{"id":"https://openalex.org/W4407269291","doi":"https://doi.org/10.1186/s13015-024-00268-0","title":"Fractional hitting sets for efficient multiset sketching","display_name":"Fractional hitting sets for efficient multiset sketching","publication_year":2025,"publication_date":"2025-02-08","ids":{"openalex":"https://openalex.org/W4407269291","doi":"https://doi.org/10.1186/s13015-024-00268-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/39923117"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-024-00268-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00268-0","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13015-024-00268-0.pdf","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13015-024-00268-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098279417","display_name":"Timoth\u00e9 Rouz\u00e9","orcid":"https://orcid.org/0009-0004-2799-6714"},"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/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I157536573"]},{"id":"https://openalex.org/I182627622","display_name":"Universit\u00e9 Sorbonne Nouvelle","ror":"https://ror.org/03z6jp965","country_code":"FR","type":"education","lineage":["https://openalex.org/I182627622"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"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/I2800921988","display_name":"Institut Pasteur de Lille","ror":"https://ror.org/05k9skc85","country_code":"FR","type":"facility","lineage":["https://openalex.org/I2800921988"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]},{"id":"https://openalex.org/I51101395","display_name":"Universit\u00e9 Paris 1 Panth\u00e9on-Sorbonne","ror":"https://ror.org/002t25c44","country_code":"FR","type":"education","lineage":["https://openalex.org/I51101395"]},{"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":true,"raw_author_name":"Timoth\u00e9 Rouz\u00e9","raw_affiliation_strings":["G5 - SeqBio, Institut pasteur, Universit\u00e9 Paris Cit\u00e9, 75724, Paris, France. trouze@pasteur.fr","Sorbonne Universit\u00e9, Coll\u00e8ge Doctoral, 75005, Paris, France. trouze@pasteur.fr","UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France. trouze@pasteur.fr","G5 - SeqBio, Institut pasteur, Universit\u00e9 Paris Cit\u00e9, 75724, Paris, France","Sorbonne Universit\u00e9, Coll\u00e8ge Doctoral, 75005, Paris, France","UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"G5 - SeqBio, Institut pasteur, Universit\u00e9 Paris Cit\u00e9, 75724, Paris, France. trouze@pasteur.fr","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I204730241"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, Coll\u00e8ge Doctoral, 75005, Paris, France. trouze@pasteur.fr","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I51101395"]},{"raw_affiliation_string":"UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France. trouze@pasteur.fr","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I2800921988","https://openalex.org/I4387153239","https://openalex.org/I7454413"]},{"raw_affiliation_string":"G5 - SeqBio, Institut pasteur, Universit\u00e9 Paris Cit\u00e9, 75724, Paris, France","institution_ids":["https://openalex.org/I204730241"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, Coll\u00e8ge Doctoral, 75005, Paris, France","institution_ids":["https://openalex.org/I182627622","https://openalex.org/I39804081"]},{"raw_affiliation_string":"UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092252951","display_name":"Igor Martayan","orcid":"https://orcid.org/0009-0008-3007-6168"},"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/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/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Igor Martayan","raw_affiliation_strings":["UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]},{"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/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/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/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Camille Marchet","raw_affiliation_strings":["UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001793115","display_name":"Antoine Limasset","orcid":"https://orcid.org/0000-0002-0669-4141"},"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/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/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Limasset","raw_affiliation_strings":["UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR9189 CRIStAL, Univ Lille, CNRS, Centrale, 59000, Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5098279417"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I157536573","https://openalex.org/I182627622","https://openalex.org/I204730241","https://openalex.org/I2279609970","https://openalex.org/I2800921988","https://openalex.org/I39804081","https://openalex.org/I4387153239","https://openalex.org/I51101395","https://openalex.org/I7454413"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":2.6804,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87545385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10888","display_name":"Augmented Reality Applications","score":0.9452000260353088,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multiset","display_name":"Multiset","score":0.8051673173904419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6405269503593445},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38466471433639526},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3766361176967621},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3240644931793213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2210787832736969},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1946074664592743}],"concepts":[{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.8051673173904419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6405269503593445},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38466471433639526},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3766361176967621},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3240644931793213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2210787832736969},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1946074664592743}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13015-024-00268-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00268-0","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13015-024-00268-0.pdf","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:39923117","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39923117","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:HAL:hal-05065061v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05065061","pdf_url":"https://hal.science/hal-05065061v1/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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, 2025, 20 (1), pp.1. ⟨10.1186/s13015-024-00268-0⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11807336","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11807336","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11807336/pdf/13015_2024_Article_268.pdf","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":"Algorithms Mol Biol","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:4dc648b018e94260b2f4d59e5dab1ae0","is_oa":true,"landing_page_url":"https://doaj.org/article/4dc648b018e94260b2f4d59e5dab1ae0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 20, Iss 1, Pp 1-25 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13015-024-00268-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-024-00268-0","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13015-024-00268-0.pdf","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2801727279","display_name":"Adequate graph structures for third-generation sequencing data exploration","funder_award_id":"ANR-21-CE45-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G351600753","display_name":null,"funder_award_id":"IndexThePlanet, 101088572","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G3753762579","display_name":null,"funder_award_id":"101088572","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6326905284","display_name":null,"funder_award_id":"AGATE ANR-21-CE45-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407269291.pdf","grobid_xml":"https://content.openalex.org/works/W4407269291.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2111295912","https://openalex.org/W2111307596","https://openalex.org/W2144560237","https://openalex.org/W2339602899","https://openalex.org/W2763390627","https://openalex.org/W2884834061","https://openalex.org/W2950150251","https://openalex.org/W2955167895","https://openalex.org/W2992400060","https://openalex.org/W3011980846","https://openalex.org/W3018162653","https://openalex.org/W3043768949","https://openalex.org/W3085875665","https://openalex.org/W3137871957","https://openalex.org/W3142668023","https://openalex.org/W3147478436","https://openalex.org/W3150463527","https://openalex.org/W3212599762","https://openalex.org/W3212612274","https://openalex.org/W4206102744","https://openalex.org/W4212888206","https://openalex.org/W4225502295","https://openalex.org/W4306939319","https://openalex.org/W4323366466","https://openalex.org/W4382631906","https://openalex.org/W4383313785","https://openalex.org/W4385708519","https://openalex.org/W6750315529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4300455649","https://openalex.org/W2296588302","https://openalex.org/W4328119206","https://openalex.org/W2033245919","https://openalex.org/W4252409532","https://openalex.org/W2006067547","https://openalex.org/W9228044"],"abstract_inverted_index":{"The":[0,217],"exponential":[1],"increase":[2],"in":[3,193,225],"publicly":[4],"available":[5,229],"sequencing":[6],"data":[7,19,218],"and":[8,21,44,110,151,179,181,210],"genomic":[9,203],"resources":[10],"necessitates":[11],"the":[12,87,105,114,128,188,195,199,222],"development":[13],"of":[14,89,95,104,116,175,190,202],"highly":[15,123],"efficient":[16,124],"methods":[17],"for":[18],"processing":[20],"analysis.":[22],"Locality-sensitive":[23],"hashing":[24],"techniques":[25],"have":[26],"successfully":[27],"transformed":[28],"large":[29],"datasets":[30],"into":[31],"smaller,":[32],"more":[33],"manageable":[34],"sketches":[35,49,78],"while":[36,82,171],"maintaining":[37],"comparability":[38],"using":[39],"metrics":[40],"such":[41,60,118],"as":[42,61,131],"Jaccard":[43],"containment":[45],"indices.":[46],"However,":[47],"fixed-size":[48],"encounter":[50],"difficulties":[51],"when":[52],"applied":[53],"to":[54,75,165,220],"divergent":[55],"datasets.":[56],"Scalable":[57],"sketching":[58],"methods,":[59],"sourmash,":[62,166],"provide":[63,134],"valuable":[64],"solutions":[65],"but":[66,122],"still":[67],"lack":[68],"resource-efficient,":[69],"tailored":[70],"indexing.":[71],"Our":[72,144],"objective":[73],"is":[74,206,228],"create":[76],"lighter":[77],"with":[79,120,154],"comparable":[80],"results":[81,153,223],"enhancing":[83],"efficiency.":[84],"We":[85],"introduce":[86],"concept":[88],"Fractional":[90],"Hitting":[91,97],"Sets,":[92,98],"a":[93,101,135],"generalization":[94],"Universal":[96],"which":[99],"cover":[100],"specified":[102],"fraction":[103],"k-mer":[106],"space.":[107],"In":[108,163],"theory":[109],"practice,":[111],"we":[112,133],"demonstrate":[113],"feasibility":[115],"achieving":[117],"coverage":[119],"simple":[121],"schemes.":[125],"By":[126],"encoding":[127],"covered":[129],"k-mers":[130],"super-k-mers,":[132],"space-efficient":[136],"exact":[137],"representation":[138],"that":[139],"also":[140],"enables":[141],"optimized":[142],"comparisons.":[143],"novel":[145],"tool,":[146],"supersampler,":[147],"implements":[148],"this":[149,226],"scheme,":[150],"experimental":[152],"real":[155],"bacterial":[156],"collections":[157],"closely":[158],"match":[159],"our":[160,191],"theoretical":[161],"findings.":[162],"comparison":[164],"supersampler":[167,205],"achieves":[168],"similar":[169],"outcomes":[170],"utilizing":[172],"an":[173,207],"order":[174],"magnitude":[176],"less":[177],"space":[178],"memory":[180],"operating":[182],"several":[183],"times":[184],"faster.":[185],"This":[186],"highlights":[187],"potential":[189],"approach":[192],"addressing":[194],"challenges":[196],"presented":[197,224],"by":[198],"ever-expanding":[200],"landscape":[201],"data.":[204],"open-source":[208],"software":[209],"can":[211],"be":[212],"accessed":[213],"at":[214,230],"https://github.com/TimRouze/supersampler":[215],".":[216,232],"required":[219],"reproduce":[221],"manuscript":[227],"https://github.com/TimRouze/supersampler/experiments":[231]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}