{ "bcoid": "GLY_000265", "title": "Rat Protein Alternative Name (UniProtKB)", "description": "The Rat Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for rat [taxid:10116] ...", "filename": "rat_protein_altnames.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Protein Alternative Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q0HA29-1...", "Nicotinate-n..." ], [ "Q0HA29-1...", "Nicotinamide..." ] ], "headers": [ "uniprotkb_ca...", "alternative_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "alternative_name_full" }, { "type": "string", "label": "alternative_name_short" }, { "type": "string", "label": "ec_name" } ], [ "Q0HA29-1", "Nicotinate-nucleotide adenylyltransferase 2", "NaMN adenylyltransferase 2", "" ], [ "Q0HA29-1", "Nicotinamide mononucleotide adenylyltransferase 2", "NMN adenylyltransferase 2", "" ], [ "Q99372-1", "Tropoelastin", "", "" ], [ "Q07969-1", "Glycoprotein IIIb", "GPIIIB", "" ], [ "Q07969-1", "Platelet glycoprotein IV", "GPIV", "" ], [ "Q07969-1", "Fatty acid translocase", "", "" ], [ "Q07969-1", "PAS-4", "", "" ], [ "Q07969-1", "Fatty acid transport protein", "", "" ], [ "Q07969-1", "PAS IV", "", "" ], [ "Q07969-1", "Adipocyte membrane protein", "", "" ], [ "A0A096MJY4-1", "Myocyte enhancer factor 2C", "", "" ], [ "A0A0G2K4P4-1", "Coiled-coil domain-containing protein 176", "", "" ], [ "P01946-1", "Alpha-1/2-globin", "", "" ], [ "P01946-1", "Hemoglobin alpha-1/2 chain", "", "" ], [ "Q5M9G9-1", "Protein TBRG4", "", "" ], [ "Q5M9G9-1", "Transforming growth factor beta regulator 4", "", "" ], [ "O35152-1", "Golgi SNARE with a size of 15 kDa", "GOS-15", "" ], [ "O35152-1", "Golgi SNARE with a size of 15 kDa", "GS15", "" ], [ "O35152-1", "Vesicle transport protein GOS15", "", "" ], [ "P30936-1", "SSR-28", "", "" ], [ "P02761-1", "Allergen Rat n I", "", "" ], [ "P02761-1", "alpha-2u globulin PGCL1", "", "" ], [ "P02761-1", "Alpha(2)-euglobulin", "", "" ], [ "P02761-1", "Alpha-2u-globulin", "", "" ], [ "Q9QYH1-1", "Discs large homolog 6", "rDLG6", "" ], [ "P02764-1", "Orosomucoid", "OMD", "" ], [ "P02767-1", "Prealbumin", "", "" ], [ "P02767-1", "TBPA", "", "" ], [ "P39020-1", "Growth arrest-specific homeobox", "", "" ], [ "P39020-1", "Mesenchyme homeobox 2", "", "" ], [ "P01230-1", "Luteinizing hormone subunit beta", "LH-B", "" ], [ "P01230-1", "Luteinizing hormone subunit beta", "LSH-B", "" ], [ "P01230-1", "Luteinizing hormone subunit beta", "LSH-beta", "" ], [ "P09006-1", "Serine protease inhibitor 3", "SPI-3", "" ], [ "P09006-1", "Contrapsin-like protease inhibitor 6", "", "" ], [ "P09006-1", "CPI-26", "", "" ], [ "P09006-1", "SPI-2.2", "", "" ], [ "Q9JHY8-1", "DNA ligase I", "", "" ], [ "Q9JHY8-1", "Polydeoxyribonucleotide synthase [ATP] 1", "", "" ], [ "Q9JHY1-1", "Junctional adhesion molecule 1", "JAM-1", "" ], [ "Q9JHY7-1", "Apoptosis inhibitor survivin", "", "" ], [ "Q02874-1", "H2A.y", "", "" ], [ "Q02874-1", "H2A/y", "", "" ], [ "P08699-1", "Carbohydrate-binding protein 35", "CBP 35", "" ], [ "P08699-1", "Lectin L-29", "", "" ], [ "P08699-1", "IgE-binding protein", "", "" ], [ "P08699-1", "Mac-2 antigen", "", "" ], [ "P08699-1", "35 kDa lectin", "", "" ], [ "P08699-1", "Laminin-binding protein", "", "" ], [ "P08699-1", "Galactose-specific lectin 3", "", "" ], [ "P56558-1", "O-linked N-acetylglucosamine transferase 110 kDa subunit", "", "" ], [ "P56558-1", "UDP-N-acetylglucosamine--peptide N-acetylglucosaminyltransferase 110 kDa subunit", "", "" ], [ "P08011-1", "Microsomal GST-I", "", "" ], [ "Q99JD4-1", "Cytoplasmic linker-associated protein 2", "", "" ], [ "Q99JD3-1", "Solute carrier family 25 member 21", "", "" ], [ "P18508-1", "Gamma-aminobutyric acid receptor subunit gamma-2", "", "" ], [ "P22002-1", "Rat brain class C", "RBC", "" ], [ "P22002-1", "Voltage-gated calcium channel subunit alpha Cav1.2", "", "" ], [ "P22002-1", "Calcium channel, L type, alpha-1 polypeptide, isoform 1, cardiac muscle", "", "" ], [ "Q02294-1", "Brain calcium channel III", "BIII", "" ], [ "Q02294-1", "Calcium channel, L type, alpha-1 polypeptide isoform 5", "", "" ], [ "Q02294-1", "Voltage-gated calcium channel subunit alpha Cav2.2", "", "" ], [ "Q02293-1", "Ras proteins prenyltransferase subunit beta", "", "" ], [ "Q02293-1", "CAAX farnesyltransferase subunit beta", "", "" ], [ "Q8K5E0-1", "snGPCR32", "", "" ], [ "Q8K5E0-1", "Lysophosphatidic acid receptor Edg-7", "", "" ], [ "Q9R1N3-1", "Solute carrier family 4 member 7", "", "" ], [ "Q9R1N3-1", "NBC-like protein", "", "" ], [ "Q9R1N3-1", "Electroneutral sodium bicarbonate cotransporter 1", "", "" ], [ "P22006-1", "Seminal vesicle secretory protein II", "SVS II", "" ], [ "D3ZSP1-1", "Sm protein E", "", "" ], [ "D3ZSP7-1", "TPR repeat protein D", "", "" ], [ "D3ZSP7-1", "RING-type E3 ubiquitin transferase TTC3", "", "" ], [ "P48550-1", "BIR1", "", "" ], [ "P48550-1", "Inward rectifier K(+) channel Kir3.2", "", "" ], [ "P48550-1", "KATP-2", "", "" ], [ "P48550-1", "Potassium channel, inwardly rectifying subfamily J member 6", "", "" ], [ "O88664-1", "Thousand and one amino acid protein 1", "", "" ], [ "P00176-1", "Cytochrome P450-B", "Cytochrome P450b", "" ], [ "P00176-1", "Cytochrome P450-PB2", "", "" ], [ "P00176-1", "Cytochrome P450-LM2", "", "" ], [ "P00176-1", "CYPIIB1", "", "" ], [ "P00176-1", "Cytochrome P450-PB1", "", "" ], [ "Q9QYH7-1", "Growth hormone secretagogue", "", "" ] ] }, "readme": "Name\n - Rat Protein Alternative Name (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-09-06T14:06:38.991804\n\nModified on\n - 2020-04-10T12:05:45.412679\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 Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for rat [taxid:10116] proteins. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - protein alternative name\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein 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/ln2data/releases/data/v-1.11.2/source/uniprot-proteome-rattus-norvegicus.nt\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 Output Subdomain\n Name: rat_protein_altnames.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/rat_protein_altnames.csv\n Name: rat_protein_altnames.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/rat_protein_altnames.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_altnames.csv" }