{"id":"https://openalex.org/W4323366486","doi":"https://doi.org/10.1093/bioinformatics/btad225","title":"Scalable sequence database search using partitioned aggregated Bloom comb trees","display_name":"Scalable sequence database search using partitioned aggregated Bloom comb trees","publication_year":2023,"publication_date":"2023-05-25","ids":{"openalex":"https://openalex.org/W4323366486","doi":"https://doi.org/10.1093/bioinformatics/btad225","pmid":"https://pubmed.ncbi.nlm.nih.gov/37387170"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad225","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad225","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i252/50741675/btad225.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/39/Supplement_1/i252/50741675/btad225.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]},{"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":"Camille Marchet","raw_affiliation_strings":["University of Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}]},{"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/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"]},{"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/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":"Antoine Limasset","raw_affiliation_strings":["University of Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille, France","Centre National de la Recherche Scientifique","Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL , F-59000 Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]},{"raw_affiliation_string":"Centre National de la Recherche Scientifique","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189","institution_ids":["https://openalex.org/I4210115519","https://openalex.org/I4387153239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001793115","https://openalex.org/A5048303382"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4210115519","https://openalex.org/I4387153239","https://openalex.org/I7454413"],"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":0.0180421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"Supplement_1","first_page":"i252","last_page":"i259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8289999961853027,"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":0.8289999961853027,"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":0.05640000104904175,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676604390144348},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7625942230224609},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.6459700465202332},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5131619572639465},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44905853271484375},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3034789562225342},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18872913718223572},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12076687812805176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676604390144348},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7625942230224609},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.6459700465202332},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5131619572639465},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44905853271484375},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3034789562225342},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18872913718223572},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12076687812805176},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005057","descriptor_name":"Eukaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005057","descriptor_name":"Eukaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005057","descriptor_name":"Eukaryotic Cells","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":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":10,"locations":[{"id":"doi:10.1093/bioinformatics/btad225","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad225","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i252/50741675/btad225.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:37387170","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37387170","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-04279824v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04279824","pdf_url":"https://hal.science/hal-04279824/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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2023, 39 (Supplement_1), pp.i252-i259. ⟨10.1093/bioinformatics/btad225⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10311332","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10311332","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10311332/pdf/btad225.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":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:HAL:hal-03832918v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03832918","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Recomb 2022- 26th Annual International Conference on Research in Computational Molecular Biology, May 2022, La jolla, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-04288481v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04288481","pdf_url":null,"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":"ISSN: 1367-4803","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/77831","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/77831","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/80069","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/80069","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/workingPaper"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/89556","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/89556","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/review"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/90840","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/90840","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/review"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad225","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad225","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i252/50741675/btad225.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/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/G7303289904","display_name":"Unbiased massive RNA data-mining for medical applications","funder_award_id":"ANR-22-CE45-0007","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4323366486.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2027667941","https://openalex.org/W2055043387","https://openalex.org/W2096128575","https://openalex.org/W2103441770","https://openalex.org/W2122316710","https://openalex.org/W2123845384","https://openalex.org/W2142678478","https://openalex.org/W2144560237","https://openalex.org/W2170727800","https://openalex.org/W2266239166","https://openalex.org/W2278452282","https://openalex.org/W2438121987","https://openalex.org/W2529838505","https://openalex.org/W2566346075","https://openalex.org/W2570372911","https://openalex.org/W2759261668","https://openalex.org/W2788348538","https://openalex.org/W2884435343","https://openalex.org/W2907484836","https://openalex.org/W2913847081","https://openalex.org/W2952379095","https://openalex.org/W2957382730","https://openalex.org/W2969627863","https://openalex.org/W3029205155","https://openalex.org/W3085875665","https://openalex.org/W3113074526","https://openalex.org/W3142668023","https://openalex.org/W3212599762","https://openalex.org/W4225502295","https://openalex.org/W4226101760"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W121740227","https://openalex.org/W2135966669","https://openalex.org/W2732769800","https://openalex.org/W3082379938","https://openalex.org/W2594143027","https://openalex.org/W2924589531","https://openalex.org/W315172248"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,209],"Sequence":[2],"Read":[3],"Archive":[4],"public":[5,40],"database":[6],"has":[7],"reached":[8],"45":[9],"petabytes":[10],"of":[11,35,47,58,117,206],"raw":[12],"sequences":[13,238],"and":[14,162],"doubles":[15],"its":[16],"nucleotide":[17],"content":[18],"every":[19],"2":[20],"years.":[21],"Although":[22],"BLAST-like":[23],"methods":[24,74,149],"can":[25,157],"routinely":[26],"search":[27],"for":[28,114,150,178,202],"a":[29,32,60,107,125,138,199],"sequence":[30,61,64,118,217],"in":[31,62,124,142,165,168,189,198,239],"small":[33,87],"collection":[34,197,218],"genomes,":[36],"making":[37],"searchable":[38],"immense":[39],"resources":[41],"accessible":[42],"is":[43,250],"beyond":[44],"the":[45,56,71,83,133,192,215],"reach":[46],"alignment-based":[48],"strategies.":[49,68],"In":[50],"recent":[51],"years,":[52],"abundant":[53],"literature":[54],"tackled":[55],"task":[57],"finding":[59],"extensive":[63],"collections":[65,95,116],"using":[66,221],"k-mer-based":[67],"At":[69],"present,":[70],"most":[72],"scalable":[73,93],"are":[75],"approximate":[76,109,223],"membership":[77,110,224],"query":[78,86,111,156,225,234],"data":[79,112],"structures":[80],"that":[81,230],"combine":[82],"ability":[84,232],"to":[85,94,97,146,212,233],"signatures":[88],"or":[89],"variants":[90],"while":[91],"being":[92],"up":[96],"10":[98],"000":[99,185,236],"eukaryotic":[100],"samples.":[101],"Results.":[102],"Here,":[103],"we":[104,175],"present":[105],"PAC,":[106],"novel":[108],"structure":[113],"querying":[115],"datasets.":[119],"PAC":[120,155,177],"index":[121,134,152,204],"construction":[122,143],"works":[123],"streaming":[126],"fashion":[127],"without":[128],"any":[129],"disk":[130],"footprint":[131],"besides":[132],"itself.":[135],"It":[136],"shows":[137],"3-6":[139],"fold":[140],"improvement":[141],"time":[144,167],"compared":[145],"other":[147],"compressed":[148],"comparable":[151],"size.":[153],"A":[154],"need":[158],"single":[159,200],"random":[160],"access":[161],"be":[163],"performed":[164],"constant":[166],"favorable":[169],"instances.":[170],"Using":[171],"limited":[172],"computation":[173],"resources,":[174],"built":[176],"very":[179],"large":[180],"collections.":[181],"They":[182],"include":[183],"32":[184],"human":[186],"RNA-seq":[187],"samples":[188],"5":[190],"days,":[191],"entire":[193],"GenBank":[194],"bacterial":[195],"genome":[196],"day":[201],"an":[203,222,242],"size":[205],"3.5":[207],"TB.":[208],"latter":[210],"is,":[211],"our":[213],"knowledge,":[214],"largest":[216],"ever":[219],"indexed":[220],"structure.":[226],"We":[227],"also":[228],"showed":[229],"PAC's":[231,247],"500":[235],"transcript":[237],"less":[240],"than":[241],"hour.":[243],"AVAILABILITY":[244],"AND":[245],"IMPLEMENTATION:":[246],"open-source":[248],"software":[249],"available":[251],"at":[252],"https://github.com/Malfoy/PAC.":[253]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}