{ "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" ], "tag": [ "Protein Information" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "A8QI34-1...", "NP_001104092..." ], [ "Q9V4A7-1...", "NP_001245400..." ] ], "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" } ], [ "A8QI34-1", "NP_001104092", "JYalpha", "1009", "" ], [ "Q9V4A7-1", "NP_001245400", "plexin B, isoform B", "2051", "" ], [ "P19538-1", "NP_524617", "cubitus interruptus, isoform A", "1397", "" ], [ "P19538-1", "NP_001245401", "cubitus interruptus, isoform C", "572", "" ], [ "P19538-1", "NP_001245402", "cubitus interruptus, isoform B", "1279", "" ], [ "P55830-1", "NP_001245404", "ribosomal protein S3A, isoform F", "268", "" ], [ "Q8IMA8-1", "NP_001245405", "pangolin, isoform Q", "494", "" ], [ "Q8IMA8-1", "NP_726528", "pangolin, isoform J", "1192", "" ], [ "Q8IMA8-1", "NP_001014685", "pangolin, isoform H", "747", "" ], [ "Q0KIE7-1", "NP_001162819", "ankyrin, isoform E", "1549", "" ], [ "A8DZ26-1", "NP_726533", "anne boleyn, isoform E", "595", "" ], [ "A8DZ26-1", "NP_726535", "anne boleyn, isoform F", "521", "" ], [ "A8DZ26-1", "NP_995587", "anne boleyn, isoform G", "1388", "" ], [ "A8DZ26-1", "NP_726534", "anne boleyn, isoform A", "1314", "" ], [ "A8DZ26-1", "NP_726532", "anne boleyn, isoform D", "658", "" ], [ "A8DZ26-1", "NP_726537", "anne boleyn, isoform C", "497", "" ], [ "A8DZ26-1", "NP_001096849", "anne boleyn, isoform H", "1451", "" ], [ "A8DZ26-1", "NP_001259043", "anne boleyn, isoform I", "1290", "" ], [ "Q8IMA2-1", "NP_726538", "uncharacterized protein", "443", "" ], [ "Q8SYQ4-1", "NP_001284709", "uncharacterized protein, isoform B", "148", "" ], [ "Q2PDM3-1", "NP_001259044", "uncharacterized protein, isoform D", "1965", "" ], [ "Q2PDM3-1", "NP_001033801", "uncharacterized protein, isoform E", "2289", "" ], [ "Q2PDM3-1", "NP_001259045", "uncharacterized protein, isoform F", "1951", "" ], [ "Q2PDM3-1", "NP_001259046", "uncharacterized protein, isoform G", "1945", "" ], [ "H9XVM3-1", "NP_651905", "ADP ribosylation factor-like 4, isoform A", "312", "" ], [ "H9XVM3-1", "NP_001245408", "ADP ribosylation factor-like 4, isoform B", "313", "" ], [ "H9XVM3-1", "NP_001259047", "ADP ribosylation factor-like 4, isoform C", "100", "" ], [ "Q7JUN3-1", "NP_001245409", "ATP binding cassette subfamily D member 1, isoform H", "730", "" ], [ "Q9V4B6-1", "NP_726548", "uncharacterized protein, isoform A", "1459", "" ], [ "Q9V4B6-1", "NP_001245410", "uncharacterized protein, isoform B", "1363", "" ], [ "Q9XYM0-1", "NP_651908", "Crk oncogene, isoform A", "271", "" ], [ "Q9XYM0-1", "NP_726550", "Crk oncogene, isoform B", "253", "" ], [ "Q9XYM0-1", "NP_001284710", "Crk oncogene, isoform G", "84", "" ], [ "Q9XYM0-1", "NP_001284711", "Crk oncogene, isoform H", "64", "" ], [ "Q9XYM0-1", "NP_001245411", "Crk oncogene, isoform E", "263", "" ], [ "Q9XYM0-1", "NP_001245412", "Crk oncogene, isoform D", "184", "" ], [ "Q9V4B8-1", "NP_001284712", "uncharacterized protein, isoform C", "917", "" ], [ "Q9V4C0-1", "NP_651912", "yellow-h", "463", "" ], [ "H9XVM9-1", "NP_651913", "uncharacterized protein, isoform B", "743", "" ], [ "H9XVM9-1", "NP_995588", "uncharacterized protein, isoform D", "264", "" ], [ "H9XVM9-1", "NP_001162821", "uncharacterized protein, isoform F", "884", "" ], [ "H9XVM9-1", "NP_726553", "uncharacterized protein, isoform I", "589", "" ], [ "H9XVM9-1", "NP_001162823", "uncharacterized protein, isoform J", "694", "" ], [ "H9XVM9-1", "NP_001245413", "uncharacterized protein, isoform K", "860", "" ], [ "H9XVM9-1", "NP_001245414", "uncharacterized protein, isoform L", "905", "" ], [ "H9XVM9-1", "NP_001259049", "uncharacterized protein, isoform M", "843", "" ], [ "A8DZ27-1", "NP_001096850", "defective proboscis extension response 7, isoform F", "312", "" ], [ "A8DZ27-1", "NP_001096851", "defective proboscis extension response 7, isoform G", "286", "" ], [ "H9XVN1-1", "NP_001033802", "Rho GTPase activating protein at 102A, isoform C", "1074", "" ], [ "H9XVN1-1", "NP_651914", "Rho GTPase activating protein at 102A, isoform E", "1137", "" ], [ "H9XVN1-1", "NP_001245416", "Rho GTPase activating protein at 102A, isoform D", "1256", "" ], [ "H9XVN1-1", "NP_001259050", "Rho GTPase activating protein at 102A, isoform F", "1242", "" ], [ "Q86P06-1", "NP_995592", "nuclear factor I, isoform B", "766", "" ], [ "Q86P06-1", "NP_001259051", "nuclear factor I, isoform C", "762", "" ], [ "Q9V4C4-1", "NP_726558", "synaptotagmin 7, isoform B", "327", "" ], [ "Q9V4C4-1", "NP_995593", "synaptotagmin 7, isoform F", "283", "" ], [ "Q9V4C4-1", "NP_726557", "synaptotagmin 7, isoform A", "416", "" ], [ "Q9V4C4-1", "NP_001245417", "synaptotagmin 7, isoform I", "345", "" ], [ "Q9V3W9-1", "NP_726561", "Rad23, isoform B", "343", "" ], [ "Q9V3W9-1", "NP_001259052", "Rad23, isoform C", "414", "" ], [ "Q9V4C6-1", "NP_001284713", "Zinc/iron regulated transporter-related protein 102B, isoform F", "297", "" ], [ "Q9V4C6-1", "NP_001137855", "Zinc/iron regulated transporter-related protein 102B, isoform D", "201", "" ], [ "Q8SX35-1", "NP_726563", "ring finger protein 11, isoform A", "147", "" ], [ "Q8SX35-1", "NP_001259053", "ring finger protein 11, isoform B", "146", "" ], [ "Q59DP9-1", "NP_001188514", "plasma membrane calcium ATPase, isoform O", "1206", "" ], [ "Q59DP9-1", "NP_001188515", "plasma membrane calcium ATPase, isoform P", "1194", "" ], [ "Q59DP9-1", "NP_001188516", "plasma membrane calcium ATPase, isoform Q", "1187", "" ], [ "Q59DP9-1", "NP_001188517", "plasma membrane calcium ATPase, isoform R", "1210", "" ], [ "Q59DP9-1", "NP_001014688", "plasma membrane calcium ATPase, isoform K", "1183", "" ], [ "Q59DP9-1", "NP_001014689", "plasma membrane calcium ATPase, isoform M", "1255", "" ], [ "Q59DP9-1", "NP_001014687", "plasma membrane calcium ATPase, isoform N", "1120", "" ], [ "Q9V4C8-1", "NP_001245420", "host cell factor, isoform E", "1484", "" ], [ "Q7KQN5-1", "NP_001245421", "datilografo, isoform C", "1150", "" ], [ "Q7KQN5-1", "NP_001245422", "datilografo, isoform D", "791", "" ], [ "Q7KQN5-1", "NP_726568", "datilografo, isoform B", "1140", "" ], [ "Q961D9-1", "NP_651922", "legless", "1469", "" ], [ "Q7JMV3-1", "NP_726574", "Calcium/calmodulin-dependent protein kinase I, isoform H", "284", "" ], [ "Q7JMV3-1", "NP_524622", "Calcium/calmodulin-dependent protein kinase I, isoform G", "405", "" ], [ "Q7JMV3-1", "NP_726571", "Calcium/calmodulin-dependent protein kinase I, isoform I", "390", "" ], [ "Q9V4D4-1", "NP_651923", "TBP-associated factor 3", "1406", "" ], [ "L7S1A0-1", "NP_001334686", "uncharacterized protein", "151", "" ], [ "Q8IMC6-1", "NP_651924", "asator, isoform D", "1349", "" ], [ "Q8IMC6-1", "NP_726576", "asator, isoform E", "1262", "" ], [ "Q8IMC6-1", "NP_001259054", "asator, isoform G", "1144", "" ] ] }, "readme": "Name\n - Fruitfly Protein Information (NCBI RefSeq)\n\nVersion\n - v-2.2.1\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-2.2.1/reviewed/fruitfly_protein_xref_refseq.csv\n Name: refseq_protein_all_7227.gpff\n URI: https:/data.glygen.org/ln2downloads/ncbi/refseq/2023_10_12/refseq_protein_all_7227.gpff\n Output Subdomain\n Name: fruitfly_protein_info_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_refseq.csv\n Name: fruitfly_protein_info_refseq.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_info_refseq.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"13691\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"20559\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"12500\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"2543\"\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/fruitfly_protein_info_refseq.csv" }