{ "bcoid": "GLY_000021", "title": "Human Protein Information (NCBI RefSeq)", "description": "The Human Protein Information (NCBI RefSeq) dataset contains human [taxid:9606] protein information such ...", "filename": "human_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": [ "Homo sapiens" ], "molecule": [ "Protein" ], "tag": [ "Protein Information" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q9Y5W7-1...", "XP_016866579..." ], [ "O75626-1...", "XP_011534364..." ] ], "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" } ], [ "Q9Y5W7-1", "XP_016866579", "sorting nexin-14 isoform X3", "893", "" ], [ "O75626-1", "XP_011534364", "PR domain zinc finger protein 1 isoform X1", "839", "" ], [ "Q15477-1", "XP_011513117", "SKI2 subunit of superkiller complex protein isoform X1", "1033", "" ], [ "Q8N878-1", "XP_011534439", "FERM domain-containing protein 1 isoform X1", "614", "" ], [ "Q96EV8-1", "XP_011513239", "dysbindin isoform X3", "195", "" ], [ "Q9Y4F9-1", "XP_016867013", "rho family-interacting cell polarization regulator 2 isoform X3", "642", "" ], [ "O75190-1", "XP_005249572", "dnaJ homolog subfamily B member 6 isoform X1", "334", "" ], [ "Q13422-1", "XP_011513364", "DNA-binding protein Ikaros isoform X5", "539", "" ], [ "Q13422-1", "XP_011513375", "DNA-binding protein Ikaros isoform X21", "452", "" ], [ "Q9Y239-1", "XP_011513390", "nucleotide-binding oligomerization domain-containing protein 1 isoform X9", "779", "" ], [ "Q8WWF3-1", "XP_005250198", "serine-rich single-pass membrane protein 1 isoform X2", "183", "" ], [ "P20711-1", "XP_005271802", "aromatic-L-amino-acid decarboxylase isoform X2", "442", "" ], [ "P50549-1", "XP_011513469", "ETS translocation variant 1 isoform X1", "491", "" ], [ "Q8NEE6-1", "XP_006715961", "dynein regulatory complex subunit 6 isoform X11", "584", "" ], [ "P0C881-1", "XP_005249716", "radial spoke head 10 homolog B isoform X2", "870", "" ], [ "P10071-1", "XP_011513576", "transcriptional activator GLI3 isoform X3", "1521", "" ], [ "Q7Z7C7-1", "XP_011514439", "stimulated by retinoic acid gene 8 protein homolog isoform X1", "379", "" ], [ "Q02218-1", "XP_005249816", "2-oxoglutarate dehydrogenase complex component E1 isoform X1", "1038", "" ], [ "Q9NZW5-1", "XP_005249832", "protein PALS2 isoform X2", "428", "" ], [ "Q9H0J9-1", "XP_005250096", "protein mono-ADP-ribosyltransferase PARP12 isoform X4", "420", "" ], [ "Q9BU79-1", "XP_005250643", "transmembrane protein 243 isoform X1", "119", "" ], [ "Q8NF64-1", "XP_005249930", "zinc finger MIZ domain-containing protein 2 isoform X6", "888", "" ], [ "Q8N2F6-1", "XP_005250685", "armadillo repeat-containing protein 10 isoform X11", "193", "" ], [ "O00189-1", "XP_005250746", "AP-4 complex subunit mu-1 isoform X1", "460", "" ], [ "Q9UHL9-1", "XP_006716245", "general transcription factor II-I repeat domain-containing protein 1 isoform X6", "960", "" ], [ "Q93062-1", "XP_016868473", "RNA-binding protein with multiple splicing isoform X5", "224", "" ], [ "Q6UXZ4-1", "XP_011542706", "netrin receptor UNC5D isoform X13", "884", "" ], [ "Q99965-1", "XP_011542782", "disintegrin and metalloproteinase domain-containing protein 2 isoform X3", "579", "" ], [ "Q5GH73-1", "XP_011542123", "XK-related protein 6 isoform X2", "287", "" ], [ "Q8N8D7-1", "XP_016868848", "sodium/potassium-transporting ATPase subunit beta-1-interacting protein 3 isoform X1", "211", "" ], [ "Q8N8D7-1", "XP_011515814", "sodium/potassium-transporting ATPase subunit beta-1-interacting protein 3 isoform X2", "186", "" ], [ "Q15149-1", "XP_005251040", "plectin isoform X18", "4524", "" ], [ "Q96HA8-1", "XP_006716660", "protein N-terminal glutamine amidohydrolase isoform X1", "196", "" ], [ "Q9NQY0-1", "XP_011542889", "bridging integrator 3 isoform X2", "149", "" ], [ "Q9P243-1", "XP_011515508", "zinc finger protein ZFAT isoform X5", "1156", "" ], [ "P34741-1", "XP_011515514", "syndecan-2 isoform X1", "172", "" ], [ "Q08648-1", "XP_016869233", "sperm-associated antigen 11A isoform X2", "80", "" ], [ "Q6P1X5-1", "XP_006716684", "transcription initiation factor TFIID subunit 2 isoform X1", "1251", "" ], [ "Q6P1X5-1", "XP_011515561", "transcription initiation factor TFIID subunit 2 isoform X2", "1214", "" ], [ "Q6P1X5-1", "XP_016869268", "transcription initiation factor TFIID subunit 2 isoform X3", "1162", "" ], [ "Q9HAB3-1", "XP_016869310", "solute carrier family 52, riboflavin transporter, member 2 isoform X2", "281", "" ], [ "Q9H169-1", "XP_005273709", "stathmin-4 isoform X1", "258", "" ], [ "Q53GL7-1", "XP_011515638", "protein mono-ADP-ribosyltransferase PARP10 isoform X2", "1016", "" ], [ "P0C5J1-1", "XP_006716319", "putative protein N-methyltransferase FAM86B1 isoform X1", "330", "" ], [ "Q5HYA8-1", "XP_011515665", "meckelin isoform X3", "701", "" ], [ "O75022-1", "XP_006726376", "leukocyte immunoglobulin-like receptor subfamily B member 3 isoform X5", "632", "" ], [ "O75022-1", "XP_006726377", "leukocyte immunoglobulin-like receptor subfamily B member 3 isoform X6", "631", "" ], [ "O75022-1", "XP_011546876", "leukocyte immunoglobulin-like receptor subfamily B member 3 isoform X2", "649", "" ], [ "Q5T9Z0-1", "NP_741997", "transmembrane epididymal protein 1", "273", "" ], [ "Q0D2K0-1", "NP_001092757", "magnesium transporter NIPA4 isoform 1", "404", "This gene likely encodes a membrane receptor. Mutations in this gene have been associated with autosomal recessive congenital ichthyosis. [provided by RefSeq, Feb 2010]. " ], [ "Q07011-1", "NP_001552", "tumor necrosis factor receptor superfamily member 9 precursor", "255", "The protein encoded by this gene is a member of the TNF-receptor superfamily. This receptor contributes to the clonal expansion, survival, and development of T cells. It can also induce proliferation in peripheral monocytes, enhance T cell apoptosis induced by TCR/CD3 triggered activation, and regulate CD28 co-stimulation to promote Th1 cell responses. The expression of this receptor is induced by lymphocyte activation. TRAF adaptor proteins have been shown to bind to this receptor and transduce the signals leading to activation of NF-kappaB. [provided by RefSeq, Jul 2008]. " ], [ "Q6P5X7-1", "NP_001138625", "transmembrane protein 71 isoform 2", "232", "" ], [ "Q8WY98-1", "NP_061991", "transmembrane protein 234 isoform a precursor", "140", "" ], [ "Q99677-1", "NP_001264929", "lysophosphatidic acid receptor 4", "370", "This gene encodes a member of the lysophosphatidic acid receptor family. It may also be related to the P2Y receptors, a family of receptors that bind purine and pyrimidine nucleotides and are coupled to G proteins. The encoded protein may play a role in monocytic differentiation. [provided by RefSeq, Feb 2009]. " ], [ "Q5TAB7-1", "NP_001009994", "protein ripply2 isoform 1", "128", "This gene encodes a nuclear protein that belongs to a novel family of proteins required for vertebrate somitogenesis. Members of this family have a tetrapeptide WRPW motif that is required for interaction with the transcriptional repressor Groucho and a carboxy-terminal Ripply homology domain/Bowline-DSCR-Ledgerline conserved region required for transcriptional repression. Null mutant mice die soon after birth and display defects in axial skeleton segmentation due to defective somitogenesis. Alternative splicing results in multiple transcript variants. [provided by RefSeq, Feb 2016]. " ], [ "Q9ULI4-1", "NP_056471", "kinesin-like protein KIF26A", "1882", "" ], [ "P14598-1", "NP_000256", "neutrophil cytosol factor 1", "390", "The protein encoded by this gene is a 47 kDa cytosolic subunit of neutrophil NADPH oxidase. This oxidase is a multicomponent enzyme that is activated to produce superoxide anion. Mutations in this gene have been associated with chronic granulomatous disease. [provided by RefSeq, Jul 2008]. " ], [ "Q8NAM6-1", "NP_689890", "zinc finger and SCAN domain-containing protein 4", "433", "The ZSCAN4 gene encodes a protein involved in telomere maintenance and with a key role in the critical feature of mouse embryonic stem (ES) cells, namely, defying cellular senescence and maintaining normal karyotype for many cell divisions in culture (Zalzman et al., 2010 [PubMed 20336070]).[supplied by OMIM, May 2010]. " ], [ "Q7Z3S9-1", "NP_982283", "notch homolog 2 N-terminal-like protein A isoform 1", "236", "" ], [ "Q5VST9-1", "NP_001258152", "obscurin isoform IC", "8923", "The obscurin gene spans more than 150 kb, contains over 80 exons and encodes a protein of approximately 720 kDa. The encoded protein contains 68 Ig domains, 2 fibronectin domains, 1 calcium/calmodulin-binding domain, 1 RhoGEF domain with an associated PH domain, and 2 serine-threonine kinase domains. This protein belongs to the family of giant sacromeric signaling proteins that includes titin and nebulin, and may have a role in the organization of myofibrils during assembly and may mediate interactions between the sarcoplasmic reticulum and myofibrils. Alternatively spliced transcript variants encoding different isoforms have been identified. [provided by RefSeq, Jul 2008]. " ], [ "P43360-1", "NP_005354", "melanoma-associated antigen 6", "314", "This gene is a member of the MAGEA gene family. The members of this family encode proteins with 50 to 80% sequence identity to each other. The promoters and first exons of the MAGEA genes show considerable variability, suggesting that the existence of this gene family enables the same function to be expressed under different transcriptional controls. The MAGEA genes are clustered at chromosomal location Xq28. They have been implicated in some hereditary disorders, such as dyskeratosis congenita. Alternative splicing results in multiple transcript variants. [provided by RefSeq, Aug 2013]. " ], [ "Q6T423-1", "NP_955384", "solute carrier family 22 member 25 isoform a", "547", "" ], [ "Q16720-1", "NP_001001344", "plasma membrane calcium-transporting ATPase 3 isoform 3b", "1220", "The protein encoded by this gene belongs to the family of P-type primary ion transport ATPases characterized by the formation of an aspartyl phosphate intermediate during the reaction cycle. These enzymes remove bivalent calcium ions from eukaryotic cells against very large concentration gradients and play a critical role in intracellular calcium homeostasis. The mammalian plasma membrane calcium ATPase isoforms are encoded by at least four separate genes and the diversity of these enzymes is further increased by alternative splicing of transcripts. The expression of different isoforms and splice variants is regulated in a developmental, tissue- and cell type-specific manner, suggesting that these pumps are functionally adapted to the physiological needs of particular cells and tissues. This gene encodes the plasma membrane calcium ATPase isoform 3. Alternatively spliced transcript variants encoding different isoforms have been identified. [provided by RefSeq, Jul 2008]. " ], [ "P0DQW0-1", "NP_001258604", "zinc finger CCCH domain-containing protein 11C", "805", "" ], [ "Q9HAR2-1", "NP_001309175", "adhesion G protein-coupled receptor L3 isoform 3 precursor", "1240", "This gene encodes a member of the latrophilin subfamily of G-protein coupled receptors (GPCR). Latrophilins may function in both cell adhesion and signal transduction. In experiments with non-human species, endogenous proteolytic cleavage within a cysteine-rich GPS (G-protein-coupled-receptor proteolysis site) domain resulted in two subunits (a large extracellular N-terminal cell adhesion subunit and a subunit with substantial similarity to the secretin/calcitonin family of GPCRs) being non-covalently bound at the cell membrane. [provided by RefSeq, Jul 2008]. " ], [ "Q8NFR3-1", "NP_001035189", "serine palmitoyltransferase small subunit B", "76", "Serine palmitoyltransferase (SPT; EC 2.3.1.50) catalyzes the first committed and rate-limiting step in sphingolipid biosynthesis. SSSPTB is a small SPT subunit that stimulates SPT activity and confers acyl-CoA preference to the SPT catalytic heterodimer of SPTLC1 (MIM 605712) and either SPTLC2 (MIM 605713) or SPTLC3 (MIM 611120) (Han et al., 2009 [PubMed 19416851]).[supplied by OMIM, Nov 2010]. " ], [ "Q96D59-1", "NP_659488", "E3 ubiquitin-protein ligase RNF183", "192", "" ], [ "O95264-1", "NP_006019", "5-hydroxytryptamine receptor 3B isoform 1 precursor", "441", "The product of this gene belongs to the ligand-gated ion channel receptor superfamily. This gene encodes subunit B of the type 3 receptor for 5-hydroxytryptamine (serotonin), a biogenic hormone that functions as a neurotransmitter, a hormone, and a mitogen. This receptor causes fast, depolarizing responses in neurons after activation. It is not functional as a homomeric complex, but a pentaheteromeric complex with subunit A (HTR3A) displays the full functional features of this receptor. [provided by RefSeq, Aug 2011]. " ], [ "P0DM63-1", "NP_001269436", "nuclear pore complex-interacting protein family member A7", "369", "" ], [ "Q15415-1", "NP_001006117", "RNA-binding motif protein, Y chromosome, family 1 member F/J", "496", "This gene encodes a protein containing an RNA-binding motif in the N-terminus and four SRGY (serine, arginine, glycine, tyrosine) boxes in the C-terminus. This protein likely functions as a splicing factor during spermatogenesis. Multiple closely related paralogs of this gene are found in a gene cluster in the AZFb azoospermia factor region of chromosome Y. Most of these related copies are thought to be pseudogenes, though several likely encode functional proteins. [provided by RefSeq, Mar 2016]. " ], [ "Q8NF91-1", "NP_149062", "nesprin-1 isoform 2", "8749", "This gene encodes a spectrin repeat containing protein expressed in skeletal and smooth muscle, and peripheral blood lymphocytes, that localizes to the nuclear membrane. Mutations in this gene have been associated with autosomal recessive spinocerebellar ataxia 8, also referred to as autosomal recessive cerebellar ataxia type 1 or recessive ataxia of Beauce. Alternatively spliced transcript variants encoding different isoforms have been described. [provided by RefSeq, Jul 2008]. " ], [ "Q9H7C9-1", "NP_001303887", "mth938 domain-containing protein isoform b", "137", "" ], [ "P09086-1", "NP_001193954", "POU domain, class 2, transcription factor 2 isoform 1", "479", "The protein encoded by this gene is a homeobox-containing transcription factor of the POU domain family. The encoded protein binds the octamer sequence 5'-ATTTGCAT-3', a common transcription factor binding site in immunoglobulin gene promoters. Several transcript variants encoding different isoforms have been found for this gene. [provided by RefSeq, Oct 2011]. " ], [ "Q8IZI9-1", "NP_001333866", "interferon lambda-3 isoform 1", "200", "This gene encodes a cytokine distantly related to type I interferons and the IL-10 family. This gene, interleukin 28A (IL28A), and interleukin 29 (IL29) are three closely related cytokine genes that form a cytokine gene cluster on a chromosomal region mapped to 19q13. Expression of the cytokines encoded by the three genes can be induced by viral infection. All three cytokines have been shown to interact with a heterodimeric class II cytokine receptor that consists of interleukin 10 receptor, beta (IL10RB) and interleukin 28 receptor, alpha (IL28RA). [provided by RefSeq, Jul 2008]. " ], [ "Q93033-1", "NP_001243035", "immunoglobulin superfamily member 2 isoform 1 precursor", "1021", "" ], [ "Q9GZU5-1", "NP_072089", "nyctalopin precursor", "476", "The product of this gene belongs to the small leucine-rich proteoglycan (SLRP) family of proteins. Defects in this gene are the cause of congenital stationary night blindness type 1 (CSNB1), also called X-linked congenital stationary night blindness (XLCSNB). CSNB1 is a rare inherited retinal disorder characterized by impaired scotopic vision, myopia, hyperopia, nystagmus and reduced visual acuity. The role of other SLRP proteins suggests that mutations in this gene disrupt developing retinal interconnections involving the ON-bipolar cells, leading to the visual losses seen in patients with complete CSNB. [provided by RefSeq, Oct 2008]. " ], [ "Q02045-1", "NP_002468", "myosin light chain 5 isoform 1", "173", "This gene encodes one of the myosin light chains, a component of the hexameric ATPase cellular motor protein myosin. Myosin is composed of two heavy chains, two nonphosphorylatable alkali light chains, and two phosphorylatable regulatory light chains. This gene product, one of the regulatory light chains, is expressed in fetal muscle and in adult retina, cerebellum, and basal ganglia. [provided by RefSeq, Jul 2008]. " ], [ "Q9H7C9-1", "NP_001303886", "mth938 domain-containing protein isoform a", "147", "" ], [ "O14607-1", "NP_001245178", "histone demethylase UTY isoform 4", "1444", "This gene encodes a protein containing tetratricopeptide repeats which are thought to be involved in protein-protein interactions. The encoded protein is also a minor histocompatibility antigen which may induce graft rejection of male stem cell grafts. A large number of alternatively spliced transcripts have been observed for this gene, but the full length nature of some of these variants has not been determined. [provided by RefSeq, Apr 2012]. " ], [ "P30518-1", "NP_000045", "vasopressin V2 receptor isoform 1", "371", "This gene encodes the vasopressin receptor, type 2, also known as the V2 receptor, which belongs to the seven-transmembrane-domain G protein-coupled receptor (GPCR) superfamily, and couples to Gs thus stimulating adenylate cyclase. The subfamily that includes the V2 receptor, the V1a and V1b vasopressin receptors, the oxytocin receptor, and isotocin and mesotocin receptors in non-mammals, is well conserved, though several members signal via other G proteins. All bind similar cyclic nonapeptide hormones. The V2 receptor is expressed in the kidney tubule, predominantly in the distal convoluted tubule and collecting ducts, where its primary property is to respond to the pituitary hormone arginine vasopressin (AVP) by stimulating mechanisms that concentrate the urine and maintain water homeostasis in the organism. When the function of this gene is lost, the disease Nephrogenic Diabetes Insipidus (NDI) results. The V2 receptor is also expressed outside the kidney although its tissue localization is uncertain. When these 'extrarenal receptors' are stimulated by infusion of a V2 selective agonist (dDAVP), a variety of clotting factors are released into the bloodstream. The physiologic importance of this property is not known - its absence does not appear to be detrimental in NDI patients. The gene expression has also been described in fetal lung tissue and lung cancer associated with alternative splicing. [provided by RefSeq, Jul 2008]. " ], [ "Q8NI99-1", "NP_001308340", "angiopoietin-related protein 6 precursor", "470", "" ], [ "Q6UW56-1", "NP_001164266", "all-trans retinoic acid-induced differentiation factor isoform c precursor", "229", "This gene is thought to be involved in apoptosis, and may also be involved in hematopoietic development and differentiation. The use of alternative splice sites and promotors result in multiple transcript variants encoding different isoforms.[provided by RefSeq, Dec 2009]. " ], [ "Q9NUQ8-1", "NP_060828", "ATP-binding cassette sub-family F member 3 isoform 1", "709", "This gene encodes a member of the ATP-binding cassette (ABC) transporter superfamily. ATP-binding cassette proteins transport various molecules across extra- and intracellular membranes. The protein encoded by this gene displays antiviral effect against flaviviruses. Alternatively spliced transcript variants encoding different isoforms have been found for this gene. [provided by RefSeq, May 2017]. " ], [ "Q14657-1", "NP_006005", "EKC/KEOPS complex subunit LAGE3", "143", "This gene belongs to the ESO/LAGE gene family, members of which are clustered together on chromosome Xq28, and have similar exon-intron structures. Unlike the other family members which are normally expressed only in testis and activated in a wide range of human tumors, this gene is ubiquitously expressed in somatic tissues. The latter, combined with the finding that it is highly conserved in mouse and rat, suggests that the encoded protein is functionally important. An intronless pseudogene with high sequence similarity to this gene is located on chromosome 9. [provided by RefSeq, Jul 2008]. " ] ] }, "readme": "Name\n - Human Protein Information (NCBI RefSeq)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2019-01-23T17:21:05.888176\n\nModified on\n - 2022-09-26T08:44:32.946781\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 Human Protein Information (NCBI RefSeq) dataset contains human [taxid:9606] 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 - NCBI RefSeq\n - protein summary\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: human_protein_xref_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_xref_refseq.csv\n Name: refseq_protein_all_9606.gpff\n URI: https:/data.glygen.org/ln2downloads/ncbi/refseq/2023_10_12/refseq_protein_all_9606.gpff\n Output Subdomain\n Name: human_protein_info_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_refseq.csv\n Name: human_protein_info_refseq.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_info_refseq.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"18692\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"21429\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"21402\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"2139\"\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"11869\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/human_protein_info_refseq.csv" }