{"id":"https://openalex.org/W7225835122","doi":"https://doi.org/10.64898/2026.11.10.765459","title":"Detection of Maximal Exact Matches in Terabases of Genome Assemblies in Compressed Space and Sublinear Time","display_name":"Detection of Maximal Exact Matches in Terabases of Genome Assemblies in Compressed Space and Sublinear Time","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225835122","doi":"https://doi.org/10.64898/2026.11.10.765459"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.10.765459","doi":"https://doi.org/10.64898/2026.11.10.765459","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765459","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.10.765459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016396311","display_name":"Ahsan Sanaullah","orcid":"https://orcid.org/0009-0002-5692-8767","observed_orcids":["https://orcid.org/0009-0002-5692-8767"]},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahsan Sanaullah","raw_affiliation_strings":["Dana-Farber Cancer Institute;"],"raw_orcid":"https://orcid.org/0009-0002-5692-8767","affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute;","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012354604","display_name":"Degui Zhi","orcid":"https://orcid.org/0000-0001-7754-1890","observed_orcids":["https://orcid.org/0000-0001-7754-1890"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Degui Zhi","raw_affiliation_strings":["Yale School of Medicine;"],"raw_orcid":"https://orcid.org/0000-0001-7754-1890","affiliations":[{"raw_affiliation_string":"Yale School of Medicine;","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338825","display_name":"Heng Li","orcid":"https://orcid.org/0000-0003-4874-2874","observed_orcids":["https://orcid.org/0000-0003-4874-2874"]},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Li","raw_affiliation_strings":["Dana-Farber Cancer Institute;"],"raw_orcid":"https://orcid.org/0000-0003-4874-2874","affiliations":[{"raw_affiliation_string":"Dana-Farber Cancer Institute;","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768909","display_name":"Shaojie Zhang","orcid":"https://orcid.org/0000-0002-4051-5549","observed_orcids":["https://orcid.org/0000-0002-4051-5549"]},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojie Zhang","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":"https://orcid.org/0000-0002-4051-5549","affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016396311"],"corresponding_institution_ids":["https://openalex.org/I4210117453"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.00019999999494757503,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":9.999999747378752e-05,"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":[],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.7149999737739563},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.6290000081062317},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.583299994468689},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43130001425743103},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4194999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41659998893737793},{"id":"https://openalex.org/C520416788","wikidata":"https://www.wikidata.org/wiki/Q5419229","display_name":"Exact solutions in general relativity","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.10.765459","doi":"https://doi.org/10.64898/2026.11.10.765459","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765459","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.10.765459","doi":"https://doi.org/10.64898/2026.11.10.765459","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765459","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detection":[0],"of":[1,8,20,27,33,61,73,78,85,89,93,102,156,168,174,203,247,253,256,263,281,314,321,353,384,398,409],"long":[2,21,79,139,150],"exact":[3,22,80,107,151,209,219,234],"matches":[4,23,81,108,152,210,220,235,266],"between":[5,24,82,153],"a":[6,13,30,43,165,279,359,367],"pair":[7],"genomes":[9],"has":[10],"historically":[11],"been":[12],"fundamental":[14,44],"operation":[15,45],"in":[16,29,46,87,112,158,186,212,224,237,249,317,338,381,394,406,424,443],"genomics.":[17],"Similarly,":[18],"detection":[19,77],"all":[25,83,106,149,154,207,217,232,318],"pairs":[26,84,155],"haplotypes":[28],"large":[31,59,136,378],"panel":[32,255],"genotyping":[34],"array":[35,352],"data":[36],"or":[37,265],"whole-genome":[38],"sequencing":[39],"variant":[40],"calls":[41],"is":[42,244,260,298,307,356],"population":[47],"genetics.":[48],"Thanks":[49],"to":[50,91,191,400,434],"various":[51],"recent":[52],"pangenome":[53],"efforts,":[54],"for":[55,147],"the":[56,71,169,172,245,250,254,261,322,345,373,382,410,444],"first":[57],"time,":[58,214,228,241],"panels":[60,88],"high-quality":[62,94],"genome":[63],"assemblies":[64,86,157,257,284],"are":[65,289,432,439],"being":[66],"constructed.":[67],"Therefore,":[68],"we":[69,142,310,342],"propose":[70],"intersection":[72],"these":[74,97],"two":[75],"approaches:":[76],"hundreds":[90,397],"thousands":[92],"assemblies.":[95],"Since":[96],"datasets":[98],"would":[99],"contain":[100],"trillions":[101],"basepairs,":[103],"practically":[104],"detecting":[105],"requires":[109],"algorithms":[110,146,199,269,438],"operating":[111],"at":[113,448],"most":[114],"linear":[115,192],"time":[116,163,193,297],"and":[117,138,161,189,221,229,258,300,366,403,407],"compressed":[118,159,166,178,187],"space.":[119],"Previous":[120],"methods":[121],"such":[122],"as":[123,441],"Mumemto":[124],"achieve":[125],"this,":[126],"but":[127],"running":[128],"them":[129],"on":[130,278,363,372],"terabase-sized":[131],"pangenomes":[132],"still":[133],"took":[134],"very":[135],"space":[137,160,177,188],"time.":[140],"Here,":[141],"describe":[143,197],"more":[144],"efficient":[145],"outputting":[148],"sublinear":[162],"given":[164],"index":[167,295,305],"panel.":[170],"Given":[171],"construction":[173,296,306],"an":[175,312],"O(r)":[176,201,213],"index\u2014a":[179],"one-time":[180],"cost":[181],"that":[182,330,344],"can":[183],"be":[184,435],"done":[185],"close":[190],"with":[194],"previous":[195],"work\u2014we":[196],"three":[198],"taking":[200],"words":[202],"memory:":[204],"(1)":[205],"computing":[206,216,231],"supermaximal":[208,218],"(SMEMs)":[211],"(2)":[215],"their":[222],"occurrences":[223,264],"O(r":[225,238],"+":[226,239],"occ)":[227,240],"(3)":[230],"maximal":[233],"(MEMs)":[236],"where":[242],"r":[243],"number":[246,262],"runs":[248],"Burrows-Wheeler":[251],"transform":[252],"occ":[259],"outputted.":[267],"Our":[268,416,437],"use":[270],"7.5":[271],"times":[272,292,302],"less":[273],"memory":[274],"than":[275],"state-of-the-art":[276],"competitors":[277],"dataset":[280,329],"human":[282],"centromere":[283,383],"from":[285,396],"625":[286],"haplotypes.":[287],"They":[288],"also":[290,376],"20":[291],"faster":[293,303],"if":[294,304],"counted,":[299],"2,500":[301],"excluded.":[308],"Finally,":[309],"perform":[311],"analysis":[313],"all-vs-all":[315],"MEMs":[316],"well-assembled":[319],"centromeres":[320],"Human":[323],"Pangenome":[324],"Reference":[325],"Consortium":[326],"Release":[327],"2":[328,355],"reveals":[331],"multiple":[332,401],"novel":[333],"insights":[334],"into":[335],"structural":[336],"variation":[337],"centromeres.":[339],"For":[340],"example,":[341],"find":[343],"active":[346,411],"\u03b1":[347,412],"-satellite":[348,413],"higher-order":[349],"repeat":[350],"(HOR)":[351],"Chromosome":[354,388],"flanked":[357],"by":[358],"~200":[360],"kbp":[361,369,399],"inversion":[362],"one":[364],"side":[365],"~200\u2013300":[368],"pseudopalindromic":[370],"sequence":[371],"other.":[374],"We":[375],"detect":[377],"segmental":[379,391],"duplications":[380,392],"every":[385],"chromosome":[386],"except":[387],"Y.":[389],"These":[390],"range":[393],"size":[395],"Mbp":[402],"occur":[404],"both":[405],"out":[408],"HOR":[414],"arrays.":[415],"computational":[417],"results":[418,429],"make":[419],"pairwise":[420],"MEM":[421],"analyses":[422],"possible":[423],"pangenomes,":[425],"while":[426],"our":[427],"biological":[428],"show":[430],"they":[431],"likely":[433],"useful.":[436],"implemented":[440],"TeraMEM":[442],"TeraTools":[445],"suite":[446],"available":[447],"https://github.com/ucfcbb/TeraTools.":[449]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}