{ "bcoid": "GLY_000021", "title": "Human Protein Information (NCBI RefSeq)", "description": "The Human NCBI RefSeq Protein Information dataset contains human [taxid:9606] protein information such ...", "filename": "human_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": "Homo Sapiens", "molecule": "Protein", "tags": "Protein Information", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P03886-1...", "YP_003024026..." ], [ "P03891-1...", "YP_003024027..." ] ], "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" } ], [ "P03886-1", "YP_003024026.1", "NADH dehydrogenase subunit 1", "318", "" ], [ "P03891-1", "YP_003024027.1", "NADH dehydrogenase subunit 2", "347", "" ], [ "P00395-1", "YP_003024028.1", "cytochrome c oxidase subunit I", "513", "" ], [ "P00403-1", "YP_003024029.1", "cytochrome c oxidase subunit II", "227", "" ], [ "P03928-1", "YP_003024030.1", "ATP synthase F0 subunit 8", "68", "" ], [ "P00846-1", "YP_003024031.1", "ATP synthase F0 subunit 6", "226", "" ], [ "P00414-1", "YP_003024032.1", "cytochrome c oxidase subunit III", "261", "" ], [ "P03897-1", "YP_003024033.1", "NADH dehydrogenase subunit 3", "115", "" ], [ "P03901-1", "YP_003024034.1", "NADH dehydrogenase subunit 4L", "98", "" ], [ "P03905-1", "YP_003024035.1", "NADH dehydrogenase subunit 4", "459", "" ], [ "P03915-1", "YP_003024036.1", "NADH dehydrogenase subunit 5", "603", "" ], [ "P03923-1", "YP_003024037.1", "NADH dehydrogenase subunit 6", "174", "" ], [ "P00156-1", "YP_003024038.1", "cytochrome b", "380", "" ], [ "Q01518-1", "XP_011538812.1", "adenylyl cyclase-associated protein 1 isoform X1", "475", "" ], [ "Q7Z5L7-1", "XP_005270514.1", "podocan isoform X2", "613", "" ], [ "Q5VXD3-1", "XP_016855866.1", "sterile alpha motif domain-containing protein 13 isoform X1", "122", "" ], [ "Q96MR6-1", "XP_005270577.1", "cilia- and flagella-associated protein 57 isoform X1", "1250", "" ], [ "A2PYH4-1", "XP_011539151.1", "probable ATP-dependent DNA helicase HFM1 isoform X1", "1435", "" ], [ "O94856-1", "XP_011507621.1", "neurofascin isoform X12", "1347", "" ], [ "Q9Y520-1", "XP_006711301.1", "protein PRRC2C isoform X5", "2896", "" ], [ "O95490-1", "XP_005270723.1", "adhesion G protein-coupled receptor L2 isoform X3", "1459", "" ], [ "Q6ZNA5-1", "XP_011539753.1", "ferric-chelate reductase 1 isoform X1", "592", "" ], [ "Q9UNH6-1", "XP_011539866.1", "sorting nexin-7 isoform X2", "387", "" ], [ "P14859-1", "XP_011507956.1", "POU domain, class 2, transcription factor 1 isoform X2", "743", "" ], [ "Q8WZA1-1", "XP_016857179.1", "protein O-linked-mannose beta-1,2-N-acetylglucosaminyltransferase 1 isoform X2", "660", "" ], [ "Q8N5J2-1", "XP_016857261.1", "ubiquitin carboxyl-terminal hydrolase MINDY-1 isoform X3", "469", "" ], [ "O60241-1", "XP_011540150.1", "adhesion G protein-coupled receptor B2 isoform X1", "1585", "" ], [ "P17040-1", "XP_006710937.1", "zinc finger and SCAN domain-containing protein 20 isoform X1", "1043", "" ], [ "Q6PGN9-1", "XP_016858049.1", "proline/serine-rich coiled-coil protein 1 isoform X1", "363", "" ], [ "Q8N7W2-1", "XP_011517694.1", "BEN domain-containing protein 7 isoform X4", "519", "" ], [ "Q9H4W6-1", "XP_005252725.1", "transcription factor COE3 isoform X4", "596", "" ], [ "Q7Z5L2-1", "XP_011537942.1", "coiled-coil domain-containing protein R3HCC1L isoform X2", "792", "" ], [ "Q5VW22-1", "XP_016871759.1", "arf-GAP with GTPase, ANK repeat and PH domain-containing protein 6 isoform X3", "663", "" ], [ "Q5VWN6-1", "XP_005252532.1", "protein FAM208B isoform X9", "2430", "" ], [ "Q9BXT4-1", "XP_011538265.1", "tudor domain-containing protein 1 isoform X2", "1180", "" ], [ "Q8N323-1", "XP_011540897.1", "NXPE family member 1 isoform X1", "547", "" ], [ "Q9UPX8-1", "XP_005277989.1", "SH3 and multiple ankyrin repeat domains protein 2 isoform X3", "1470", "" ], [ "P48058-1", "XP_006718886.1", "glutamate receptor 4 isoform X2", "902", "" ], [ "Q9C0C7-1", "XP_005253066.1", "activating molecule in BECN1-regulated autophagy protein 1 isoform X1", "1298", "" ], [ "P15918-1", "XP_005253098.1", "V(D)J recombination-activating protein 1 isoform X1", "1043", "" ], [ "O15020-1", "XP_005274249.1", "spectrin beta chain, non-erythrocytic 2 isoform X2", "2390", "" ], [ "P45378-1", "XP_011518645.1", "troponin T, fast skeletal muscle isoform X4", "269", "" ], [ "Q86UT5-1", "XP_011541302.1", "Na(+)/H(+) exchange regulatory cofactor NHE-RF4 isoform X1", "571", "" ], [ "A8K2U0-1", "XP_016874359.1", "alpha-2-macroglobulin-like protein 1 isoform X3", "1454", "" ], [ "Q9UPS6-1", "XP_005253915.1", "histone-lysine N-methyltransferase SETD1B isoform X1", "1966", "" ], [ "Q13683-1", "XP_005268896.1", "integrin alpha-7 isoform X1", "1181", "" ], [ "Q8WUI4-1", "XP_011536783.1", "histone deacetylase 7 isoform X5", "952", "" ], [ "Q5T8P6-1", "XP_011533490.1", "RNA-binding protein 26 isoform X13", "1007", "" ], [ "Q05BV3-1", "XP_006720133.1", "echinoderm microtubule-associated protein-like 5 isoform X7", "1969", "" ], [ "Q3B8N5-1", "XP_005267600.1", "prospero homeobox protein 2 isoform X2", "592", "" ], [ "Q9Y4F5-1", "XP_005267607.1", "centrosomal protein of 170 kDa protein B isoform X3", "1589", "" ], [ "Q6IN85-1", "XP_005267899.1", "serine/threonine-protein phosphatase 4 regulatory subunit 3A isoform X1", "833", "" ], [ "Q17RD7-1", "XP_006720335.1", "synaptotagmin-16 isoform X1", "645", "" ], [ "O95428-1", "XP_011535592.1", "papilin isoform X1", "1278", "" ], [ "Q02078-1", "XP_011519883.1", "myocyte-specific enhancer factor 2A isoform X2", "507", "" ], [ "Q2KHR2-1", "XP_011520227.1", "DNA-binding protein RFX7 isoform X2", "1363", "" ], [ "Q9ULZ0-1", "XP_006721089.1", "TP53-target gene 3 protein isoform X2", "132", "" ], [ "Q8IXQ8-1", "XP_006721092.1", "PDZ domain-containing protein 9 isoform X2", "264", "" ], [ "Q6PII5-1", "XP_005255688.1", "hydroxyacylglutathione hydrolase-like protein isoform X1", "290", "" ], [ "Q15572-1", "XP_005256283.1", "TATA box-binding protein-associated factor RNA polymerase I subunit C isoform X2", "869", "" ], [ "Q8N6K4-1", "XP_016879449.1", "putative uncharacterized protein MGC34800", "173", "" ], [ "P07307-1", "XP_016880141.1", "asialoglycoprotein receptor 2 isoform X7", "311", "" ], [ "Q9BSJ5-1", "XP_011523263.1", "uncharacterized protein C17orf80 isoform X1", "609", "" ], [ "Q8IVT5-1", "XP_011523731.1", "kinase suppressor of Ras 1 isoform X1", "923", "" ], [ "Q8IVV2-1", "XP_016881037.1", "lipoxygenase homology domain-containing protein 1 isoform X10", "2067", "" ], [ "Q68D86-1", "XP_016881464.1", "coiled-coil domain-containing protein 102B isoform X3", "513", "" ], [ "Q8IYT4-1", "XP_006722617.1", "katanin p60 ATPase-containing subunit A-like 2 isoform X1", "538", "" ], [ "Q9Y2G2-1", "XP_006723167.1", "caspase recruitment domain-containing protein 8 isoform X11", "431", "" ], [ "Q6ZSZ5-4", "XP_006722769.1", "rho guanine nucleotide exchange factor 18 isoform X3", "1361", "" ], [ "Q149M9-1", "XP_011526231.1", "NACHT domain- and WD repeat-containing protein 1 isoform X1", "1564", "" ], [ "Q86TI2-1", "XP_011526712.1", "dipeptidyl peptidase 9 isoform X3", "863", "" ], [ "A0A2R8Y872-1", "XP_011525773.1", "putative ATP-dependent RNA helicase TDRD12 isoform X1", "1335", "" ], [ "Q8TB72-1", "XP_005262664.1", "pumilio homolog 2 isoform X1", "1066", "" ], [ "Q7Z4S9-1", "XP_016859347.1", "SH2 domain-containing protein 6 isoform X16", "143", "" ], [ "Q9NUZ1-1", "XP_011509718.1", "acyl-coenzyme A oxidase-like protein isoform X8", "547", "" ], [ "Q3V6T2-1", "XP_011531268.1", "girdin isoform X7", "1871", "" ], [ "Q9NY46-1", "XP_016860149.1", "sodium channel protein type 3 subunit alpha isoform X2", "2000", "" ], [ "Q15858-1", "XP_011509918.1", "sodium channel protein type 9 subunit alpha isoform X1", "1988", "" ], [ "Q6ZV50-1", "XP_016860340.1", "DNA-binding protein RFX8 isoform X1", "586", "" ], [ "Q8TD35-1", "XP_005260257.3", "protein LKAAEAR1 isoform X2", "194", "" ], [ "Q9ULU4-1", "XP_005260423.1", "protein kinase C-binding protein 1 isoform X15", "1186", "" ], [ "P52736-1", "XP_011527639.1", "zinc finger protein 133 isoform X3", "654", "" ], [ "O75354-1", "XP_011527698.1", "ectonucleoside triphosphate diphosphohydrolase 6 isoform X3", "484", "" ], [ "O60299-1", "XP_005260950.1", "leucine zipper putative tumor suppressor 3 isoform X3", "673", "" ] ] }, "readme": "Name\n - Human Protein Information (NCBI RefSeq)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-01-23T17:21:05.888176\n\nModified on\n - 2019-09-12T12:53:11.935170\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]\n\nAuthors\n - \n\nChecksum\n - \n\nUsability Domain\n - The Human NCBI RefSeq Protein Information dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summmary from NCBI RefSeq database. 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/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/ln2wwwdata/source/refseq_protein_all_9606.gpff\n Name: human_protein_info_refseq.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv\n Output Subdomain\n Name: human_protein_info_refseq.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv\n Name: human_protein_info_refseq.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.stat.csv\n\nFields\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"9552\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"14956\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"14956\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"14955\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"1986\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/human_protein_info_refseq.csv" }