{"id":"https://openalex.org/W4412454122","doi":"https://doi.org/10.1093/bioinformatics/btaf211","title":"<tt>CREMSA</tt>: compressed indexing of (ultra) large multiple sequence alignments","display_name":"<tt>CREMSA</tt>: compressed indexing of (ultra) large multiple sequence alignments","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4412454122","doi":"https://doi.org/10.1093/bioinformatics/btaf211","pmid":"https://pubmed.ncbi.nlm.nih.gov/40662774"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf211","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i246/63745245/btaf211.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i246/63745245/btaf211.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108732186","display_name":"Mika\u00ebl Salson","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mika\u00ebl Salson","raw_affiliation_strings":["Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille,"],"raw_orcid":"https://orcid.org/0000-0003-1166-1720","affiliations":[{"raw_affiliation_string":"Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille,","institution_ids":["https://openalex.org/I7454413","https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114667577","display_name":"Arthur Boddaert","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arthur Boddaert","raw_affiliation_strings":["D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I4210115519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114667578","display_name":"Awa Bousso Gueye","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Awa Bousso Gueye","raw_affiliation_strings":["D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I4210115519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017247640","display_name":"Laurent Bulteau","orcid":"https://orcid.org/0000-0003-1645-9345"},"institutions":[{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Bulteau","raw_affiliation_strings":["CNRS UMR 8049 LIGM, Gustave Eiffel University , F-77420 Marne-la-Vall\u00e9e,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS UMR 8049 LIGM, Gustave Eiffel University , F-77420 Marne-la-Vall\u00e9e,","institution_ids":["https://openalex.org/I4210154111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114667579","display_name":"Yohan Hernandez--Courbevoie","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yohan Hernandez--Courbevoie","raw_affiliation_strings":["D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9partement d\u2019Informatique, Lille University , F-59000 Lille,","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I4210115519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048303382","display_name":"Camille Marchet","orcid":"https://orcid.org/0000-0002-7235-7346"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Camille Marchet","raw_affiliation_strings":["Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille,","institution_ids":["https://openalex.org/I7454413","https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114667580","display_name":"Nan Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nan Pan","raw_affiliation_strings":["CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103135268","display_name":"Sebastian Will","orcid":"https://orcid.org/0000-0002-2376-9205"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sebastian Will","raw_affiliation_strings":["CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,"],"raw_orcid":"https://orcid.org/0000-0002-2376-9205","affiliations":[{"raw_affiliation_string":"CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076325273","display_name":"Yann Ponty","orcid":"https://orcid.org/0000-0002-7615-3930"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yann Ponty","raw_affiliation_strings":["CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,"],"raw_orcid":"https://orcid.org/0000-0002-7615-3930","affiliations":[{"raw_affiliation_string":"CNRS UMR 7161 LIX, Ecole Polytechnique, Institut Polytechnique de Paris , F-91120 Palaiseau,","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13664468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":"Supplement_1","first_page":"i246","last_page":"i254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8130000233650208,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8130000233650208,"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/T11269","display_name":"Algorithms and Data Compression","score":0.13289999961853027,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.022199999541044235,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.7868376970291138},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6242780685424805},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5804373025894165},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5649117827415466},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5628117918968201},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.538870632648468},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4628009498119354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4005265533924103},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17467615008354187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17325365543365479},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10397180914878845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868376970291138},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6242780685424805},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5804373025894165},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5649117827415466},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5628117918968201},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.538870632648468},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4628009498119354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4005265533924103},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17467615008354187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17325365543365479},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10397180914878845},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaf211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf211","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i246/63745245/btaf211.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40662774","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40662774","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:HAL:hal-04910677v2","is_oa":true,"landing_page_url":"https://hal.science/hal-04910677","pdf_url":"https://hal.science/hal-04910677v2/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISMB/ECCB 2025 - 33rd international conference on Intelligent Systems for Molecular Biology, ISCB, Jul 2025, Liverpool, United Kingdom. pp.i246-i254, &#x27E8;10.1093/bioinformatics/btaf211&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:pubmedcentral.nih.gov:12261481","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12261481","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf211","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf211","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i246/63745245/btaf211.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2558356852","display_name":null,"funder_award_id":"ANR-11-INBS-0013","funder_id":"https://openalex.org/F4320316916","funder_display_name":"Institut Fran\u00e7ais de Bioinformatique"},{"id":"https://openalex.org/G5802621812","display_name":null,"funder_award_id":"ANR-11-INBS","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5868464814","display_name":null,"funder_award_id":"ANR-21-ESRE-0048","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6068764742","display_name":null,"funder_award_id":"ANR-11-INBS-0013","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320316916","display_name":"Institut Fran\u00e7ais de Bioinformatique","ror":"https://ror.org/045f7pv37"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412454122.pdf","grobid_xml":"https://content.openalex.org/works/W4412454122.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974033543","https://openalex.org/W2050411378","https://openalex.org/W2088386938","https://openalex.org/W2111272410","https://openalex.org/W2125498037","https://openalex.org/W2134814259","https://openalex.org/W2147477044","https://openalex.org/W2554065905","https://openalex.org/W2883628759","https://openalex.org/W3043124965","https://openalex.org/W3098049011","https://openalex.org/W4289313383","https://openalex.org/W4396561520","https://openalex.org/W4400255619","https://openalex.org/W4409283813"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W1981780420","https://openalex.org/W4206019083","https://openalex.org/W2182707996","https://openalex.org/W2048865712","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2397952901"],"abstract_inverted_index":{"MOTIVATION:":[0],"Recent":[1],"viral":[2,34],"outbreaks":[3],"motivate":[4],"the":[5,19,70,115,127,164,187,190,194,205,235,245],"systematic":[6],"collection":[7],"of":[8,21,31,72,84,122,139,156,166,177,189,196,208],"pathogenic":[9],"genomes":[10,35,143],"in":[11,163,244],"order":[12,78,165],"to":[13,24,66,79,107,125],"accelerate":[14],"their":[15,25,32],"study":[16],"and":[17,28,39,52,198,252],"monitor":[18],"apparition/spread":[20],"variants.":[22],"Due":[23],"limited":[26],"length":[27],"temporal":[29],"proximity":[30],"sequencing,":[33],"are":[36,49],"usually":[37],"organized,":[38],"analyzed":[40],"as":[41],"oversized":[42],"Multiple":[43],"Sequence":[44],"Alignments":[45],"(MSAs).":[46],"Such":[47,169],"MSAs":[48,197],"largely":[50],"ungapped,":[51],"mostly":[53],"homogeneous":[54],"on":[55,103,193,248],"a":[56,62,98,134,154,170,174,200,218],"column-wise":[57],"level":[58,64],"but":[59],"not":[60],"at":[61,217,229,250],"sequential":[63,73],"due":[65],"local":[67],"variations,":[68],"hindering":[69],"performances":[71],"compression":[74,215],"algorithms.":[75],"RESULTS:":[76],"In":[77],"enable":[80],"an":[81,109,119,209],"efficient":[82],"handling":[83],"MSAs,":[85],"including":[86],"subsequent":[87],"statistical":[88],"analyses,":[89],"we":[90],"introduce":[91],"CREMSA":[92,225],"(Column-wise":[93],"Run-length":[94],"Encoding":[95],"for":[96,118,234],"MSAs),":[97],"new":[99],"index":[100],"that":[101],"builds":[102],"sparse":[104],"bitvector":[105],"representations":[106],"compress":[108],"existing":[110],"or":[111],"streamed":[112],"MSA,":[113],"all":[114],"while":[116,159],"allowing":[117],"expressive":[120],"set":[121],"accelerated":[123],"requests":[124,162],"query":[126],"alignment":[128],"without":[129],"prior":[130],"decompression.":[131],"Using":[132],"CREMSA,":[133],"65":[135],"GB":[136],"MSA":[137],"consisting":[138],"1.9M":[140],"SARS-CoV":[141],"2":[142],"could":[144],"be":[145],"compressed":[146],"into":[147],"22":[148],"MB":[149],"using":[150],"less":[151],"than":[152],"half":[153],"gigabyte":[155],"main":[157],"memory,":[158],"executing":[160],"access":[161],"100":[167],"ns.":[168],"speed":[171],"up":[172],"enables":[173],"comprehensive":[175],"analysis":[176],"covariation":[178],"over":[179],"this":[180],"very":[181],"large":[182],"MSA.":[183],"We":[184],"further":[185],"assess":[186],"impact":[188],"sequence":[191],"ordering":[192],"compressibility":[195],"propose":[199],"resorting":[201],"strategy":[202],"that,":[203],"despite":[204],"proven":[206],"NP-hardness":[207],"optimal":[210],"sort,":[211],"induces":[212],"greatly":[213],"increased":[214],"ratios":[216],"marginal":[219],"computational":[220],"cost.":[221],"AVAILABILITY":[222],"AND":[223],"IMPLEMENTATION:":[224],"is":[226,237,247],"freely":[227],"accessible":[228],"https://gitlab.univ-lille.fr/cremsa/cremsa.":[230],"The":[231,241],"Snakemake":[232],"workflow":[233],"benchmarks":[236],"available":[238],"at:":[239],"https://gitlab.univ-lille.fr/cremsa/bench.":[240],"data":[242],"used":[243],"paper":[246],"Zenodo":[249],"https://zenodo.org/records/14698859":[251],"https://zenodo.org/records/15100011.":[253]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-07-16T00:00:00"}
