{"id":"https://openalex.org/W4386022705","doi":"https://doi.org/10.1093/bioinformatics/btad512","title":"Minmers are a generalization of minimizers that enable unbiased local Jaccard estimation","display_name":"Minmers are a generalization of minimizers that enable unbiased local Jaccard estimation","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4386022705","doi":"https://doi.org/10.1093/bioinformatics/btad512","pmid":"https://pubmed.ncbi.nlm.nih.gov/37603771"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad512","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad512","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad512/51201597/btad512.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/advance-article-pdf/doi/10.1093/bioinformatics/btad512/51201597/btad512.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072499401","display_name":"Bryce Kille","orcid":"https://orcid.org/0000-0003-2946-6915"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bryce Kille","raw_affiliation_strings":["Department of Computer Science, Rice University , Houston, TX, United States"],"raw_orcid":"https://orcid.org/0000-0003-2946-6915","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University , Houston, TX, United States","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008992371","display_name":"Erik Garrison","orcid":"https://orcid.org/0000-0003-3821-631X"},"institutions":[{"id":"https://openalex.org/I160606119","display_name":"University of Tennessee Health Science Center","ror":"https://ror.org/0011qv509","country_code":"US","type":"education","lineage":["https://openalex.org/I160606119"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Garrison","raw_affiliation_strings":["Department of Genetics, Genomics and Informatics, University of Tennessee Health Science Center , Memphis, TN, United States"],"raw_orcid":"https://orcid.org/0000-0003-3821-631X","affiliations":[{"raw_affiliation_string":"Department of Genetics, Genomics and Informatics, University of Tennessee Health Science Center , Memphis, TN, United States","institution_ids":["https://openalex.org/I160606119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054369332","display_name":"Todd J. Treangen","orcid":"https://orcid.org/0000-0002-3760-564X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd J Treangen","raw_affiliation_strings":["Department of Computer Science, Rice University , Houston, TX, United States"],"raw_orcid":"https://orcid.org/0000-0002-3760-564X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rice University , Houston, TX, United States","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086869042","display_name":"Adam M. Phillippy","orcid":"https://orcid.org/0000-0003-2983-8934"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090236","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090236"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adam M Phillippy","raw_affiliation_strings":["Genome Informatics Section, Computational and Statistical Genomics Branch, National Human Genome Research Institute, National Institutes of Health , Bethesda, MD, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Informatics Section, Computational and Statistical Genomics Branch, National Human Genome Research Institute, National Institutes of Health , Bethesda, MD, United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072499401","https://openalex.org/A5086869042"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090236","https://openalex.org/I74775410"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":8.8261,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98363908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"39","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.5493000149726868,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.5493000149726868,"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"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.08510000258684158,"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"}},{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.08479999750852585,"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/jaccard-index","display_name":"Jaccard index","score":0.9341890811920166},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8383994698524475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5981771945953369},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5035893321037292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3437316417694092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28066760301589966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2561579942703247},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08059269189834595}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9341890811920166},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8383994698524475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5981771945953369},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5035893321037292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3437316417694092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28066760301589966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2561579942703247},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08059269189834595},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad512","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad512","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad512/51201597/btad512.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:37603771","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37603771","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10505501","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10505501","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10505501/pdf/btad512.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"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad512","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad512","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad512/51201597/btad512.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/G143167659","display_name":null,"funder_award_id":"P01\u2010AI152999","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G1538685144","display_name":null,"funder_award_id":"NIDA U01DA047638","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"},{"id":"https://openalex.org/G2239731442","display_name":"MIM: Elucidating the Rules of Cooperation and Resiliency in Microbial Communities through Stochastic Graph Grammars","funder_award_id":"2126387","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2328657408","display_name":null,"funder_award_id":"AI152999","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G2640905883","display_name":null,"funder_award_id":"T15LM007093","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G2996460108","display_name":"Project 3: Functional Microbiome and Host Signatures in Transition from Commensal to pathogen","funder_award_id":"5p01ai152999-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3263214147","display_name":null,"funder_award_id":"U01DA047638","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"},{"id":"https://openalex.org/G3511783147","display_name":"NLM Research Training Program in Biomedical Informatics and Data Science for Predoctoral and Postdoctoral Fellows","funder_award_id":"5t15lm007093-32","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3681866668","display_name":null,"funder_award_id":"R01 GM123489","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G373495704","display_name":"System genetics of menthol and nicotine addiction","funder_award_id":"5u01da047638-05","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7564846446","display_name":"Collaborative Research: PPoSS: LARGE: Panorama: Integrated Rack-Scale Acceleration for Computational Pangenomics","funder_award_id":"2118709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386022705.pdf","grobid_xml":"https://content.openalex.org/works/W4386022705.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1579534339","https://openalex.org/W2141978199","https://openalex.org/W2144560237","https://openalex.org/W2519890620","https://openalex.org/W2615471603","https://openalex.org/W2789843538","https://openalex.org/W2807521829","https://openalex.org/W2892689606","https://openalex.org/W2950150251","https://openalex.org/W2950572599","https://openalex.org/W2951254987","https://openalex.org/W2951822379","https://openalex.org/W2952609831","https://openalex.org/W2958388979","https://openalex.org/W2987650093","https://openalex.org/W2992400060","https://openalex.org/W3016701095","https://openalex.org/W3043768949","https://openalex.org/W3086678357","https://openalex.org/W3112069035","https://openalex.org/W3128964673","https://openalex.org/W3206657624","https://openalex.org/W4220999759","https://openalex.org/W4221104280","https://openalex.org/W4224278121","https://openalex.org/W4225293672","https://openalex.org/W4226289813","https://openalex.org/W4243450674","https://openalex.org/W4294670644","https://openalex.org/W4317625860","https://openalex.org/W4382680160","https://openalex.org/W4386113054","https://openalex.org/W4386923678"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W2913569734","https://openalex.org/W4401519790","https://openalex.org/W2702570413"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,135],"Jaccard":[2,66,122],"similarity":[3,43],"on":[4,50,75],"k-mer":[5],"sets":[6],"has":[7],"shown":[8,58],"to":[9,33,47,59],"be":[10,60],"a":[11,99],"convenient":[12],"proxy":[13],"for":[14,155],"sequence":[15,25],"identity.":[16],"By":[17],"avoiding":[18],"expensive":[19],"base-level":[20],"alignments":[21],"and":[22,62,112,124],"comparing":[23],"reduced":[24],"representations,":[26],"tools":[27,72],"such":[28],"as":[29],"MashMap":[30,56],"can":[31],"scale":[32],"massive":[34],"numbers":[35],"of":[36,55,65,78,98,120,133],"pairwise":[37],"comparisons":[38],"while":[39],"still":[40],"providing":[41],"useful":[42],"estimates.":[44,80],"However,":[45],"due":[46],"their":[48],"reliance":[49],"minimizer":[51,94],"winnowing,":[52],"previous":[53],"versions":[54],"were":[57],"biased":[61],"inconsistent":[63],"estimators":[64],"similarity.":[67],"This":[68],"directly":[69],"impacts":[70],"downstream":[71],"that":[73,114],"rely":[74],"the":[76,87,93,144,148],"accuracy":[77],"these":[79],"RESULTS:":[81],"To":[82],"address":[83],"this,":[84],"we":[85,125],"propose":[86],"minmer":[88],"winnowing":[89],"scheme,":[90],"which":[91],"generalizes":[92],"scheme":[95,128],"by":[96],"use":[97],"rolling":[100],"minhash":[101],"with":[102],"multiple":[103],"sampled":[104],"k-mers":[105],"per":[106],"window.":[107],"We":[108],"show":[109],"both":[110],"theoretically":[111],"empirically":[113],"minmers":[115],"yield":[116],"an":[117,130],"unbiased":[118],"estimator":[119],"local":[121],"similarity,":[123],"implement":[126],"this":[127],"in":[129],"updated":[131],"version":[132,146],"MashMap.":[134],"minmer-based":[136],"implementation":[137],"is":[138,164],"over":[139],"10":[140],"times":[141],"faster":[142],"than":[143],"minimizer-based":[145],"under":[147],"default":[149],"ANI":[150],"threshold,":[151],"making":[152],"it":[153],"well-suited":[154],"large-scale":[156],"comparative":[157],"genomics":[158],"applications.":[159],"AVAILABILITY":[160],"AND":[161],"IMPLEMENTATION:":[162],"MashMap3":[163],"available":[165],"at":[166],"https://github.com/marbl/MashMap.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
