{"id":"https://openalex.org/W4226101760","doi":"https://doi.org/10.1093/bioadv/vbac029","title":"kmtricks: efficient and flexible construction of Bloom filters for large sequencing data collections","display_name":"kmtricks: efficient and flexible construction of Bloom filters for large sequencing data collections","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226101760","doi":"https://doi.org/10.1093/bioadv/vbac029","pmid":"https://pubmed.ncbi.nlm.nih.gov/36699393","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9710589"},"language":"en","primary_location":{"id":"doi:10.1093/bioadv/vbac029","doi":"https://doi.org/10.1093/bioadv/vbac029","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbac029","pdf_url":"https://academic.oup.com/bioinformaticsadvances/article-pdf/2/1/vbac029/47086128/vbac029.pdf","source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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 Advances","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformaticsadvances/article-pdf/2/1/vbac029/47086128/vbac029.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078221150","display_name":"T\u00e9o Lemane","orcid":"https://orcid.org/0000-0002-7210-3178","observed_orcids":["https://orcid.org/0000-0002-7210-3178"]},"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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"T\u00e9o Lemane","raw_affiliation_strings":["Univ. Rennes, Inria, CNRS, IRISA , Rennes F-35000, France"],"raw_orcid":"https://orcid.org/0000-0002-7210-3178","affiliations":[{"raw_affiliation_string":"Univ. Rennes, Inria, CNRS, IRISA , Rennes F-35000, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X","observed_orcids":["https://orcid.org/0000-0003-3143-594X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University , University Park, PA 16801, USA","Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA 16801, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA 16801, USA"],"raw_orcid":"https://orcid.org/0000-0003-3143-594X","affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , University Park, PA 16801, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA 16801, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA 16801, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058310668","display_name":"Rayan Chikhi","orcid":"https://orcid.org/0000-0003-1099-8735","observed_orcids":["https://orcid.org/0000-0003-1099-8735"]},"institutions":[{"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/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rayan Chikhi","raw_affiliation_strings":["Sequence Bioinformatics, Institut Pasteur, Universit\u00e9 Paris Cit\u00e9 , Paris F-75015, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequence Bioinformatics, Institut Pasteur, Universit\u00e9 Paris Cit\u00e9 , Paris F-75015, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012897398","display_name":"Pierre Peterlongo","orcid":"https://orcid.org/0000-0003-0776-6407","observed_orcids":["https://orcid.org/0000-0003-0776-6407"]},"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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Pierre Peterlongo","raw_affiliation_strings":["Univ. Rennes, Inria, CNRS, IRISA , Rennes F-35000, France"],"raw_orcid":"https://orcid.org/0000-0003-0776-6407","affiliations":[{"raw_affiliation_string":"Univ. Rennes, Inria, CNRS, IRISA , Rennes F-35000, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5012897398"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937","https://openalex.org/I56067802"],"apc_list":{"value":2472,"currency":"USD","value_usd":2472},"apc_paid":{"value":2162,"currency":"EUR","value_usd":2331},"fwci":6.9913,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97654784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"vbac029","last_page":"vbac029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6685000061988831,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6685000061988831,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.32280001044273376,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0013000000035390258,"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/bloom-filter","display_name":"Bloom filter","score":0.9340000152587891},{"id":"https://openalex.org/keywords/k-mer-counting","display_name":"k-mer counting","score":0.8149999976158142},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.7319999933242798},{"id":"https://openalex.org/keywords/k-mers","display_name":"k-mers","score":0.5289999842643738},{"id":"https://openalex.org/keywords/data-indexing","display_name":"data indexing","score":0.30799999833106995}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9861820936203003},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7235357761383057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.716354250907898},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.6420558094978333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5617076754570007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48324641585350037},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.48108574748039246},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4305555522441864},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4211823344230652},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33637070655822754},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3343455493450165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32680290937423706},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24043726921081543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20833396911621094},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08845311403274536},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1093/bioadv/vbac029","doi":"https://doi.org/10.1093/bioadv/vbac029","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbac029","pdf_url":"https://academic.oup.com/bioinformaticsadvances/article-pdf/2/1/vbac029/47086128/vbac029.pdf","source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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 Advances","raw_type":"journal-article"},{"id":"doi:10.1101/2021.02.16.429304","doi":"https://doi.org/10.1101/2021.02.16.429304","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2021.02.16.429304","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2021/02/17/2021.02.16.429304.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:9710589","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9710589","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinform Adv","raw_type":"Text"},{"id":"pmid:36699393","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36699393","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,"listed_in":[],"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 advances","raw_type":"Journal Article"},{"id":"pmh:oai:HAL:hal-03166007v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03166007v1/document","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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 Advances, 2022, ⟨10.1093/bioadv/vbac029⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioadv/vbac029","doi":"https://doi.org/10.1093/bioadv/vbac029","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbac029","pdf_url":"https://academic.oup.com/bioinformaticsadvances/article-pdf/2/1/vbac029/47086128/vbac029.pdf","source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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 Advances","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3010527862","display_name":null,"funder_award_id":"ANR\u201019","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5196283127","display_name":"Institut Convergences pour l\u2019\u00e9tude de l\u2019Emergence des Pathologies au Travers des Individus et des populatiONs","funder_award_id":"ANR-16-CONV-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5280846027","display_name":"Search engine for environmental genomic sequencing data","funder_award_id":"ANR-19-CE45-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5420063140","display_name":null,"funder_award_id":"ANR-16","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226101760.pdf","grobid_xml":"https://content.openalex.org/works/W4226101760.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1962019683","https://openalex.org/W2025943989","https://openalex.org/W2045204781","https://openalex.org/W2055043387","https://openalex.org/W2057253402","https://openalex.org/W2057970678","https://openalex.org/W2080234606","https://openalex.org/W2096128575","https://openalex.org/W2099085143","https://openalex.org/W2104052851","https://openalex.org/W2111307596","https://openalex.org/W2123845384","https://openalex.org/W2125266506","https://openalex.org/W2129949113","https://openalex.org/W2266239166","https://openalex.org/W2339602899","https://openalex.org/W2531153203","https://openalex.org/W2570372911","https://openalex.org/W2583363792","https://openalex.org/W2599417231","https://openalex.org/W2788348538","https://openalex.org/W2799324424","https://openalex.org/W2809649683","https://openalex.org/W2897927784","https://openalex.org/W2913847081","https://openalex.org/W2945318807","https://openalex.org/W2949074212","https://openalex.org/W2949565680","https://openalex.org/W2952158800","https://openalex.org/W2957382730","https://openalex.org/W2969627863","https://openalex.org/W3043153155","https://openalex.org/W3090493712","https://openalex.org/W3113074526","https://openalex.org/W3148807116","https://openalex.org/W4321748347"],"related_works":["https://openalex.org/W2163584430","https://openalex.org/W2417068752","https://openalex.org/W4376871908","https://openalex.org/W4383893239","https://openalex.org/W7155986522","https://openalex.org/W2949074212","https://openalex.org/W2943222183","https://openalex.org/W4411476414","https://openalex.org/W2937172564","https://openalex.org/W4310752881"],"abstract_inverted_index":{"Abstract":[0],"Summary":[1],"When":[2],"indexing":[3],"large":[4,192],"collections":[5,102],"of":[6,32,47,54,72,103,135,153,167,187],"short-read":[7],"sequencing":[8,104],"data,":[9],"a":[10,30,45,93,122,147,191],"common":[11],"operation":[12],"that":[13,150,173],"has":[14],"now":[15],"been":[16],"implemented":[17],"in":[18,60,69,161,190],"several":[19,162],"tools":[20],"(Sequence":[21],"Bloom":[22,33,39,98,124],"Trees":[23],"and":[24,82,131,196],"variants,":[25],"BIGSI)":[26],"is":[27,41,66,138],"to":[28,43,156],"construct":[29],"collection":[31],"filters,":[34],"one":[35],"per":[36],"sample.":[37,62],"Each":[38],"filter":[40,125],"used":[42],"represent":[44],"set":[46,53],"k-mers":[48,58,78,117,159,180,189],"which":[49,137],"approximates":[50],"the":[51,56,61,70,165,182],"desired":[52],"all":[55],"non-erroneous":[57,83,168],"present":[59,160],"However,":[63],"this":[64,174],"approximation":[65],"imperfect,":[67],"especially":[68],"case":[71],"metagenomics":[73,193],"data.":[74,105],"Erroneous":[75],"but":[76,84],"abundant":[77],"are":[79,87,109,203],"wrongly":[80,88],"included,":[81],"low-abundant":[85,158],"ones":[86],"discarded.":[89],"We":[90],"propose":[91],"kmtricks,":[92],"novel":[94,148],"approach":[95],"for":[96,114],"generating":[97],"filters":[99],"from":[100],"terabase-sized":[101],"Our":[106,170],"main":[107],"contributions":[108],"(i)":[110],"an":[111],"efficient":[112],"method":[113],"jointly":[115],"counting":[116,155],"across":[118],"multiple":[119],"samples,":[120,163],"including":[121],"streamlined":[123],"construction":[126],"by":[127],"directly":[128],"counting,":[129],"partitioning":[130],"sorting":[132],"hashes":[133],"instead":[134],"k-mers,":[136],"approximately":[139],"four":[140],"times":[141],"faster":[142],"than":[143,181],"state-of-the-art":[144],"tools;":[145],"(ii)":[146],"technique":[149,175],"takes":[151],"advantage":[152],"joint":[154],"preserve":[157],"improving":[164],"recovery":[166],"k-mers.":[169],"experiments":[171],"highlight":[172],"preserves":[176],"around":[177],"8\u00d7":[178],"more":[179],"usual":[183],"yet":[184],"crude":[185],"filtering":[186],"low-abundance":[188],"dataset.":[194],"Availability":[195],"implementation":[197],"https://github.com/tlemane/kmtricks.":[198],"Supplementary":[199,201],"information":[200],"data":[202],"available":[204],"at":[205],"Bioinformatics":[206],"Advances":[207],"online.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-05-05T00:00:00"}