{ "bcoid": "GLY_000394", "title": "Rat Protein Names (NCBI RefSeq)", "description": "The Rat Protein Names (NCBI RefSeq) dataset contains rat [taxid:10116] protein names (primary and other ...", "filename": "rat_protein_proteinnames_refseq.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Protein Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D3ZB44-1...", "XP_006223048..." ], [ "D3ZB44-1...", "XP_006223048..." ] ], "headers": [ "uniprotkb_ca...", "refseq_ac..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "refseq_ac" }, { "type": "string", "label": "refseq_protein_name" } ], [ "D3ZB44-1", "XP_006223048.1", "zinc finger protein 324A" ], [ "D3ZB44-1", "XP_006223048", "zinc finger protein 324A" ], [ "D3ZB49-1", "XP_001056612.2", "oxidative stress-induced growth inhibitor 2 isoform X2" ], [ "D3ZB49-1", "XP_001056612", "oxidative stress-induced growth inhibitor 2 isoform X2" ], [ "D3ZB48-1", "NP_001101416.1", "protein Hook homolog 1" ], [ "D3ZB48-1", "NP_001101416.1", "hook homolog 1" ], [ "D3ZB48-1", "NP_001101416", "protein Hook homolog 1" ], [ "D3ZB48-1", "NP_001101416", "hook homolog 1" ], [ "Q5RJZ1-1", "XP_006235834.1", "regulator of telomere elongation helicase 1 isoform X1" ], [ "Q5RJZ1-1", "XP_006235834", "regulator of telomere elongation helicase 1 isoform X1" ], [ "Q0HA29-1", "NP_001041507.1", "nicotinamide/nicotinic acid mononucleotide adenylyltransferase 2" ], [ "Q0HA29-1", "NP_001041507.1", "nicotinamide mononucleotide adenylyltransferase 2; NMN adenylyltransferase 2; naMN adenylyltransferase 1; nicotinate-nucleotide adenylyltransferase 1; naMN adenylyltransferase 2; NMN/NaMN adenylyltransferase 2; nicotinate-nucleotide adenylyltransferase 2" ], [ "Q0HA29-1", "NP_001041507", "nicotinamide/nicotinic acid mononucleotide adenylyltransferase 2" ], [ "Q0HA29-1", "NP_001041507", "nicotinamide mononucleotide adenylyltransferase 2; NMN adenylyltransferase 2; naMN adenylyltransferase 1; nicotinate-nucleotide adenylyltransferase 1; naMN adenylyltransferase 2; NMN/NaMN adenylyltransferase 2; nicotinate-nucleotide adenylyltransferase 2" ], [ "A0A0G2JVG8-1", "NP_001000969.1", "olfactory receptor Olr410" ], [ "A0A0G2JVG8-1", "NP_001000969.1", "olfactory receptor gene Olr410" ], [ "A0A0G2JVG8-1", "NP_001000969", "olfactory receptor Olr410" ], [ "A0A0G2JVG8-1", "NP_001000969", "olfactory receptor gene Olr410" ], [ "Q99372-1", "NP_036854.1", "elastin precursor" ], [ "Q99372-1", "NP_036854.1", "Tropoelastin" ], [ "Q99372-1", "NP_036854", "elastin precursor" ], [ "Q99372-1", "NP_036854", "Tropoelastin" ], [ "A0A096MJY4-1", "XP_006224017.1", "myocyte-specific enhancer factor 2C isoform X1" ], [ "A0A096MJY4-1", "XP_006224017", "myocyte-specific enhancer factor 2C isoform X1" ], [ "A0A096MJY1-1", "XP_001077762.3", "glypican-6 isoform X2" ], [ "A0A096MJY1-1", "XP_001077762", "glypican-6 isoform X2" ], [ "A0A0G2KA92-1", "XP_006229432.1", "chromodomain-helicase-DNA-binding protein 2 isoform X2" ], [ "A0A0G2KA92-1", "XP_006229432", "chromodomain-helicase-DNA-binding protein 2 isoform X2" ], [ "A0A0G2K4P4-1", "NP_001128103.1", "basal body-orientation factor 1" ], [ "A0A0G2K4P4-1", "NP_001128103.1", "coiled-coil domain containing 176" ], [ "A0A0G2K4P4-1", "NP_001128103", "basal body-orientation factor 1" ], [ "A0A0G2K4P4-1", "NP_001128103", "coiled-coil domain containing 176" ], [ "Q5RJK6-1", "NP_001012131.1", "inositol polyphosphate 1-phosphatase" ], [ "Q5RJK6-1", "NP_001012131", "inositol polyphosphate 1-phosphatase" ], [ "Q62949-1", "NP_036967.1", "cortistatin preproprotein" ], [ "Q62949-1", "NP_036967.1", "Preprocortistatin" ], [ "Q62949-1", "NP_036967", "cortistatin preproprotein" ], [ "Q62949-1", "NP_036967", "Preprocortistatin" ], [ "P01946-1", "NP_001007723.1", "hemoglobin alpha, adult chain 2" ], [ "P01946-1", "NP_001007723.1", "2-alpha-1 globin; 2-alpha globin; hemoglobin alpha 2 chain; globin c2; globin c3; Hemoglobin subunit alpha-1/2; Alpha-1/2-globin; Hemoglobin alpha-1/2 chain; hemoglobin, alpha 2" ], [ "P01946-1", "NP_001007723", "hemoglobin alpha, adult chain 2" ], [ "P01946-1", "NP_001007723", "2-alpha-1 globin; 2-alpha globin; hemoglobin alpha 2 chain; globin c2; globin c3; Hemoglobin subunit alpha-1/2; Alpha-1/2-globin; Hemoglobin alpha-1/2 chain; hemoglobin, alpha 2" ], [ "Q5M9G9-1", "NP_001012154.1", "FAST kinase domain-containing protein 4" ], [ "Q5M9G9-1", "NP_001012154.1", "protein TBRG4; transforming growth factor beta regulated gene 4" ], [ "Q5M9G9-1", "NP_001012154", "FAST kinase domain-containing protein 4" ], [ "Q5M9G9-1", "NP_001012154", "protein TBRG4; transforming growth factor beta regulated gene 4" ], [ "O35152-1", "NP_062241.2", "BET1-like protein" ], [ "O35152-1", "NP_062241.2", "GOS-15; Golgi soluble N-ethylmaleimide-sensitive factor attachment protein 15; golgi SNARE, 15 kD; vesicle transport protein GOS15; golgi SNARE with a size of 15 kDa; blocked early in transport 1 homolog like" ], [ "O35152-1", "NP_062241", "BET1-like protein" ], [ "O35152-1", "NP_062241", "GOS-15; Golgi soluble N-ethylmaleimide-sensitive factor attachment protein 15; golgi SNARE, 15 kD; vesicle transport protein GOS15; golgi SNARE with a size of 15 kDa; blocked early in transport 1 homolog like" ], [ "P30936-1", "NP_598206.1", "somatostatin receptor type 3" ], [ "P30936-1", "NP_598206.1", "SS3R; SSR-28; SS3-R; SS-3-R; somatostatin receptor 28; somatostatin receptor subtype 3" ], [ "P30936-1", "NP_598206", "somatostatin receptor type 3" ], [ "P30936-1", "NP_598206", "SS3R; SSR-28; SS3-R; SS-3-R; somatostatin receptor 28; somatostatin receptor subtype 3" ], [ "O35158-1", "NP_059054.1", "cell adhesion molecule-related/down-regulated by oncogenes precursor" ], [ "O35158-1", "NP_059054.1", "immunoglobulin superfamily member; cell adhesion molecule-related/down-regulated by oncogenes; Cdon homolog" ], [ "O35158-1", "NP_059054", "cell adhesion molecule-related/down-regulated by oncogenes precursor" ], [ "O35158-1", "NP_059054", "immunoglobulin superfamily member; cell adhesion molecule-related/down-regulated by oncogenes; Cdon homolog" ], [ "P02761-1", "NP_671747.1", "major urinary protein precursor" ], [ "P02761-1", "NP_671747.1", "major urinary protein; alpha-2u-globulin; alpha(2)-euglobulin; allergen n I; allergen Rat n I" ], [ "P02761-1", "NP_671747", "major urinary protein precursor" ], [ "P02761-1", "NP_671747", "major urinary protein; alpha-2u-globulin; alpha(2)-euglobulin; allergen n I; allergen Rat n I" ], [ "P02764-1", "NP_445740.1", "alpha-1-acid glycoprotein precursor" ], [ "P02764-1", "NP_445740.1", "alpha-1-acid glycoprotein" ], [ "P02764-1", "NP_445740", "alpha-1-acid glycoprotein precursor" ], [ "P02764-1", "NP_445740", "alpha-1-acid glycoprotein" ], [ "P02767-1", "NP_036813.2", "transthyretin precursor" ], [ "P02767-1", "NP_036813.2", "prealbumin, amyloidosis type I" ], [ "P02767-1", "NP_036813", "transthyretin precursor" ], [ "P02767-1", "NP_036813", "prealbumin, amyloidosis type I" ], [ "D4A4W8-1", "NP_001099679.1", "brachyury protein" ], [ "D4A4W8-1", "NP_001099679.1", "brachyury homolog; T brachyury transcription factor" ], [ "D4A4W8-1", "NP_001099679", "brachyury protein" ], [ "D4A4W8-1", "NP_001099679", "brachyury homolog; T brachyury transcription factor" ], [ "D4A4W0-1", "NP_001000252.1", "olfactory receptor Olr338" ], [ "D4A4W0-1", "NP_001000252.1", "olfactory receptor gene Olr338" ], [ "D4A4W0-1", "NP_001000252", "olfactory receptor Olr338" ], [ "D4A4W0-1", "NP_001000252", "olfactory receptor gene Olr338" ], [ "D4A4W1-1", "XP_017443583.1", "membrane protein FAM174B isoform X1" ], [ "D4A4W1-1", "XP_017443583", "membrane protein FAM174B isoform X1" ], [ "F7EN52-1", "XP_006240610.1", "cholesterol 24-hydroxylase isoform X1" ], [ "F7EN52-1", "XP_006240610", "cholesterol 24-hydroxylase isoform X1" ], [ "D4A4W4-1", "NP_001102458.1", "epoxide hydrolase 3" ], [ "D4A4W4-1", "NP_001102458.1", "abhydrolase domain containing 9" ] ] }, "readme": "Name\n - Rat Protein Names (NCBI RefSeq)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:32:44.009025\n\nModified on\n - 2022-01-13T16:12:12.828698\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The Rat Protein Names (NCBI RefSeq) dataset contains rat [taxid:10116] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen\n\nDescription Domain\n Keywords\n - protein names\n - NCBI RefSeq\n\n Pipeline Steps\n - Step-1: The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions\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: refseq_protein_all_10116.gpff\n URI: https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff\n Name: rat_protein_xref_refseq.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv\n Output Subdomain\n Name: rat_protein_proteinnames_refseq.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_proteinnames_refseq.csv\n Name: rat_protein_proteinnames_refseq.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_proteinnames_refseq.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_proteinnames_refseq.csv" }