{ "bcoid": "GLY_000136", "title": "Mouse Transcript Locus", "description": "Th Mouse Transcript Locus contains UniProtKB mouse [taxid:10090] canonical accessions mapped to their ...", "filename": "mouse_protein_transcriptlocus.csv", "filetype": "csv", "categories": { "status": "Reviewed" }, "minitable": { "content": [ [ "Q8BH24-1...", "Q8BH24-1..." ], [ "Q8BH27-1...", "F8WHT8-1..." ] ], "headers": [ "uniprotkb_ca...", "uniprotkb_is..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "uniprotkb_isoform_ac" }, { "type": "string", "label": "transcript_id" }, { "type": "string", "label": "peptide_id" }, { "type": "string", "label": "chromosome_id" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" } ], [ "Q8BH24-1", "Q8BH24-1", "ENSMUST00000089027", "ENSMUSP00000086422", "2", "153161557", "153208753" ], [ "Q8BH27-1", "F8WHT8-1", "ENSMUST00000037881", "ENSMUSP00000040801", "4", "70463419", "70534822" ], [ "Q8BH27-1", "Q8BH27-1", "ENSMUST00000107359", "ENSMUSP00000102982", "4", "70433083", "70534822" ], [ "Q8BH26-1", "Q8BH26-1", "ENSMUST00000057416", "ENSMUSP00000054611", "12", "102744087", "102745008" ], [ "Q8VF69-1", "Q8VF69-1", "ENSMUST00000215626", "ENSMUSP00000149991", "11", "59589131", "59590087" ], [ "Q9JHR7-1", "F6RPJ9-1", "ENSMUST00000131070", "ENSMUSP00000121358", "19", "37270744", "37330613" ], [ "Q8VF63-1", "Q7TRE2-1", "ENSMUST00000212489", "ENSMUSP00000148535", "9", "37992509", "37993435" ], [ "Q8VF63-1", "Q8VF63-1", "ENSMUST00000074611", "ENSMUSP00000074193", "9", "37992494", "37993435" ], [ "Q8VF60-1", "Q7TS12-1", "ENSMUST00000217039", "ENSMUSP00000150934", "7", "84856371", "84857315" ], [ "Q8VF60-1", "Q8VF60-1", "ENSMUST00000211582", "ENSMUSP00000148266", "7", "84856365", "84857315" ], [ "Q8VF66-1", "Q8VF66-1", "ENSMUST00000075704", "ENSMUSP00000075122", "7", "107822526", "107823467" ], [ "Q8VF65-1", "Q8VF65-1", "ENSMUST00000220193", "ENSMUSP00000151543", "7", "107844790", "107845731" ], [ "Q8VF64-1", "Q8VF64-1", "ENSMUST00000072974", "ENSMUSP00000072741", "9", "38025808", "38026734" ], [ "B2RXV4-1", "B2RXV4-1", "ENSMUST00000085635", "ENSMUSP00000082777", "1", "191008142", "191026093" ], [ "B2RXV4-1", "A0A0A6YWJ7-1", "ENSMUST00000191946", "ENSMUSP00000141578", "1", "191025356", "191026093" ], [ "B2RXV4-1", "A0A0A6YXG8-1", "ENSMUST00000192666", "ENSMUSP00000141985", "1", "191013426", "191025967" ], [ "Q3T9W8-1", "Q3T9W8-1", "ENSMUST00000170816", "ENSMUSP00000131611", "12", "4592829", "4592927" ], [ "E9Q3P4-1", "E9Q3P4-1", "ENSMUST00000171929", "ENSMUSP00000129738", "1", "189642602", "189685106" ], [ "E9Q3P4-1", "E9Q776-1", "ENSMUST00000165663", "ENSMUSP00000130308", "1", "189684647", "189685106" ], [ "E9Q3P4-1", "F6V6F0-1", "ENSMUST00000165798", "ENSMUSP00000132430", "1", "189642697", "189648856" ], [ "E9Q3P4-1", "E9PY14-1", "ENSMUST00000165962", "ENSMUSP00000132759", "1", "189658727", "189685106" ], [ "A0A087WRQ3-1", "A0A075B5Z4-1", "ENSMUST00000103567", "ENSMUSP00000100344", "14", "52427967", "52428874" ], [ "A0A087WRQ3-1", "A0A087WRQ3-1", "ENSMUST00000185651", "ENSMUSP00000140728", "14", "52427967", "52428874" ], [ "Q9CXG9-1", "A0A0J9YU15-1", "ENSMUST00000202907", "ENSMUSP00000143954", "2", "34911164", "34911796" ], [ "Q9CXG9-1", "Q9CXG9-1", "ENSMUST00000028232", "ENSMUSP00000028232", "2", "34895722", "34911796" ], [ "Q07968-1", "Q07968-1", "ENSMUST00000027615", "ENSMUSP00000027615", "1", "139501746", "139523424" ], [ "A5H0M4-1", "A5H0M4-1", "ENSMUST00000081321", "ENSMUSP00000080069", "8", "27447818", "27495033" ], [ "Q9CXG3-1", "D6RJ77-1", "ENSMUST00000143214", "ENSMUSP00000119332", "10", "7792951", "7795862" ], [ "Q9CXG3-1", "Q9CXG3-1", "ENSMUST00000015901", "ENSMUSP00000015901", "10", "7792951", "7821200" ], [ "B1AQ89-1", "B1AQ89-1", "ENSMUST00000104929", "ENSMUSP00000100533", "11", "99649657", "99650181" ], [ "B1AQ89-1", "E9PUW3-1", "ENSMUST00000073126", "ENSMUSP00000131822", "11", "99649660", "99650181" ], [ "B1AQ87-1", "B1AQ87-1", "ENSMUST00000105073", "ENSMUSP00000100694", "11", "99690591", "99690740" ], [ "B1AQ85-1", "B1AQ85-1", "ENSMUST00000058987", "ENSMUSP00000056162", "11", "99634524", "99635024" ], [ "A0A1B0GST0-1", "A0A1B0GST0-1", "ENSMUST00000213481", "ENSMUSP00000148998", "7", "102856324", "102857280" ], [ "A0A1B0GST0-1", "Q7TRS5-1", "ENSMUST00000071393", "ENSMUSP00000071344", "7", "102856324", "102857271" ], [ "Q3UU21-1", "Q3UU21-1", "ENSMUST00000097849", "ENSMUSP00000095461", "4", "134191093", "134202992" ], [ "P01942-1", "Q91VB8-1", "ENSMUST00000093207", "ENSMUSP00000090895", "11", "32296524", "32297205" ], [ "P03899-1", "P03899-1", "ENSMUST00000082411", "ENSMUSP00000080998", "Mitochondrion", "9459", "9803" ], [ "O35153-1", "A0A1B0GSF3-1", "ENSMUST00000209320", "ENSMUSP00000147913", "7", "140854902", "140856239" ], [ "O35153-1", "A0A1B0GR52-1", "ENSMUST00000211590", "ENSMUSP00000147377", "7", "140854427", "140856239" ], [ "O35153-1", "O35153-1", "ENSMUST00000026557", "ENSMUSP00000026557", "7", "140854459", "140856239" ], [ "O35153-1", "A0A1B0GQV3-1", "ENSMUST00000211624", "ENSMUSP00000147264", "7", "140854459", "140855115" ], [ "O35153-1", "A0A1B0GR53-1", "ENSMUST00000210710", "ENSMUSP00000147378", "7", "140854792", "140856239" ], [ "O35153-1", "A0A1B0GS34-1", "ENSMUST00000211527", "ENSMUSP00000147777", "7", "140854459", "140856239" ], [ "Q9QYH9-1", "Q9QYH9-1", "ENSMUST00000005976", "ENSMUSP00000005976", "17", "57190514", "57194069" ], [ "P52479-1", "P52479-1", "ENSMUST00000108988", "ENSMUSP00000104616", "8", "119910919", "119956767" ], [ "P52479-1", "P52479-2", "ENSMUST00000144458", "ENSMUSP00000123590", "8", "119910919", "119956767" ], [ "P52479-1", "G3X9U6-1", "ENSMUST00000108982", "ENSMUSP00000104610", "8", "119947743", "119951934" ], [ "P52479-1", "G3UYQ8-1", "ENSMUST00000134729", "ENSMUSP00000134182", "8", "119953275", "119956709" ], [ "B1AXU1-1", "B1AXU1-1", "ENSMUST00000074894", "ENSMUSP00000074433", "X", "68892518", "68893007" ], [ "P02762-1", "P02762-1", "ENSMUST00000201756", "ENSMUSP00000143924", "CHR_MG3562_PATCH", "61478892", "61481658" ], [ "Q9QYH6-1", "Q9QYH6-1", "ENSMUST00000026142", "ENSMUSP00000026142", "X", "94535871", "94541295" ], [ "Q3SXJ3-1", "Q3SXJ3-1", "ENSMUST00000213136", "ENSMUSP00000150607", "2", "88909462", "88910391" ], [ "Q08AU9-1", "A0A1B0GR98-1", "ENSMUST00000140447", "ENSMUSP00000147434", "11", "107025894", "107029772" ], [ "Q08AU9-1", "A0A1B0GT03-1", "ENSMUST00000106767", "ENSMUSP00000148142", "11", "107028410", "107029772" ], [ "Q08AU7-1", "Q08AU7-2", "ENSMUST00000026134", "ENSMUSP00000026134", "11", "120646352", "120648007" ], [ "Q5EBH1-1", "D3Z6G2-1", "ENSMUST00000112442", "ENSMUSP00000108061", "1", "131180582", "131245130" ], [ "Q5EBH1-1", "Q5EBH1-1", "ENSMUST00000027688", "ENSMUSP00000027688", "1", "131178528", "131245130" ], [ "Q5EBH1-1", "A0A1D5RM65-1", "ENSMUST00000212202", "ENSMUSP00000148646", "1", "131178528", "131233559" ], [ "Q5EBH1-1", "Q5EBH1-2", "ENSMUST00000068564", "ENSMUSP00000067011", "1", "131178528", "131199972" ], [ "A0A087WSM5-1", "A0A087WSM5-1", "ENSMUST00000185705", "ENSMUSP00000141109", "Y", "7994970", "7995650" ], [ "Q61409-1", "E9QLQ3-1", "ENSMUST00000032909", "ENSMUSP00000032909", "7", "114415551", "114536245" ], [ "A2AVK5-1", "A2AVK5-1", "ENSMUST00000111543", "ENSMUSP00000107168", "2", "89362486", "89363427" ], [ "Q80YU0-1", "Q80YU0-1", "ENSMUST00000069649", "ENSMUSP00000066520", "2", "181493307", "181494728" ], [ "Q61400-1", "A0A0R4J0G1-1", "ENSMUST00000038069", "ENSMUSP00000037036", "7", "24777276", "24784473" ], [ "Q61400-1", "A0A0U1RQ24-1", "ENSMUST00000206847", "ENSMUSP00000146217", "7", "24777276", "24784473" ], [ "Q61400-1", "A0A0U1RQ82-1", "ENSMUST00000206850", "ENSMUSP00000146284", "7", "24777281", "24780920" ], [ "Q61406-1", "A0A0A6YXP6-1", "ENSMUST00000161224", "ENSMUSP00000142078", "1", "139550757", "139553599" ], [ "Q61406-1", "Q61406-1", "ENSMUST00000023965", "ENSMUSP00000023965", "1", "139547703", "139560158" ], [ "Q5SRT8-1", "Q5SRT8-1", "ENSMUST00000050574", "ENSMUSP00000058111", "11", "43529397", "43585712" ], [ "A0A140LIA7-1", "A0A140LIA7-1", "ENSMUST00000207856", "ENSMUSP00000146742", "2", "181657220", "181659462" ], [ "P70419-1", "P70419-1", "ENSMUST00000028378", "ENSMUSP00000028378", "2", "66084173", "66107364" ], [ "Q9EP78-1", "Q9EP78-1", "ENSMUST00000044138", "ENSMUSP00000043222", "X", "20097121", "20097521" ], [ "Q9EP79-1", "A0A2I3BQJ2-1", "ENSMUST00000227578", "ENSMUSP00000154194", "6", "90177899", "90179642" ], [ "Q9EP79-1", "Q9EP79-1", "ENSMUST00000079832", "ENSMUSP00000078760", "6", "90178716", "90179642" ], [ "Q9EP79-1", "A0A2I3BQW2-1", "ENSMUST00000228385", "ENSMUSP00000154336", "6", "90178397", "90179642" ], [ "Q9EP79-1", "A0A2I3BRC4-1", "ENSMUST00000227100", "ENSMUSP00000154539", "6", "90177899", "90179642" ], [ "Q3URK3-1", "G3UXI7-1", "ENSMUST00000173087", "ENSMUSP00000133706", "10", "62813515", "62814539" ], [ "Q3URK3-1", "G3UZ35-1", "ENSMUST00000174121", "ENSMUSP00000134328", "10", "62812622", "62814540" ], [ "Q3URK3-1", "E9Q9Y4-1", "ENSMUST00000174189", "ENSMUSP00000133279", "10", "62812535", "62880014" ], [ "Q3URK3-1", "G3UZN8-1", "ENSMUST00000173905", "ENSMUSP00000134571", "10", "62813705", "62814541" ], [ "Q3URK3-1", "A0A1W2P7E3-1", "ENSMUST00000218782", "ENSMUSP00000151633", "10", "62879874", "62880014" ], [ "Q3URK3-1", "Q3URK3-1", "ENSMUST00000050826", "ENSMUSP00000059527", "10", "62812535", "62880014" ], [ "Q9EP73-1", "Q9EP73-1", "ENSMUST00000016640", "ENSMUSP00000016640", "19", "29372468", "29385409" ] ] }, "readme": "Name\n - Mouse Transcript Locus\n\nVersion\n - 1.0.13\n\nCreated on\n - 2019-03-16T16:06:41.833239\n\nModified on\n - 2019-04-24T11:36:52.305115\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Leyla Garcia [ljgarcia@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - Th Mouse Transcript Locus contains UniProtKB mouse [taxid:10090] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts's start and end position\n - The dataset is derived from 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen\n\nDescription Domain\n Keywords\n - transcript locus\n - peptide id\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.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: uniprot-proteome-10090-mus-musculus-2018-11.nt\n URI: http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt\n Name: mouse_protein_idmapping.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_idmapping.csv\n Output Subdomain\n Name: mouse_protein_transcriptlocus.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_transcriptlocus.csv\n Name: mouse_protein_transcriptlocus.stat.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_transcriptlocus.stat.csv\n\nFields\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: \"22002\"\n Name: \"chromosome_id\"\n Description: \"\"\n Unique Values: \"58\"\n Name: \"peptide_id\"\n Description: \"Protein identifier in Ensembl database\"\n Unique Values: \"55579\"\n Name: \"uniprotkb_isoform_ac\"\n Description: \"\"\n Unique Values: \"55626\"\n Name: \"transcript_id\"\n Description: \"Transcript Identifier in Ensembl database\"\n Unique Values: \"55579\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"39481\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"39598\"", "downloadurl": "/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_transcriptlocus.csv" }