{ "bcoid": "GLY_000392", "title": "Human Protein Names (NCBI RefSeq)", "description": "The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] protein names (primary and ...", "filename": "human_protein_proteinnames_refseq.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Protein Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF5-1...", "NP_001159776..." ], [ "Q8TBF5-1...", "NP_001159776..." ] ], "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" } ], [ "Q8TBF5-1", "NP_001159776.1", "phosphatidylinositol-glycan biosynthesis class X protein isoform 1 precursor" ], [ "Q8TBF5-1", "NP_001159776.1", "GPI-mannosyltransferase subunit; phosphatidylinositol-glycan biosynthesis class X protein" ], [ "Q8TBF4-1", "NP_149105.3", "zinc finger CCHC-type and RNA-binding motif-containing protein 1" ], [ "Q8TBF4-1", "NP_149105.3", "U11/U12-31K; U11/U12 snRNP 31K; zinc finger CCHC-type and RNA binding motif 1; U11/U12 snRNP 31 kDa protein; U11/U12 small nuclear ribonucleoprotein 31 kDa protein" ], [ "Q9NRJ4-1", "NP_001007467.1", "tubby-related protein 4 isoform 2" ], [ "Q9NRJ4-1", "NP_001007467.1", "tubby super-family protein; tubby like protein 4; tubby superfamily protein; tubby-related protein 4" ], [ "Q9NQ79-1", "NP_001193457.1", "cartilage acidic protein 1 isoform B precursor" ], [ "Q9NQ79-1", "NP_001193457.1", "acidic secreted protein in cartilage; chondrocyte expressed protein 68 kDa CEP-68" ], [ "Q9NVL8-1", "NP_001269985.1", "uncharacterized protein CCDC198 isoform 1" ], [ "Q9NVL8-1", "NP_001269985.1", "uncharacterized protein C14orf105" ], [ "Q9NRQ5-1", "NP_064564.1", "single-pass membrane and coiled-coil domain-containing protein 4" ], [ "Q9NRQ5-1", "NP_064564.1", "UPF0443 protein C11orf75" ], [ "Q8IZF5-1", "NP_001138640.1", "adhesion G-protein coupled receptor F3 isoform 1 precursor" ], [ "Q8IZF5-1", "NP_001138640.1", "G protein-coupled receptor 113; G protein-coupled receptor PGR23; seven transmembrane helix receptor; probable G-protein coupled receptor 113" ], [ "P30613-1", "NP_000289.1", "pyruvate kinase PKLR isoform 1" ], [ "P30613-1", "NP_000289.1", "pyruvate kinase type L; pyruvate kinase, liver and blood cell; pyruvate kinase 1; pyruvate kinase isozyme R/L; R-type/L-type pyruvate kinase; red cell/liver pyruvate kinase; pyruvate kinase isozymes R/L; pyruvate kinase isozymes L/R; pyruvate kinase PKLR; pyruvate kinase, liver and RBC" ], [ "Q5H9L4-1", "NP_001161946.1", "transcription initiation factor TFIID subunit 7-like isoform 2" ], [ "Q5H9L4-1", "NP_001161946.1", "TBP-associated factor, RNA polymerase II, Q; TAF7-like RNA polymerase II, TATA box binding protein (TBP)-associated factor, 50kDa; cancer/testis antigen 40; RNA polymerase II TBP-associated factor subunit Q; TATA box-binding protein-associated factor 50 kDa; transcription initiation factor TFIID 50 kDa subunit" ], [ "Q9BZL4-1", "NP_001258547.1", "protein phosphatase 1 regulatory subunit 12C isoform b" ], [ "Q9BZL4-1", "NP_001258547.1", "protein phosphatase 1, regulatory (inhibitor) subunit 12C; myosin-binding subunit 85; leukocyte receptor cluster (LRC) member 3; leukocyte receptor cluster (LRC) encoded novel gene 3; protein phosphatase 1 myosin-binding subunit p85; protein phosphatase 1 myosin-binding subunit of 85 kDa" ], [ "Q5QJ38-1", "NP_001008536.1", "trichohyalin-like protein 1" ], [ "Q5QJ38-1", "NP_001008536.1", "intermediate filament-associated protein; S100 calcium-binding protein A17; basalin" ], [ "Q9NQ75-1", "NP_001157586.1", "cas scaffolding protein family member 4 isoform b" ], [ "Q9NQ75-1", "NP_001157586.1", "Cas scaffolding protein family member 4; HEF-like protein; HEF1-EFS-p130Cas-like protein" ], [ "P20930-1", "NP_002007.1", "filaggrin" ], [ "P20930-1", "NP_002007.1", "epidermal filaggrin" ], [ "P20933-1", "NP_000018.2", "N(4)-(beta-N-acetylglucosaminyl)-L-asparaginase isoform 1 preproprotein" ], [ "P20933-1", "NP_000018.2", "N(4)-(beta-N-acetylglucosaminyl)-L-asparaginase; glycosylasparaginase; N4-(N-acetyl-beta-glucosaminyl)-L-asparagine amidase; aspartylglucosylamine deaspartylase" ], [ "P20936-1", "NP_002881.1", "ras GTPase-activating protein 1 isoform 1" ], [ "P20936-1", "NP_002881.1", "RAS p21 protein activator (GTPase activating protein) 1; triphosphatase-activating protein; p120 RAS GTPase activating protein" ], [ "Q8NFX7-1", "NP_001291405.1", "syntaxin-binding protein 6 isoform 1" ], [ "Q9UM21-1", "NP_001153626.1", "alpha-1,3-mannosyl-glycoprotein 4-beta-N-acetylglucosaminyltransferase A isoform 2" ], [ "Q9UM21-1", "NP_001153626.1", "UDP-N-acetylglucosamine:alpha1,3-d-mannoside beta1,4-N-acetylglucosaminyltransferase; UDP-GlcNAc:a-1,3-D-mannoside b-1,4-acetylglucosaminyltransferase IV; alpha-1,3-mannosyl-glycoprotein beta-1,4-N-acetylglucosaminyltransferase; N-acetylglucosaminyltransferase IVa; mannosyl (alpha-1,3-)-glycoprotein beta-1,4-N-acetylglucosaminyltransferase, isozyme A; mannosyl (alpha-1,3-)-glycoprotein beta-1,4-N-acetylglucosaminyltransferase, isoenzyme A; N-glycosyl-oligosaccharide-glycoprotein N-acetylglucosaminyltransferase IVa; UDP-N-acetylglucosamine: alpha-1,3-D-mannoside beta-1,4-N-acetylglucosaminyltransferase IVa; glcNAc-T IVa" ], [ "Q496A3-1", "NP_659463.1", "spermatogenesis-associated serine-rich protein 1" ], [ "P83859-1", "NP_937823.1", "orexigenic neuropeptide QRFP preproprotein" ], [ "P83859-1", "NP_937823.1", "P518 precursor protein; RF(Arg-Phe)amide family 26 amino acid peptide (P518); orexigenic neuropeptide QRFP; prepro-QRFP" ], [ "P40617-1", "NP_001032241.1", "ADP-ribosylation factor-like protein 4A" ], [ "P40617-1", "NP_001032241.1", "ADP-ribosylation factor-like 4; ADP-ribosylation factor-like 4A" ], [ "Q70EL4-1", "NP_001254505.1", "ubiquitin carboxyl-terminal hydrolase 43 isoform 2" ], [ "Q70EL4-1", "NP_001254505.1", "ubiquitin specific protease 43; ubiquitin thioesterase 43; deubiquitinating enzyme 43; ubiquitin-specific-processing protease 43; ubiquitin carboxyl-terminal hydrolase 43; ubiquitin thiolesterase 43" ], [ "Q8TBF2-1", "NP_001182665.1", "prostamide/prostaglandin F synthase isoform a" ], [ "Q8TBF2-1", "NP_001182665.1", "prostamide/PGF synthase; prostamide/PG F synthase; prostamide/prostaglandin F synthase; family with sequence similarity 213 member B; thioredoxin-type PGF synthase" ], [ "Q15573-1", "NP_001188465.1", "TATA box-binding protein-associated factor RNA polymerase I subunit A isoform 1" ], [ "Q15573-1", "NP_001188465.1", "SL1, 48kD subunit; TATA box binding protein (TBP)-associated factor, RNA polymerase I, A, 48kDa; TBP-associated factor 1A; transcription factor SL1; TATA box-binding protein-associated factor 1A; transcription initiation factor SL1/TIF-IB subunit A; RNA polymerase I-specific TBP-associated factor 48 kDa; TATA-box binding protein associated factor, RNA polymerase I, A" ], [ "Q15572-1", "NP_001230085.1", "TATA box-binding protein-associated factor RNA polymerase I subunit C isoform 3" ], [ "Q15572-1", "NP_001230085.1", "transcription factor SL1; SL1, 110kD subunit; TATA box binding protein (TBP)-associated factor, RNA polymerase I, C, 110kDa; TBP-associated factor 1C; TATA box-binding protein-associated factor 1C; transcription initiation factor SL1/TIF-IB subunit C; RNA polymerase I-specific TBP-associated factor 110 kDa; TATA-box binding protein associated factor, RNA polymerase I, C" ], [ "Q9BQP9-1", "NP_001035904.1", "BPI fold-containing family A member 3 isoform 2 precursor" ], [ "Q9BQP9-1", "NP_001035904.1", "short long palate, lung and nasal epithelium carcinoma associated 3" ], [ "Q9H999-1", "NP_078870.1", "pantothenate kinase 3" ], [ "Q9H999-1", "NP_078870.1", "hPanK3; pantothenic acid kinase 3" ], [ "P23919-1", "NP_001158503.1", "thymidylate kinase isoform 2" ], [ "P23919-1", "NP_001158503.1", "deoxythymidylate kinase (thymidylate kinase); dTMP kinase" ], [ "Q8NHX4-1", "NP_620712.2", "spermatogenesis-associated protein 3" ], [ "Q8NHX4-1", "NP_620712.2", "testis and spermatogenesis cell apoptosis related gene 1; testis spermatocyte apoptosis-related protein 1; testis and spermatogenesis cell-related protein 1" ], [ "Q8NHX9-1", "NP_620714.2", "two pore calcium channel protein 2" ], [ "Q8NHX9-1", "NP_620714.2", "voltage-dependent calcium channel protein TPC2" ], [ "A8MU46-1", "NP_001099035.2", "smoothelin-like protein 1" ], [ "A8MU46-1", "NP_001099035.2", "calponin homology-associated smooth muscle protein" ], [ "Q6ZNW5-1", "NP_001013679.2", "GDP-D-glucose phosphorylase 1" ], [ "Q6ZNW5-1", "NP_001013679.2", "GDP-D-glucose phosphorylase C15orf58" ], [ "Q9NXR8-1", "NP_061944.2", "inhibitor of growth protein 3 isoform 1" ], [ "Q9NXR8-1", "NP_061944.2", "inhibitor of growth protein 3" ], [ "Q9C0H2-1", "NP_079526.1", "protein tweety homolog 3" ], [ "Q9C0H2-1", "NP_079526.1", "hTTY3; tweety homolog 3" ], [ "Q9C0H5-1", "NP_001295136.1", "rho GTPase-activating protein 39 isoform 1" ], [ "Q9C0H5-1", "NP_001295136.1", "crossGAP homolog; RhoGAP93B homolog" ], [ "Q9C0H6-1", "NP_061990.2", "kelch-like protein 4 isoform 1" ], [ "Q9C0H6-1", "NP_061990.2", "kelch-like protein 4" ], [ "Q9C0H9-5", "NP_079524.2", "SRC kinase signaling inhibitor 1" ], [ "Q9C0H9-5", "NP_079524.2", "SNAP25-interacting protein; p140Cap; P130Cas-associated protein; SNAP-25-interacting protein" ], [ "Q9NXR1-2", "NP_001137451.1", "nuclear distribution protein nudE homolog 1" ], [ "Q9NXR1-2", "NP_001137451.1", "LIS1-interacting protein NUDE1, rat homolog; nudE nuclear distribution gene E homolog 1; nudE nuclear distribution E homolog 1; epididymis secretory sperm binding protein" ], [ "Q00537-1", "NP_001163935.1", "cyclin-dependent kinase 17 isoform 2" ], [ "Q00537-1", "NP_001163935.1", "serine/threonine-protein kinase PCTAIRE-2; protein kinase cdc2-related PCTAIRE-2; PCTAIRE-motif protein kinase 2; cell division protein kinase 17" ], [ "Q00536-1", "NP_001163931.1", "cyclin-dependent kinase 16 isoform 3" ], [ "Q00536-1", "NP_001163931.1", "PCTAIRE-motif protein kinase 1; serine/threonine-protein kinase PCTAIRE-1; cell division protein kinase 16; testis secretory sperm-binding protein Li 224n" ], [ "Q9NXR5-1", "NP_001273650.1", "ankyrin repeat domain-containing protein 10 isoform 2" ], [ "Q9NXR5-1", "NP_001273650.1", "ankyrin repeat domain-containing protein 10" ], [ "Q00532-1", "NP_004187.2", "cyclin-dependent kinase-like 1 isoform 1" ], [ "Q00532-1", "NP_004187.2", "serine/threonine protein kinase KKIALRE; cyclin-dependent kinase-like 1 (CDC2-related kinase); protein kinase p42 KKIALRE" ], [ "Q96J66-1", "NP_115972.2", "ATP-binding cassette sub-family C member 11 isoform a" ], [ "Q96J66-1", "NP_115972.2", "ATP-binding cassette, sub-family C (CFTR/MRP), member 11; multi-resistance protein 8; ATP-binding cassette transporter MRP8; ATP-binding cassette protein C11; multidrug resistance-associated protein 8; ATP-binding cassette transporter sub-family C member 11; ATP-binding cassette sub-family C member 11" ], [ "O00244-1", "NP_004036.1", "copper transport protein ATOX1" ], [ "O00244-1", "NP_004036.1", "ATX1 antioxidant protein 1 homolog; metal transport protein ATX1" ] ] }, "readme": "Name\n - Human Protein Names (NCBI RefSeq)\n\nVersion\n - 1.8.25\n\nCreated on\n - 2020-03-15T13:26:46.282740\n\nModified on\n - 2020-04-10T11:49:01.913927\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - \n\nChecksum\n - \n\nUsability Domain\n - The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] 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. 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_9606.gpff\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/source/refseq_protein_all_9606.gpff\n Name: human_protein_xref_refseq.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_xref_refseq.csv\n Output Subdomain\n Name: human_protein_proteinnames_refseq.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_proteinnames_refseq.csv\n Name: human_protein_proteinnames_refseq.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_proteinnames_refseq.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/human_protein_proteinnames_refseq.csv" }