{"id":"https://openalex.org/W3043768949","doi":"https://doi.org/10.1093/bioinformatics/btaa472","title":"Improved design and analysis of practical minimizers","display_name":"Improved design and analysis of practical minimizers","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3043768949","doi":"https://doi.org/10.1093/bioinformatics/btaa472","mag":"3043768949"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa472","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa472","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/Supplement_1/i119/33488913/btaa472.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/36/Supplement_1/i119/33488913/btaa472.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":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","institution_ids":["https://openalex.org/I74973139"]},{"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":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","institution_ids":["https://openalex.org/I74973139"]},{"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":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA Computational Biology Department,","institution_ids":["https://openalex.org/I74973139"]},{"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":null,"fwci":5.0671,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.96164347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"36","issue":"Supplement_1","first_page":"i119","last_page":"i127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10996","display_name":"Computational Geometry and Mesh Generation","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer 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":0.6251319646835327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251319646835327}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btaa472","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa472","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/Supplement_1/i119/33488913/btaa472.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8248892","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8248892","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa472","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa472","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/Supplement_1/i119/33488913/btaa472.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1325684988","display_name":null,"funder_award_id":"CCF-1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science 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/G8925788920","display_name":null,"funder_award_id":"CCF-1319998","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043768949.pdf","grobid_xml":"https://content.openalex.org/works/W3043768949.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1980664567","https://openalex.org/W2010454899","https://openalex.org/W2144560237","https://openalex.org/W2438121987","https://openalex.org/W2477408078","https://openalex.org/W2487384794","https://openalex.org/W2789843538","https://openalex.org/W2937044610","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W2972805712","https://openalex.org/W3016701095","https://openalex.org/W3023465514"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Minimizers":[2,43],"are":[3,44,222],"methods":[4],"to":[5,54,148,156,187],"sample":[6],"k-mers":[7,18],"from":[8],"a":[9,33,47,81,98,128,142,175],"string,":[10],"with":[11,122,151],"the":[12,29,41,63,84,88,146,152,166,180,188,206,209],"guarantee":[13,155],"that":[14,119,185],"similar":[15,23],"set":[16],"of":[17,50,80,90,135,182,190,205],"will":[19],"be":[20,214],"chosen":[21],"on":[22,40,158],"strings.":[24],"It":[25],"is":[26,83,100,113,120,168],"parameterized":[27],"by":[28],"k-mer":[30],"length":[31,35],"k,":[32],"window":[34],"w":[36,193],"and":[37,52,58,110,130,164,173,192,201,208],"an":[38],"order":[39],"k-mers.":[42,92],"used":[45,194],"in":[46,105,160,195],"large":[48],"number":[49],"softwares":[51],"pipelines":[53],"improve":[55],"computation":[56],"efficiency":[57],"decrease":[59],"memory":[60],"usage.":[61],"Despite":[62],"method\u2019s":[64],"popularity,":[65],"many":[66],"theoretical":[67,94,154],"questions":[68],"regarding":[69],"its":[70],"performance":[71,79],"remain":[72],"open.":[73],"The":[74,93],"core":[75],"metric":[76],"for":[77,97,133,211],"measuring":[78],"minimizer":[82,99],"density,":[85],"which":[86,178],"measures":[87],"sparsity":[89],"sampled":[91],"optimal":[95,117,137],"density":[96,123,159],"1/w,":[101],"provably":[102],"not":[103],"achievable":[104],"general.":[106],"For":[107],"given":[108],"k":[109,191],"w,":[111],"little":[112],"known":[114],"about":[115],"asymptotically":[116,136],"minimizers,":[118],"minimizers":[121,150,184],"O(1/w).":[124],"Results":[125],"We":[126,139],"derive":[127],"necessary":[129],"sufficient":[131],"condition":[132],"existence":[134],"minimizers.":[138],"also":[140],"provide":[141],"randomized":[143],"algorithm,":[144],"called":[145],"Miniception,":[147],"design":[149,181],"best":[153],"date":[157],"practical":[161],"scenarios.":[162],"Constructing":[163],"using":[165,174],"Miniception":[167,207],"as":[169,171],"easy":[170],"constructing":[172],"random":[176],"minimizer,":[177],"allows":[179],"efficient":[183],"scale":[186],"values":[189],"current":[196],"bioinformatics":[197],"software":[198],"programs.":[199],"Availability":[200],"implementation":[202,204],"Reference":[203],"codes":[210],"analysis":[212],"can":[213],"found":[215],"at":[216,224],"https://github.com/kingsford-group/miniception.":[217],"Supplementary":[218,220],"information":[219],"data":[221],"available":[223],"Bioinformatics":[225],"online.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2020-07-23T00:00:00"}
