{ "bcoid": "GLY_000645", "title": "Fruitfly Protein Information (NCBI RefSeq)", "description": "The Fruitfly Protein Information (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein information ...", "filename": "fruitfly_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": [ "Drosophila melanogaster" ], "molecule": [ "Protein" ], "tags": [ "Protein Information" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "B7Z101-1...", "NP_001138216..." ], [ "Q7KN85-1...", "NP_001137674..." ] ], "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" } ], [ "B7Z101-1", "NP_001138216", "uncharacterized protein", "200", "" ], [ "Q7KN85-1", "NP_001137674", "ATP citrate lyase, isoform E", "1112", "" ], [ "Q7KU18-1", "NP_608696", "uncharacterized protein", "275", "" ], [ "Q8IPI3-1", "NP_001260178", "Na[+]-driven anion exchanger 1, isoform E", "1086", "" ], [ "Q9VJT4-1", "NP_609705", "male sterile (2) 34Fe", "1566", "" ], [ "Q9VZL1-1", "NP_523910", "maggie, isoform A", "148", "" ], [ "Q9VF02-1", "NP_001287351", "helicase 89B, isoform C", "1923", "" ], [ "Q27237-1", "NP_001286777", "uncharacterized protein, isoform E", "445", "" ], [ "Q9VIP9-1", "NP_001286094", "barren, isoform C", "735", "" ], [ "Q9VID4-1", "NP_001163032", "mondo, isoform F", "1119", "" ], [ "Q9VTG6-1", "NP_648447", "uncharacterized protein, isoform B", "447", "" ], [ "P13097-1", "NP_536753", "enhancer of split m7, helix-loop-helix", "186", "" ], [ "Q9W1F0-1", "NP_611858", "uncharacterized protein", "202", "" ], [ "Q9V428-1", "NP_001285902", "icarus, isoform B", "283", "" ], [ "Q9VZX7-1", "NP_001261341", "Autophagy-related 2, isoform B", "1906", "" ], [ "Q9VVJ7-1", "NP_649000", "uncharacterized protein", "178", "" ], [ "Q9NBD7-1", "NP_524651", "chromosome bows, isoform A", "1491", "" ], [ "Q9W530-1", "NP_569974", "uncharacterized protein", "205", "" ], [ "P17886-1", "NP_477118", "crooked neck", "702", "" ], [ "M9PDW8-1", "NP_001259276", "uncharacterized protein, isoform M", "1826", "" ], [ "M9MS30-1", "NP_001188557", "uncharacterized protein, isoform A", "87", "" ], [ "M9NDS9-1", "NP_001096934", "chitinase 6, isoform H", "2225", "" ], [ "Q9VZ26-1", "NP_001245617", "uncharacterized protein, isoform B", "116", "" ], [ "Q27294-1", "NP_001259602", "cabeza, isoform E", "124", "" ], [ "P19109-1", "NP_001246941", "Rm62, isoform M", "478", "" ], [ "Q07407-1", "NP_524394", "heartless, isoform B", "729", "" ], [ "A0A0B4K7N1-1", "NP_524530", "sidestep, isoform A", "939", "" ], [ "Q9V9U3-1", "NP_733451", "uncharacterized protein, isoform C", "466", "" ], [ "A0A0B4LG30-1", "NP_001286618", "uncharacterized protein, isoform B", "282", "" ], [ "Q9VR36-1", "NP_608867", "uncharacterized protein", "489", "" ], [ "Q9VL60-1", "NP_001285787", "uncharacterized protein, isoform B", "463", "" ], [ "M9MRT1-1", "NP_609442", "uncharacterized protein, isoform B", "346", "" ], [ "Q9VTP4-1", "NP_648514", "ribosomal protein L10Ab, isoform A", "217", "" ], [ "Q400N2-1", "NP_001261866", "Pericentrin-like protein, isoform O", "1701", "" ], [ "A0A6I8WFJ4-1", "NP_001104054", "glycoprotein hormone alpha 2", "129", "" ], [ "Q9W3J1-1", "NP_572452", "Gbeta5", "358", "" ], [ "A0A0B4JD97-1", "NP_001246915", "transforming acidic coiled-coil protein, isoform L", "1225", "" ], [ "Q9VNG6-1", "NP_649574", "Rab23", "268", "" ], [ "Q9VHS4-1", "NP_524277", "odorant receptor 85a", "397", "" ], [ "Q9VEH9-1", "NP_001287377", "uncharacterized protein, isoform B", "153", "" ], [ "A0A0B4KGE5-1", "NP_524724", "bonus, isoform A", "1133", "" ], [ "Q9VCX3-1", "NP_651072", "mitochondrial ribosomal protein L45", "361", "" ], [ "Q9VBD5-1", "NP_733160", "TweedleN", "309", "" ], [ "Q0KHY5-1", "NP_001036778", "uncharacterized protein", "47", "" ], [ "A1Z7T0-1", "NP_001286243", "protein kinase N, isoform P", "1280", "" ], [ "A1Z9J3-1", "NP_001163147", "short stop, isoform Q", "5155", "" ], [ "Q9V416-1", "NP_995719", "uncharacterized protein, isoform B", "1259", "" ], [ "Q7KT16-1", "NP_724288", "varicose, isoform B", "636", "" ], [ "Q9W0N5-1", "NP_612054", "uncharacterized protein", "528", "" ], [ "Q9VZP5-1", "NP_001246600", "eukaryotic translation initiation factor 5B, isoform D", "1090", "" ], [ "A8JNK1-1", "NP_001261402", "ensconsin, isoform J", "968", "" ], [ "Q8IRB3-1", "NP_729000", "uncharacterized protein", "415", "" ], [ "Q9GNK5-1", "NP_001163396", "peptidoglycan recognition protein LC, isoform D", "500", "" ], [ "Q9VT90-1", "NP_524018", "odorant receptor 67c", "404", "" ], [ "X2JGL7-1", "NP_648565", "spermine synthase, isoform B", "366", "" ], [ "Q9VVU8-1", "NP_001246828", "cytochrome c oxidase subunit 6A-like 2, isoform C", "289", "" ], [ "M9PJN5-1", "NP_573017", "histone deacetylase 6, isoform A", "1128", "" ], [ "Q9VRI1-1", "NP_001285519", "what else, isoform B", "85", "" ], [ "Q8IMN9-1", "NP_001189302", "uncharacterized protein, isoform B", "750", "" ], [ "Q9NJH0-1", "NP_001189308", "eukaryotic translation elongation factor 1 gamma, isoform C", "431", "" ], [ "A0A0B4K6Z6-1", "NP_001036520", "down syndrome cell adhesion molecule 1, isoform L", "2031", "" ], [ "A1Z8G0-1", "NP_001137643", "menage a trois, isoform C", "585", "" ], [ "Q9W2M0-1", "NP_611545", "Rabaptin-5", "647", "" ], [ "Q9VPW2-1", "NP_608563", "Autophagy-related 4a, isoform A", "411", "" ], [ "Q24246-11", "NP_001285486", "short wing, isoform N", "634", "" ], [ "P16376-1", "NP_001262499", "seven up, isoform E", "554", "" ], [ "A0A0B4KH37-1", "NP_001138092", "ladybird late, isoform B", "294", "" ], [ "Q7KS72-1", "NP_476873", "C15", "339", "" ], [ "Q9VPT6-1", "NP_608547", "uncharacterized protein", "263", "" ], [ "Q9VPD7-1", "NP_730548", "uncharacterized protein, isoform B", "246", "" ], [ "Q9W5B5-1", "NP_651985", "uncharacterized protein", "406", "" ], [ "M9PDW8-1", "NP_001284946", "uncharacterized protein, isoform W", "4808", "" ], [ "P46150-1", "NP_001245583", "moesin, isoform K", "646", "" ], [ "X2JEY5-1", "NP_001285234", "AMP deaminase, isoform L", "786", "" ], [ "Q9VDH8-1", "NP_001287433", "ribosomal protein S30, isoform C", "132", "" ], [ "O01367-1", "NP_001027203", "held out wings, isoform C", "380", "" ], [ "A0A0B4LI00-1", "NP_001287561", "uncharacterized protein", "69", "" ], [ "Q7KPG8-1", "NP_610605", "menage a trois 1", "320", "" ], [ "Q7JR72-1", "NP_725208", "no extended memory, isoform A", "290", "" ], [ "O77477-1", "NP_001286791", "uncharacterized protein, isoform B", "406", "" ], [ "Q95SH0-1", "NP_611864", "PAS kinase", "985", "" ], [ "Q9VQ86-1", "NP_001259914", "uncharacterized protein, isoform B", "587", "" ], [ "Q9VLB7-1", "NP_001245953", "GDP dissociation inhibitor, isoform B", "443", "" ], [ "X2JAM4-1", "NP_001189034", "supervillin, isoform J", "266", "" ] ] }, "readme": "Name\n - Fruitfly Protein Information (NCBI RefSeq)\n\nVersion\n - v-2.1.1\n\nCreated on\n - 2022-08-30T16:17:01.573604\n\nModified on\n - 2022-09-26T09:08:12.614356\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 - \n\nChecksum\n - \n\nUsability Domain\n - The Fruitfly Protein Information (NCBI RefSeq) dataset contains fruitfly [taxid:7227] 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: fruitfly_protein_xref_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_refseq.csv\n Name: refseq_protein_all_7227.gpff\n URI: /data/shared/glyds/downloads/ncbi/refseq/2023_04/refseq_protein_all_7227.gpff\n Output Subdomain\n Name: fruitfly_protein_info_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.csv\n Name: fruitfly_protein_info_refseq.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1581\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"1684\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"1046\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"951\"\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_info_refseq.csv" }