{"id":"https://openalex.org/W4226289813","doi":"https://doi.org/10.1093/bioinformatics/btac244","title":"The minimizer Jaccard estimator is biased and inconsistent","display_name":"The minimizer Jaccard estimator is biased and inconsistent","publication_year":2022,"publication_date":"2022-04-14","ids":{"openalex":"https://openalex.org/W4226289813","doi":"https://doi.org/10.1093/bioinformatics/btac244","pmid":"https://pubmed.ncbi.nlm.nih.gov/35758786"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac244","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":"hybrid","oa_url":"https://doi.org/10.1093/bioinformatics/btac244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028555855","display_name":"Mahdi Belbasi","orcid":"https://orcid.org/0000-0002-2021-2292"},"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":"Mahdi Belbasi","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008395399","display_name":"Antonio Blanca","orcid":"https://orcid.org/0000-0002-4675-2596"},"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":"Antonio Blanca","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074817739","display_name":"Robert S. Harris","orcid":"https://orcid.org/0000-0001-5464-6892"},"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":"Robert S Harris","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002668669","display_name":"David Koslicki","orcid":"https://orcid.org/0000-0002-0640-954X"},"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":"David Koslicki","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University , University Park, PA, USA","Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"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":true,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University , University Park, PA, USA","Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066909672"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.8191,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8535718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"38","issue":"Supplement_1","first_page":"i169","last_page":"i176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.24279999732971191,"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/T10885","display_name":"Gene expression and cancer classification","score":0.24279999732971191,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.1177000030875206,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0794999971985817,"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/jaccard-index","display_name":"Jaccard index","score":0.9823051691055298},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7681331038475037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.622008740901947},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5531924962997437},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5104090571403503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48535409569740295},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.44645631313323975},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4300318956375122},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4155755043029785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40776193141937256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2193046510219574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20805853605270386}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9823051691055298},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7681331038475037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622008740901947},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5531924962997437},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5104090571403503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48535409569740295},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.44645631313323975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4300318956375122},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4155755043029785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40776193141937256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2193046510219574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20805853605270386},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btac244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac244","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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:35758786","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35758786","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:scholarsphere.psu.edu:f16a50d4-3d6a-4521-94ca-262a2b0285bc","is_oa":false,"landing_page_url":"https://scholarsphere.psu.edu/resources/f16a50d4-3d6a-4521-94ca-262a2b0285bc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401507","display_name":"ScholarSphere (Penn State Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3130638595","host_organization_name":"Pangasinan State University","host_organization_lineage":["https://openalex.org/I3130638595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9235516","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9235516","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac244","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac244","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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/G174627229","display_name":null,"funder_award_id":"1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2039187732","display_name":null,"funder_award_id":"1356529","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":null,"funder_award_id":"1453527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5619972195","display_name":null,"funder_award_id":"2029170","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1496357020","https://openalex.org/W1954100204","https://openalex.org/W2144560237","https://openalex.org/W2144982963","https://openalex.org/W2194172909","https://openalex.org/W2789843538","https://openalex.org/W2884834061","https://openalex.org/W2892689606","https://openalex.org/W2937044610","https://openalex.org/W2950150251","https://openalex.org/W2950572599","https://openalex.org/W2951254987","https://openalex.org/W2951822379","https://openalex.org/W2952609831","https://openalex.org/W2953328352","https://openalex.org/W2955167895","https://openalex.org/W2961460076","https://openalex.org/W2972805712","https://openalex.org/W2987650093","https://openalex.org/W2992400060","https://openalex.org/W3010772070","https://openalex.org/W3042377559","https://openalex.org/W3043768949","https://openalex.org/W3114310315","https://openalex.org/W3119188679","https://openalex.org/W3128964673","https://openalex.org/W3206657624","https://openalex.org/W4221104280","https://openalex.org/W4237829275","https://openalex.org/W4243450674","https://openalex.org/W6681658524"],"related_works":["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","https://openalex.org/W3127229356","https://openalex.org/W2901284887","https://openalex.org/W2294604808"],"abstract_inverted_index":{"MOTIVATION:":[0],"Sketching":[1,17],"is":[2,61,81],"now":[3],"widely":[4,157],"used":[5,158],"in":[6,85],"bioinformatics":[7],"to":[8,45,167],"reduce":[9],"data":[10,14,178],"size":[11],"and":[12,31,42,63,77,121],"increase":[13],"processing":[15],"speed.":[16],"approaches":[18],"entice":[19],"with":[20],"improved":[21],"scalability":[22],"but":[23],"also":[24],"carry":[25],"the":[26,39,47,57,68,72,75,78,86,89,92,101,108,115,130,136,144,153,156],"danger":[27],"of":[28,91,106,127,155],"decreased":[29],"accuracy":[30,154],"added":[32],"bias.":[33],"In":[34],"this":[35,150],"article,":[36],"we":[37,147],"investigate":[38],"minimizer":[40,58],"sketch":[41],"its":[43],"use":[44],"estimate":[46],"Jaccard":[48,59,138],"similarity":[49],"between":[50,74],"two":[51],"sequences.":[52,116],"RESULTS:":[53],"We":[54,95,117],"show":[55,118],"that":[56,67,123,149],"estimator":[60,76],"biased":[62],"inconsistent,":[64],"which":[65],"means":[66],"expected":[69],"difference":[70],"(i.e.":[71],"bias)":[73],"true":[79,137],"value":[80],"not":[82],"zero,":[83],"even":[84],"limit":[87],"as":[88,103],"lengths":[90],"sequences":[93,128],"grow.":[94],"derive":[96],"an":[97],"analytical":[98],"formula":[99],"for":[100],"bias":[102,131,151],"a":[104],"function":[105],"how":[107],"shared":[109],"k-mers":[110],"are":[111,125,171,179],"laid":[112],"out":[113],"along":[114],"both":[119],"theoretically":[120],"empirically":[122],"there":[124],"families":[126],"where":[129],"can":[132,139],"be":[133,140],"substantial":[134],"(e.g.":[135],"more":[141],"than":[142],"double":[143],"estimate).":[145],"Finally,":[146],"demonstrate":[148],"affects":[152],"mashmap":[159],"read":[160],"mapping":[161],"tool.":[162],"AVAILABILITY":[163],"AND":[164],"IMPLEMENTATION:":[165],"Scripts":[166],"reproduce":[168],"our":[169],"experiments":[170],"available":[172,180],"at":[173,181],"https://github.com/medvedevgroup/minimizer-jaccard-estimator/tree/main/reproduce.":[174],"SUPPLEMENTARY":[175],"INFORMATION:":[176],"Supplementary":[177],"Bioinformatics":[182],"online.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
