{"id":"https://openalex.org/W2306375491","doi":"https://doi.org/10.1051/ro/2015039","title":"High-order statistical compressor for long-term storage of DNA sequencing data","display_name":"High-order statistical compressor for long-term storage of DNA sequencing data","publication_year":2015,"publication_date":"2015-10-02","ids":{"openalex":"https://openalex.org/W2306375491","doi":"https://doi.org/10.1051/ro/2015039","mag":"2306375491"},"language":"en","primary_location":{"id":"doi:10.1051/ro/2015039","is_oa":false,"landing_page_url":"https://doi.org/10.1051/ro/2015039","pdf_url":null,"source":{"id":"https://openalex.org/S20631277","display_name":"RAIRO - Operations Research","issn_l":"0399-0559","issn":["0399-0559","1290-3868","2804-7303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319748","host_organization_name":"EDP Sciences","host_organization_lineage":["https://openalex.org/P4310319748","https://openalex.org/P4310319982"],"host_organization_lineage_names":["EDP Sciences","Science Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RAIRO - Operations Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.numdam.org/item/10.1051/ro/2015039.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014643005","display_name":"Marek Ch\u0142opkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marek Chlopkowski","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045163807","display_name":"Maciej Antczak","orcid":"https://orcid.org/0000-0002-5320-2023"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Maciej Antczak","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075412363","display_name":"Michal Slusarczyk","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Michal Slusarczyk","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031697909","display_name":"Aleksander Wdowinski","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Aleksander Wdowinski","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001542943","display_name":"Micha\u0142 Zaj\u0105czkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Michal Zajaczkowski","raw_affiliation_strings":["Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036768913","display_name":"Marta Kasprzak","orcid":"https://orcid.org/0000-0002-9863-5412"},"institutions":[{"id":"https://openalex.org/I4210152414","display_name":"Institute of Bioorganic Chemistry, Polish Academy of Sciences","ror":"https://ror.org/04ejdtr48","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210152414","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marta Kasprzak","raw_affiliation_strings":["Institute of Bioorganic Chemistry, Polish Academy of Sciences, Poznan, Poland","Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Bioorganic Chemistry, Polish Academy of Sciences, Poznan, Poland","institution_ids":["https://openalex.org/I4210152414"]},{"raw_affiliation_string":"Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":0,"currency":"EUR","value_usd":0},"apc_paid":null,"fwci":1.0357,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87262059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"50","issue":"2","first_page":"351","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744842529296875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5469858050346375},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5321416258811951},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5017147064208984},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.487093448638916},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4466424882411957},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44494229555130005},{"id":"https://openalex.org/keywords/gas-compressor","display_name":"Gas compressor","score":0.4217190444469452},{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.4176984429359436},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.41080036759376526},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.4107893109321594},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3487577736377716},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3031184673309326},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2833542227745056},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.2546790838241577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21448326110839844},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17671099305152893},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1626964807510376},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13550949096679688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11921119689941406},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11566007137298584},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1061866283416748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09047135710716248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744842529296875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5469858050346375},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5321416258811951},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5017147064208984},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.487093448638916},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4466424882411957},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44494229555130005},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.4217190444469452},{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.4176984429359436},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.41080036759376526},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.4107893109321594},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3487577736377716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3031184673309326},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2833542227745056},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2546790838241577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21448326110839844},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17671099305152893},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1626964807510376},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13550949096679688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11921119689941406},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11566007137298584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1061866283416748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09047135710716248},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1051/ro/2015039","is_oa":false,"landing_page_url":"https://doi.org/10.1051/ro/2015039","pdf_url":null,"source":{"id":"https://openalex.org/S20631277","display_name":"RAIRO - Operations Research","issn_l":"0399-0559","issn":["0399-0559","1290-3868","2804-7303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319748","host_organization_name":"EDP Sciences","host_organization_lineage":["https://openalex.org/P4310319748","https://openalex.org/P4310319982"],"host_organization_lineage_names":["EDP Sciences","Science Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RAIRO - Operations Research","raw_type":"journal-article"},{"id":"pmh:oai:numdam.org:RO_2016__50_2_351_0","is_oa":true,"landing_page_url":"http://www.numdam.org/articles/10.1051/ro/2015039/","pdf_url":"https://www.numdam.org/item/10.1051/ro/2015039.pdf","source":{"id":"https://openalex.org/S4306402264","display_name":"French digital mathematics library (Numdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I70900168","host_organization_name":"Universit\u00e9 Savoie Mont Blanc","host_organization_lineage":["https://openalex.org/I70900168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:numdam.org:RO_2016__50_2_351_0","is_oa":true,"landing_page_url":"http://www.numdam.org/articles/10.1051/ro/2015039/","pdf_url":"https://www.numdam.org/item/10.1051/ro/2015039.pdf","source":{"id":"https://openalex.org/S4306402264","display_name":"French digital mathematics library (Numdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I70900168","host_organization_name":"Universit\u00e9 Savoie Mont Blanc","host_organization_lineage":["https://openalex.org/I70900168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322481","display_name":"Politechnika Pozna\u0144ska","ror":"https://ror.org/00p7p3302"},{"id":"https://openalex.org/F4320322650","display_name":"Narodowym Centrum Nauki","ror":"https://ror.org/03ha2q922"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2306375491.pdf","grobid_xml":"https://content.openalex.org/works/W2306375491.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1976826191","https://openalex.org/W1990653637","https://openalex.org/W1995875735","https://openalex.org/W2051929999","https://openalex.org/W2060108852","https://openalex.org/W2061343917","https://openalex.org/W2107745473","https://openalex.org/W2111044311","https://openalex.org/W2114792961","https://openalex.org/W2117608012","https://openalex.org/W2122962290","https://openalex.org/W2129652681","https://openalex.org/W2138196010","https://openalex.org/W2146235863","https://openalex.org/W2158521043","https://openalex.org/W2166022874","https://openalex.org/W2166588423","https://openalex.org/W2167943254","https://openalex.org/W2171777347","https://openalex.org/W2885727518"],"related_works":["https://openalex.org/W1538652242","https://openalex.org/W2011521129","https://openalex.org/W2461968736","https://openalex.org/W4379164835","https://openalex.org/W4386544342","https://openalex.org/W2270443735","https://openalex.org/W1996282642","https://openalex.org/W2912106387","https://openalex.org/W2145275182","https://openalex.org/W2912031806"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,69],"specialized":[3],"compressor":[4,49],"designed":[5],"for":[6,24,31,35,54],"efficient":[7],"data":[8,43],"storage":[9,33],"of":[10,42,73,84],"FASTQ":[11],"files":[12],"produced":[13],"by":[14],"high-throughput":[15],"DNA":[16,74],"sequencers.":[17],"Since":[18],"the":[19,62,82,85,95],"method":[20],"has":[21],"been":[22],"optimized":[23],"compression":[25],"quality,":[26],"it":[27],"is":[28,65,76],"especially":[29],"suitable":[30],"long-term":[32],"and":[34],"genome":[36],"research":[37],"centers":[38],"processing":[39],"huge":[40],"amount":[41],"(counted":[44],"in":[45,67],"petabytes).":[46],"The":[47],"proposed":[48],"uses":[50],"high-order":[51],"statistical":[52],"models":[53],"range":[55],"encoding,":[56],"similar":[57],"to":[58,79],"Markov":[59],"models,":[60],"but":[61],"whole":[63],"input":[64],"considered":[66],"building":[68],"symbol":[70],"context.":[71],"Compression":[72],"reads":[75],"performed":[77],"according":[78],"LZ-style":[80],"with":[81,94],"use":[83],"5\u20137th":[86],"order":[87,97],"model,":[88],"while":[89],"nucleotides\u2019":[90],"scores":[91],"are":[92],"encoded":[93],"3rd":[96],"model.":[98]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}
