{"id":"https://openalex.org/W3182040180","doi":"https://doi.org/10.1093/bioinformatics/btab313","title":"Sequence-specific minimizers via polar sets","display_name":"Sequence-specific minimizers via polar sets","publication_year":2021,"publication_date":"2021-05-12","ids":{"openalex":"https://openalex.org/W3182040180","doi":"https://doi.org/10.1093/bioinformatics/btab313","mag":"3182040180","pmid":"https://pubmed.ncbi.nlm.nih.gov/34252928"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab313","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab313","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i187/39620355/btab313.pdf","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://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i187/39620355/btab313.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070273851","display_name":"Hongyu Zheng","orcid":"https://orcid.org/0000-0002-7668-2090"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyu Zheng","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009407234","display_name":"Guillaume Mar\u00e7ais","orcid":"https://orcid.org/0000-0002-5083-5925"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guillaume Mar\u00e7ais","raw_affiliation_strings":["Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009407234"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.9545,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.86879563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"Supplement_1","first_page":"i187","last_page":"i195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.18219999969005585,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.18219999969005585,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.12240000069141388,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.10729999840259552,"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/sequence","display_name":"Sequence (biology)","score":0.7769070863723755},{"id":"https://openalex.org/keywords/polar","display_name":"Polar","score":0.7205660939216614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4693881869316101},{"id":"https://openalex.org/keywords/polar-coordinate-system","display_name":"Polar coordinate system","score":0.42965346574783325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4000498950481415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3593037724494934},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1886599063873291},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.17530924081802368},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12987664341926575},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10017135739326477}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7769070863723755},{"id":"https://openalex.org/C29705727","wikidata":"https://www.wikidata.org/wiki/Q294562","display_name":"Polar","level":2,"score":0.7205660939216614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4693881869316101},{"id":"https://openalex.org/C40069579","wikidata":"https://www.wikidata.org/wiki/Q62494","display_name":"Polar coordinate system","level":2,"score":0.42965346574783325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4000498950481415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3593037724494934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1886599063873291},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.17530924081802368},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12987664341926575},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10017135739326477},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab313","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab313","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i187/39620355/btab313.pdf","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:34252928","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34252928","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:pubmedcentral.nih.gov:8686682","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8686682","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/btab313","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab313","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i187/39620355/btab313.pdf","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1191257363","display_name":null,"funder_award_id":"4100070287","funder_id":"https://openalex.org/F4320311953","funder_display_name":"Shurl and Kay Curci Foundation"},{"id":"https://openalex.org/G3023850491","display_name":null,"funder_award_id":"R01GM122935","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5836720286","display_name":null,"funder_award_id":"R01 GM122935","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7686337660","display_name":null,"funder_award_id":"DBI-1937540","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/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320308109","display_name":"Pennsylvania Department of Health","ror":"https://ror.org/00ra1fg11"},{"id":"https://openalex.org/F4320311953","display_name":"Shurl and Kay Curci Foundation","ror":"https://ror.org/05t9fgt79"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1825683889","https://openalex.org/W1980664567","https://openalex.org/W2009119978","https://openalex.org/W2010454899","https://openalex.org/W2125266506","https://openalex.org/W2130062792","https://openalex.org/W2144560237","https://openalex.org/W2438121987","https://openalex.org/W2563930566","https://openalex.org/W2597444305","https://openalex.org/W2763390627","https://openalex.org/W2789843538","https://openalex.org/W2792368734","https://openalex.org/W2937044610","https://openalex.org/W2937172564","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W3016701095","https://openalex.org/W3042374389","https://openalex.org/W3042377559","https://openalex.org/W3043768949","https://openalex.org/W3100437611","https://openalex.org/W3114310315","https://openalex.org/W3128964673","https://openalex.org/W3133954690","https://openalex.org/W4237975145"],"related_works":["https://openalex.org/W49546004","https://openalex.org/W2362929369","https://openalex.org/W3006858033","https://openalex.org/W4378530320","https://openalex.org/W2970011562","https://openalex.org/W4205581374","https://openalex.org/W2387889211","https://openalex.org/W893388528","https://openalex.org/W2161804380","https://openalex.org/W207384436"],"abstract_inverted_index":{"MOTIVATION:":[0],"Minimizers":[1],"are":[2,120,124,214,221],"efficient":[3,23,63,177,197],"methods":[4,20,92],"to":[5,21,46,61,65,97,110,135,179],"sample":[6,66],"k-mers":[7,29,41,68],"from":[8,158],"genomic":[9],"sequences":[10],"that":[11,42,123],"unconditionally":[12],"preserve":[13],"sufficiently":[14],"long":[15],"matches":[16],"between":[17],"sequences.":[18,100,137],"Well-established":[19],"construct":[22,62,180],"minimizers":[24,64],"focus":[25],"on":[26,30,69,128,186],"sampling":[27],"fewer":[28,67],"a":[31,70,145,163],"random":[32],"sequence":[33,72],"and":[34,90,131,149,160,183,206],"use":[35],"universal":[36,115],"hitting":[37,116],"sets":[38,119,122],"(sets":[39],"of":[40,56,85,106,114,172],"appear":[43],"frequently":[44],"enough)":[45],"upper":[47],"bound":[48],"the":[49,54,75,82,104,111,129,152,187],"sketch":[50,98,153,173],"size.":[51,174],"In":[52],"contrast,":[53],"problem":[55,87],"sequence-specific":[57,198],"minimizers,":[58],"which":[59],"is":[60,78,88],"specific":[71,99,136],"such":[73],"as":[74],"reference":[76,189,204],"genome,":[77,190],"less":[79],"studied.":[80],"Currently,":[81],"theoretical":[83],"understanding":[84],"this":[86],"lacking,":[89],"existing":[91,112],"do":[93],"not":[94],"specialize":[95,133],"well":[96,134,142],"RESULTS:":[101],"We":[102,175],"propose":[103,176],"concept":[105],"polar":[107,146,181],"sets,":[108,182],"complementary":[109],"idea":[113],"sets.":[117],"Polar":[118],"k-mer":[121],"spread":[125,143],"out":[126,144],"enough":[127],"reference,":[130],"provably":[132],"Link":[138],"energy":[139],"measures":[140],"how":[141],"set":[147],"is,":[148],"with":[150],"it,":[151],"size":[154],"can":[155],"be":[156],"bounded":[157],"above":[159],"below":[161],"in":[162,195],"theoretically":[164],"sound":[165],"way.":[166],"This":[167],"allows":[168],"for":[169,208],"direct":[170],"optimization":[171],"heuristics":[178],"via":[184],"experiments":[185],"human":[188],"show":[191],"their":[192],"practical":[193],"superiority":[194],"designing":[196],"minimizers.":[199],"AVAILABILITY":[200],"AND":[201],"IMPLEMENTATION:":[202],"A":[203],"implementation":[205],"code":[207],"analyses":[209],"under":[210],"an":[211],"open-source":[212],"license":[213],"at":[215,223],"https://github.com/kingsford-group/polarset.":[216],"SUPPLEMENTARY":[217],"INFORMATION:":[218],"Supplementary":[219],"data":[220],"available":[222],"Bioinformatics":[224],"online.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
