{"id":"https://openalex.org/W4417167781","doi":"https://doi.org/10.1186/s12859-025-06333-8","title":"Density-reducing Jaccard estimators for sketch-based long read applications","display_name":"Density-reducing Jaccard estimators for sketch-based long read applications","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4417167781","doi":"https://doi.org/10.1186/s12859-025-06333-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/41366730"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06333-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06333-8","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-025-06333-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102943780","display_name":"Tazin Rahman","orcid":"https://orcid.org/0009-0001-8469-0234"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tazin Rahman","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA. tazin.rahman@wsu.edu","School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA. tazin.rahman@wsu.edu","institution_ids":[]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048410309","display_name":"Ananth Kalyanaraman","orcid":"https://orcid.org/0000-0001-6721-233X"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Kalyanaraman","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99164, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102943780"],"corresponding_institution_ids":["https://openalex.org/I72951846"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37752131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.6187999844551086,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.6187999844551086,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.11810000240802765,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.039000000804662704,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/sketch","display_name":"Sketch","score":0.8306000232696533},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.8011000156402588},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5965999960899353},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.5113999843597412},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5016999840736389},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.39480000734329224},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3675999939441681}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8306000232696533},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8011000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124999761581421},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25850000977516174}],"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":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06333-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06333-8","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41366730","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41366730","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:7c38893d8baf4a389ac4286573a9bd60","is_oa":true,"landing_page_url":"https://doaj.org/article/7c38893d8baf4a389ac4286573a9bd60","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1, Pp 1-22 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12781685","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12781685/","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06333-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06333-8","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2217127445","display_name":null,"funder_award_id":"2316160, 1919122","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2062037904","https://openalex.org/W2105656684","https://openalex.org/W2111295912","https://openalex.org/W2125266506","https://openalex.org/W2137759177","https://openalex.org/W2144560237","https://openalex.org/W2156858199","https://openalex.org/W2157539385","https://openalex.org/W2194172909","https://openalex.org/W2337261418","https://openalex.org/W2755302678","https://openalex.org/W2763390627","https://openalex.org/W2789843538","https://openalex.org/W2892689606","https://openalex.org/W2907043693","https://openalex.org/W2949066452","https://openalex.org/W2950150251","https://openalex.org/W2950354111","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W2973021521","https://openalex.org/W3016701095","https://openalex.org/W3042377559","https://openalex.org/W3043768949","https://openalex.org/W3128964673","https://openalex.org/W3174300009","https://openalex.org/W3200242814","https://openalex.org/W3206657624","https://openalex.org/W4242729757","https://openalex.org/W4243450674","https://openalex.org/W4285283141","https://openalex.org/W4307475426","https://openalex.org/W4311803917","https://openalex.org/W4364353615","https://openalex.org/W4379054112","https://openalex.org/W4382632048","https://openalex.org/W4385585436","https://openalex.org/W4386272000","https://openalex.org/W4388775333","https://openalex.org/W4389153027","https://openalex.org/W4401410921","https://openalex.org/W4409845837"],"related_works":[],"abstract_inverted_index":{"Sequence":[0],"sketching-a":[1],"class":[2],"of":[3,10,26,37,55,63,75,98,109,119,146,153,184,213,220],"techniques":[4],"aimed":[5],"at":[6],"generating":[7],"compact":[8],"representations":[9],"longer":[11],"sequences-has":[12],"become":[13],"widely":[14],"used":[15],"in":[16,50,116,137],"numerous":[17],"long":[18,192],"read":[19,193],"applications,":[20],"including":[21,202],"assembly":[22],"and":[23,39,48,164,204,206,227,256],"mapping.":[24,121,168],"Instead":[25],"comparing":[27],"sequences,":[28],"sketches":[29],"allow":[30],"us":[31],"to":[32,72,133,159,171,197,209,223,252,266],"sample":[33],"from":[34,141,231],"a":[35,64,84,150,161,189],"subspace":[36],"k-mers":[38,78,147],"use":[40],"those":[41],"samples":[42],"for":[43,89,167],"comparison,":[44],"saving":[45],"both":[46],"time":[47],"memory":[49,259],"the":[51,56,61,67,73,76,81,96,99,107,117,155,182,211,218],"end":[52],"application.":[53],"One":[54],"important":[57],"metrics":[58],"that":[59,129,166,238],"determines":[60],"performance":[62,229],"sketch":[65,68,111,135,163],"is":[66,87,176],"density,":[69,173],"which":[70],"refers":[71],"fraction":[74],"sampled":[77],"retained":[79],"by":[80],"sketch.":[82],"While":[83],"lower":[85],"density":[86,112,136,226],"preferable":[88],"space":[90],"considerations,":[91],"it":[92],"could":[93],"also":[94,177],"impact":[95],"sensitivity":[97],"mapping":[100,138,194,243],"process.":[101],"In":[102,169,233],"this":[103,174],"work,":[104],"we":[105,187],"visit":[106],"problem":[108],"reducing":[110,172,245,258],"while":[113,244],"preserving":[114],"accuracy":[115],"context":[118],"long-read":[120],"We":[122],"present":[123],"an":[124,142],"efficient":[125],"algorithm":[126],"called":[127],"MHsketch":[128,208,239],"uses":[130,165],"Jaccard":[131],"estimators":[132],"reduce":[134,225],"applications.":[139],"Starting":[140],"initial":[143],"ground":[144],"set":[145],"generated":[148],"through":[149],"sketching":[151,200],"method":[152],"choice,":[154],"approach":[156,175,222],"applies":[157],"MinHashing":[158],"derive":[160],"smaller":[162],"addition":[170],"easily":[178],"parallelizable.":[179],"To":[180],"demonstrate":[181],"efficacy":[183],"our":[185,221,235],"method,":[186],"modified":[188],"recently":[190],"developed":[191],"tool":[195],"(JEM-mapper)":[196],"adopt":[198],"different":[199],"schemes,":[201],"Syncmer":[203],"Strobemer,":[205],"incorporated":[207],"evaluate":[210],"effectiveness":[212],"downsampling.":[214],"Experimental":[215],"evaluation":[216],"demonstrates":[217],"ability":[219],"significantly":[224],"reap":[228],"benefits":[230],"it.":[232],"particular,":[234],"experiments":[236],"reveal":[237],"(syncmers)":[240],"achieves":[241],"high-quality":[242],"time-to-solution":[246],"(speedups":[247],"between":[248],"[Formula:":[249,253],"see":[250,254,262],"text]":[251,263],"text]),":[255],"drastically":[257],"usage":[260],"([Formula:":[261],"savings)":[264],"compared":[265],"state-of-the-art":[267],"tools.":[268],"Availability:":[269],"https://github.com/TazinRahman1105050/MHsketch":[270],".":[271]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-12-09T00:00:00"}
