{ "bcoid": "GLY_000022", "title": "Mouse Protein Information (NCBI RefSeq)", "description": "The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information ...", "filename": "mouse_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": [ "Mus musculus" ], "molecule": [ "Protein" ], "tags": [ "Protein Information" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "F7CXU4-1...", "NP_808304..." ], [ "Q9JHG1-1...", "NP_001153088..." ] ], "headers": [ "uniprotkb_ca...", "p_refseq_ac_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "p_refseq_ac_best_match" }, { "type": "string", "label": "refseq_protein_name" }, { "type": "string", "label": "refseq_protein_length" }, { "type": "string", "label": "refseq_protein_summary" } ], [ "F7CXU4-1", "NP_808304", "histocompatibility 2, M region locus 1 precursor", "344", "" ], [ "Q9JHG1-1", "NP_001153088", "phosphatidylinositol N-acetylglucosaminyltransferase subunit P isoform a", "132", "" ], [ "O35066-1", "NP_032471", "kinesin-like protein KIF3C", "796", "" ], [ "Q8CHE4-1", "NP_598582", "PH domain leucine-rich repeat-containing protein phosphatase 1", "1687", "" ], [ "Q61595-1", "NP_001334452", "kinectin isoform 8", "1253", "" ], [ "Q4FZD7-1", "NP_898975", "inactive serine/threonine-protein kinase PLK5 isoform 1", "599", "" ], [ "Q6NZQ6-1", "NP_001276620", "zinc finger protein 740 isoform 2", "168", "" ], [ "Q91WP0-1", "NP_001003893", "mannan-binding lectin serine protease 2 isoform 1 precursor", "685", "" ], [ "Q8CAE2-1", "NP_001072114", "small RNA 2'-O-methyltransferase", "395", "" ], [ "P63213-1", "NP_001033726", "guanine nucleotide-binding protein G(I)/G(S)/G(O) subunit gamma-2", "71", "" ], [ "P59438-1", "NP_001161336", "BLOC-2 complex member HPS5 isoform 2", "1093", "" ], [ "Q8R1W8-1", "NP_071299", "interphotoreceptor matrix proteoglycan 1 precursor", "798", "" ], [ "P33610-1", "NP_032948", "DNA primase large subunit", "505", "" ], [ "Q9QZ47-1", "NP_001334475", "troponin T, fast skeletal muscle isoform 9", "262", "" ], [ "O35887-1", "NP_908942", "calumenin isoform 2 precursor", "315", "" ], [ "Q9QUK4-1", "NP_001119654", "baculoviral IAP repeat-containing protein 1b", "1447", "" ], [ "Q80Y72-1", "NP_808323", "cystatin-like 1 isoform 2 precursor", "140", "" ], [ "Q11011-1", "NP_032968", "puromycin-sensitive aminopeptidase", "920", "" ], [ "Q6NXJ0-1", "NP_598552", "protein WWC2", "1187", "" ], [ "Q7TT28-1", "NP_080128", "RNA exonuclease 1 homolog", "1213", "" ], [ "Q8CB59-1", "NP_766169", "protein FAM161B", "589", "" ], [ "P58281-1", "NP_001186106", "dynamin-like 120 kDa protein, mitochondrial isoform 1", "978", "" ], [ "P43431-1", "NP_001152896", "interleukin-12 subunit alpha isoform 2 precursor", "215", "" ], [ "P61255-1", "NP_033106", "60S ribosomal protein L26", "145", "" ], [ "P41164-1", "NP_031986", "ETS translocation variant 1 isoform a", "477", "" ], [ "Q63959-1", "XP_006540724", "potassium voltage-gated channel subfamily C member 3 isoform X11", "729", "" ], [ "P28652-1", "NP_001167525", "calcium/calmodulin-dependent protein kinase type II subunit beta isoform 3", "529", "" ], [ "Q62312-2", "NP_033397", "TGF-beta receptor type-2 isoform 1 precursor", "592", "" ], [ "F8VPT3-1", "NP_001074547", "lactase/phlorizin hydrolase preproprotein", "1931", "" ], [ "Q8R2D2-1", "NP_598938", "vomeronasal 1 receptor 30", "302", "" ], [ "Q69ZT9-1", "NP_083333", "TBC1 domain family member 30 isoform 1", "766", "" ], [ "Q8BSL0-1", "NP_001238762", "zinc finger protein with KRAB and SCAN domains 8 isoform 2", "516", "" ], [ "Q8VG63-1", "NP_667005", "olfactory receptor family 4 subfamily C member 52", "306", "Olfactory receptors interact with odorant molecules in the nose, to initiate a neuronal response that triggers the perception of a smell. The olfactory receptor proteins are members of a large family of G-protein-coupled receptors (GPCR) arising from single coding-exon genes. Olfactory receptors share a 7-transmembrane domain structure with many neurotransmitter and hormone receptors and are responsible for the recognition and G protein-mediated transduction of odorant signals. The olfactory receptor gene family is the largest in the genome. The nomenclature assigned to the olfactory receptor genes and proteins for this organism is independent of other organisms. [provided by RefSeq, Jul 2008]. " ], [ "J3QQ27-1", "NP_082077", "coiled-coil domain-containing protein 191", "883", "" ], [ "Q5F293-1", "NP_083624", "zinc finger and BTB domain-containing protein 4", "982", "" ], [ "Q9QZ88-1", "NP_001334382", "vacuolar protein sorting-associated protein 29 isoform 1", "186", "" ], [ "Q924W9-1", "NP_001289134", "rhombotin-1 isoform 2", "155", "" ], [ "Q60935-1", "NP_033840", "GPI-linked NAD(P)(+)--arginine ADP-ribosyltransferase 1 isoform 1 precursor", "325", "" ], [ "B9EKF4-1", "NP_001074851", "zinc finger protein 777 isoform 1", "885", "" ], [ "Q8VCS3-1", "NP_663388", "glycosaminoglycan xylosylkinase isoform a", "409", "" ], [ "Q8R2S8-1", "NP_081138", "CD177 antigen precursor", "817", "" ], [ "E9Q9V5-1", "NP_001263327", "membrane-spanning 4-domains subfamily A member 7 isoform c", "267", "" ], [ "E9Q365-1", "NP_001160308", "vomeronasal 1 receptor 101", "307", "" ], [ "E9Q9D8-1", "NP_001074608", "ankyrin repeat domain-containing protein 35 isoform 1", "996", "" ], [ "J3QPC5-1", "NP_001241880", "zinc finger protein 850", "689", "" ], [ "Q8C898-1", "NP_001032998", "SP140 nuclear body protein family member isoform 2", "263", "" ], [ "Q8VGN6-1", "NP_667189", "olfactory receptor family 4 subfamily C member 10", "311", "Olfactory receptors interact with odorant molecules in the nose, to initiate a neuronal response that triggers the perception of a smell. The olfactory receptor proteins are members of a large family of G-protein-coupled receptors (GPCR) arising from single coding-exon genes. Olfactory receptors share a 7-transmembrane domain structure with many neurotransmitter and hormone receptors and are responsible for the recognition and G protein-mediated transduction of odorant signals. The olfactory receptor gene family is the largest in the genome. The nomenclature assigned to the olfactory receptor genes and proteins for this organism is independent of other organisms. [provided by RefSeq, Jul 2008]. " ], [ "Q60682-1", "NP_001095090", "killer cell lectin-like receptor 8 isoform 1", "266", "" ], [ "Q91XE8-1", "NP_001240797", "transmembrane protein 205 isoform 2", "189", "" ], [ "Q8CFZ5-1", "NP_033229", "solute carrier family 22 member 12", "553", "" ], [ "Q80WM5-1", "NP_839986", "hyaluronan and proteoglycan link protein 3 precursor", "359", "" ], [ "F8VPZ9-1", "NP_001074887", "BRD4-interacting chromatin-remodeling complex-associated protein", "1578", "" ], [ "P36363-1", "NP_032034", "fibroblast growth factor 7 precursor", "194", "" ], [ "Q91ZB7-1", "NP_780743", "mas-related G-protein coupled receptor member E", "310", "" ], [ "Q8BGQ4-1", "NP_700464", "protein O-mannosyl-transferase 2", "820", "This gene encodes an integral membrane protein that belongs to the dolichyl-phosphate-mannose-protein mannosyltransferase family. The encoded enzyme is found in the membrane of the endoplasmic reticulum. This protein is a component of the protein O-mannosyltransferase enzyme complex which is involved in modification of the protein alpha-dystroglycan. Mutations in the human gene are a cause of different forms of muscular dystrophy-dystroglycanopathy (MDDG), type A2 (also known as Walker-Warburg syndrome), type B2 and type C2 (also known as limb-girdle muscular dystrophy). [provided by RefSeq, Sep 2015]. " ], [ "Q60610-1", "NP_001139359", "rho guanine nucleotide exchange factor TIAM1 isoform 2", "622", "" ], [ "Q8CGM1-1", "NP_001186625", "adhesion G protein-coupled receptor B2 isoform 2 precursor", "1506", "" ], [ "Q8C650-1", "NP_001020081", "septin-10 isoform 1", "452", "" ], [ "Q8K2W9-1", "NP_083166", "uncharacterized protein C14orf93 homolog precursor", "541", "" ], [ "Q6GQX2-1", "NP_001001884", "nck-associated protein 5-like", "1323", "" ], [ "Q6NZQ8-1", "NP_001159844", "E3 ubiquitin-protein ligase MARCHF1 isoform 1", "285", "" ], [ "Q8C2B3-1", "NP_001191208", "histone deacetylase 7 isoform 6", "892", "" ], [ "Q9QY48-1", "NP_064341", "deoxyribonuclease-2-beta precursor", "354", "" ], [ "P61961-1", "NP_080711", "ubiquitin-fold modifier 1", "85", "" ], [ "P62849-1", "NP_035427", "40S ribosomal protein S24 isoform 1", "130", "" ], [ "P30548-1", "NP_033339", "substance-P receptor", "407", "This gene encodes the receptor for the tachykinin, substance P, also referred to as neurokinin 1. This gene belongs to a gene family of tachykinin receptors which are characterized by interactions with G proteins and contain seven hydrophobic transmembrane regions. This receptor has been associated with nitric oxide formation, and it has been localized to cholinergic and nitrergic neurons as well as on smooth muscle cells. [provided by RefSeq, Mar 2010]. " ], [ "Q91ZD1-1", "NP_473390", "protein odd-skipped-related 2 isoform 2", "276", "" ], [ "P47239-1", "NP_035169", "paired box protein Pax-7", "503", "" ], [ "O54890-1", "NP_058060", "integrin beta-3 precursor", "787", "" ], [ "A0A571BDE3-1", "XP_003689010", "spindlin-2A-like", "236", "" ], [ "A0A0B4J1F8-1", "NP_898851", "non-protein coding RNA 86", "78", "" ], [ "E9Q9Z0-1", "NP_001011837", "olfactory receptor 748", "307", "Olfactory receptors interact with odorant molecules in the nose, to initiate a neuronal response that triggers the perception of a smell. The olfactory receptor proteins are members of a large family of G-protein-coupled receptors (GPCR) arising from single coding-exon genes. Olfactory receptors share a 7-transmembrane domain structure with many neurotransmitter and hormone receptors and are responsible for the recognition and G protein-mediated transduction of odorant signals. The olfactory receptor gene family is the largest in the genome. The nomenclature assigned to the olfactory receptor genes and proteins for this organism is independent of other organisms. [provided by RefSeq, Jul 2008]. " ], [ "Q8BM11-1", "NP_001276676", "protein-glutamine gamma-glutamyltransferase 6 isoform 2", "483", "" ], [ "Q9Z150-1", "NP_942589", "zinc finger and BTB domain-containing protein 12 isoform 1", "459", "" ], [ "Q9CRA8-1", "NP_613052", "exosome complex component RRP46", "235", "" ], [ "O70622-1", "NP_001020535", "reticulon-2 isoform C", "204", "" ], [ "Q3V0B4-1", "NP_001034584", "cilia- and flagella-associated protein 65", "1847", "" ], [ "Q6P253-1", "NP_766487", "dermokine isoform b precursor", "508", "" ], [ "Q8BJQ4-1", "NP_775570", "TIR domain-containing adapter molecule 2", "232", "" ], [ "P97402-1", "NP_076376", "N-acetyllactosaminide beta-1,6-N-acetylglucosaminyl-transferase isoform B", "401", "" ], [ "Q9CR16-1", "NP_080628", "peptidyl-prolyl cis-trans isomerase D isoform 1", "370", "" ], [ "P70227-1", "NP_542120", "inositol 1,4,5-trisphosphate receptor type 3", "2670", "" ], [ "O09108-1", "NP_032523", "lutropin subunit beta precursor", "141", "" ], [ "Q5BKR2-1", "NP_849208", "sodium/hydrogen exchanger 9B2 isoform 1", "547", "" ] ] }, "readme": "Name\n - Mouse Protein Information (NCBI RefSeq)\n\nVersion\n - v-2.1.1\n\nCreated on\n - 2019-01-23T17:21:05.888176\n\nModified on\n - 2022-09-26T08:48:18.844146\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summary 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 information\n - protein length\n - protein summary\n - NCBI RefSeq\n\n Pipeline Steps\n - Step-1: The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions\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: mouse_protein_xref_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_refseq.csv\n Name: refseq_protein_all_10090.gpff\n URI: /data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_10090.gpff\n Output Subdomain\n Name: mouse_protein_info_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.csv\n Name: mouse_protein_info_refseq.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20206\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"23521\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"23388\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"2211\"\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"1322\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_info_refseq.csv" }