "", "" ], [ "Q99JD3-1", "Mitochondrial 2-oxodicarboxylate carrier", "", "" ], [ "Q99JD2-1", "Tektin-1", "", "" ], [ "Q7TP40-1", "PEST proteolytic signal-containing nuclear protein", "", "" ], [ "P18508-1", "GABA(A) receptor subunit gamma-2", "", "" ], [ "P22002-1", "Voltage-dependent L-type calcium channel subunit alpha-1C", "", "" ], [ "M0R8G6-1", "Ig-like domain-containing protein", "", "" ], [ "F1M9T2-1", "Poly [ADP-ribose] polymerase", "PARP", "2.4.2.-" ], [ "Q02294-1", "Voltage-dependent N-type calcium channel subunit alpha-1B", "", "" ], [ "M0R8G2-1", "G_PROTEIN_RECEP_F1_2 domain-containing protein", "", "" ], [ "Q02293-1", "Protein farnesyltransferase subunit beta", "FTase-beta", "2.5.1.58" ], [ "M0R8G9-1", "Olfactory receptor", "", "" ], [ "D3ZGR8-1", "Olfactory receptor", "", "" ], [ "Q8K5E0-1", "Lysophosphatidic acid receptor 3", "LPA receptor 3", "" ], [ "Q8K5E0-1", "Lysophosphatidic acid receptor 3", "LPA-3", "" ], [ "Q460M5-1", "Leucine-rich repeat and fibronectin type-III domain-containing protein 2", "", "" ], [ "Q9R1N3-1", "Sodium bicarbonate cotransporter 3", "", "" ], [ "D3ZIY7-1", "40S ribosomal protein S2", "", "" ], [ "P22006-1", "Seminal vesicle secretory protein 2", "", "" ], [ "D3ZSP1-1", "Small nuclear ribonucleoprotein E", "snRNP-E", "" ], [ "D3ZSP7-1", "E3 ubiquitin-protein ligase TTC3", "", "2.3.2.27" ], [ "P48550-1", "G protein-activated inward rectifier potassium channel 2", "GIRK-2", "" ], [ "D3ZFP4-1", "DNA helicase", "", "3.6.4.12" ], [ "Q6B4M5-1", "Partitioning defective 6 homolog alpha", "PAR-6", "" ], [ "Q6B4M5-1", "Partitioning defective 6 homolog alpha", "PAR-6 alpha", "" ], [ "Q6B4M5-1", "Partitioning defective 6 homolog alpha", "PAR-6A", "" ], [ "D4A130-1", "Olfactory receptor", "", "" ], [ "D4A133-1", "H(+)-transporting two-sector ATPase", "", "7.1.2.2" ], [ "P09875-1", "UDP-glucuronosyltransferase", "", "2.4.1.17" ], [ "F1LUJ0-1", "Takusan domain-containing protein", "", "" ], [ "D3ZHE6-1", "60S ribosomal protein L14", "", "" ], [ "Q9JIL8-1", "DNA repair protein RAD50", "", "3.6.-.-" ] ] }, "readme": "Name\n - Rat Protein Recommended Names (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-09-06T14:06:38.950487\n\nModified on\n - 2022-01-19T11:27:40.272500\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 Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for rat [taxid:10116] proteins. 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\nDescription Domain\n Keywords\n - protein recommended name\n - protein name\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file. \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/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_recnames.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_recnames.csv\n Name: rat_protein_recnames.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_recnames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"16\"\n Name: \"motif_start\"\n Description: \"\"\n Unique Values: \"23\"\n Name: \"filter_flags\"\n Description: \"Filter tags/flags assigned to the mutation entries that have passed the mutation filter criteria\"\n Unique Values: \"19\"\n Name: \"sift_prediction\"\n Description: \"The SIFT qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"3\"\n Name: \"somatic_status\"\n Description: \"The status of the variant whether it is germline (somatic status =0) or somatic (somatic status =1) variant\"\n Unique Values: \"1\"\n Name: \"chr_pos\"\n Description: \"Chromosome Position of a gene\"\n Unique Values: \"19\"\n Name: \"chr_id\"\n Description: \"\"\n Unique Values: \"10\"\n Name: \"dbsnp_id\"\n Description: \"\"A reference SNP ID number\"\n Unique Values: \"19\"\n Name: \"evidence_ECO:0000313\"\n Description: \"A type of evidence that is imported information used in an automatic assertion\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"19\"\n Name: \"mim_id\"\n Description: \"Disease ID from the OMIM database\"\n Unique Values: \"1\"\n Name: \"description\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"begin_aa_pos\"\n Description: \"Start position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"cytogenic_band\"\n Description: \"One of the subregions of a chromosome visible microscopically after special staining\"\n Unique Values: \"14\"\n Name: \"aa_pos\"\n Description: \"Position of the amino acid in canonical sequence of protein in the UniProtKB database\"\n Unique Values: \"18\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"9\"\n Name: \"sift_score\"\n Description: \"SIFT predicts whether an amino acid substitution is likely to affect protein function based on sequence homology and the physico-chemical similarity between the alternate amino acids. The data we provide for each amino acid substitution is a score and a qualitative prediction (either 'tolerated' or 'deleterious'). The score is the normalized probability that the amino acid change is tolerated so scores nearer zero are more likely to be deleterious. The qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"10\"\n Name: \"alt_motif\"\n Description: \"Altered motif\"\n Unique Values: \"24\"\n Name: \"disease_xrefs\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"polyphen_score\"\n Description: \"The score assigned to a amino acid substitution by a tool called as PolyPhen (=Polymorphism Phenotyping) which predicts possible impact of an amino acid substitution on the structure and function of a human protein using straightforward physical and comparative considerations. The PolyPhen score ranges from 0.0 (tolerated) to 1.0 (deleterious). Variants with scores of 0.0 are predicted to be benign. Values closer to 1.0 are more confidently predicted to be deleterious\"\n Unique Values: \"1\"\n Name: \"polyphen_prediction\"\n Description: \"\"The PolyPhen prediction values are - greater than 0.908 - \"\"Probably Damaging\"\"; greater than 0.446 and less than or equal to 0.908 - \"\"Possibly Damaging\"\"; less than or equal to 0.446 - \"\"Benign\"\"\"\n Unique Values: \"1\"\n Name: \"is_known_glycoprotein\"\n Description: \"Yes or no flag to denote if a protein is experimentally proven glycoprotein\"\n Unique Values: \"1\"\n Name: \"alt_nt\"\n Description: \"Alternative nucleotide\"\n Unique Values: \"1\"\n Name: \"protein_name\"\n Description: \"Protein name in the UniProtKB\"\n Unique Values: \"16\"\n Name: \"disease_evidence_ECO:0000313\"\n Description: \"The evidence that could be a PMID or a ClinVar ID that associates disease with the variant\"\n Unique Values: \"1\"\n Name: \"effect\"\n Description: \"The effect on glycosylation or N-sequon due to variation at site of glycosylated amino acid.\"\n Unique Values: \"3\"\n Name: \"end_aa_pos\"\n Description: \"End position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"mutation_type\"\n Description: \"Denotes whether mutation was reported with reference to amino acid or nucleotide\"\n Unique Values: \"1\"\n Name: \"disease_description\"\n Description: \"The disease description and/or definition \"\n Unique Values: \"1\"\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"1\"\n Name: \"evidence_ECO:0000269\"\n Description: \"A type of experimental evidence that is used in a manual assertion. Usually the values are PMIDs\"\n Unique Values: \"1\"\n Name: \"ref_nt\"\n Description: \"Reference nucleotide\"\n Unique Values: \"4\"\n Name: \"disease\"\n Description: \"The disease name for the cell line\"\n Unique Values: \"1\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"10\"\n Name: \"cosmic_id\"\n Description: \"Legacy mutation identifier (COSM) in Catalogue of Somatic Mutations in Cancer (COSMIC) represents existing COSM mutation identifiers. This identifier remains the same between different assemblies (GRCh37 and GRCh38). All the COSM ids at the same genomic location have been collapsed into one representative COSM id. These ids are maintained to help track existing mutations\"\n Unique Values: \"1\"\n Name: \"ref_motif\"\n Description: \"Reference motif\"\n Unique Values: \"20\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"minor_allelic_frequency\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"17\"\n Name: \"disease_evidence_ECO:0000269\"\n Description: \"The PMID evidence for the association of the disease with the variant.\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.11.2/reviewed/rat_protein_recnames.csv" }