{"id":"https://openalex.org/W3157183682","doi":"https://doi.org/10.1145/3412841.3441851","title":"Efficient DNA sequence partitioning using probabilistic subsets and hypergraphs","display_name":"Efficient DNA sequence partitioning using probabilistic subsets and hypergraphs","publication_year":2021,"publication_date":"2021-03-22","ids":{"openalex":"https://openalex.org/W3157183682","doi":"https://doi.org/10.1145/3412841.3441851","mag":"3157183682"},"language":"en","primary_location":{"id":"doi:10.1145/3412841.3441851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412841.3441851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035080938","display_name":"Mahdi Belcaid","orcid":"https://orcid.org/0009-0004-5185-0643"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Belcaid","raw_affiliation_strings":["University of Hawaii at Manoa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083440317","display_name":"C\u00e9dric Arisdakessian","orcid":"https://orcid.org/0000-0001-5255-0942"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cedric Arisdakessian","raw_affiliation_strings":["University of Hawaii at Manoa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052459756","display_name":"Yuliia Kravchenko","orcid":null},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuliia Kravchenko","raw_affiliation_strings":["University of Hawaii at Manoa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa","institution_ids":["https://openalex.org/I117965899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03098228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9966999888420105,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9941999912261963,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7826029062271118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813091278076172},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7002402544021606},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4814452528953552},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4451858401298523},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4402579665184021},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4313317537307739},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3979873061180115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3328663110733032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.260492742061615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17746174335479736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15979161858558655},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10545718669891357}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7826029062271118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813091278076172},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7002402544021606},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4814452528953552},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4451858401298523},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4402579665184021},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4313317537307739},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3979873061180115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3328663110733032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.260492742061615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17746174335479736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15979161858558655},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10545718669891357},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3412841.3441851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412841.3441851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1986022261","https://openalex.org/W2006290495","https://openalex.org/W2014213504","https://openalex.org/W2085315239","https://openalex.org/W2104189907","https://openalex.org/W2108211735","https://openalex.org/W2115387350","https://openalex.org/W2116699248","https://openalex.org/W2124351063","https://openalex.org/W2156125289","https://openalex.org/W2160209604","https://openalex.org/W2170747616","https://openalex.org/W2513506562"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2760721665","https://openalex.org/W2588219639"],"abstract_inverted_index":{"Sequence":[0],"clustering":[1,26,51],"is":[2,34,45],"an":[3,104],"important":[4],"computational":[5,91],"step":[6,102],"in":[7,134,144],"numerous":[8],"bioinformatics":[9],"applications":[10],"such":[11],"as":[12],"high-throughput":[13,32],"immune":[14],"system":[15],"characterization,":[16],"marker-based":[17],"diversity":[18],"profiling,":[19],"and":[20,36,47,113],"reduced-complexity":[21],"population":[22],"genetic":[23],"experiments.":[24],"However,":[25],"very":[27],"large":[28,43,69],"datasets":[29,44,70,148],"produced":[30],"by":[31],"sequencers":[33],"CPU-":[35],"memory-intensive.":[37],"As":[38],"such,":[39],"the":[40,115],"analysis":[41],"of":[42,71,73,109,118],"challenging":[46],"often":[48],"requires":[49],"compromising":[50],"sensitivity":[52,87],"for":[53,106,114],"speed.":[54],"To":[55],"address":[56],"this":[57,100],"limitation,":[58],"we":[59,132],"propose":[60],"a":[61,135,145],"new":[62],"probabilistic":[63],"data":[64],"partitioning":[65,101,157],"technique":[66],"that":[67,80,128,149],"divides":[68],"sequences":[72],"equal":[74],"length":[75],"into":[76],"smaller,":[77],"non-overlapping":[78],"subsets":[79],"can":[81,139],"subsequently":[82],"be":[83,140],"clustered":[84],"using":[85,121],"higher":[86],"algorithms":[88],"at":[89],"lower":[90],"costs.":[92],"In":[93],"addition":[94],"to":[95,142,154],"substantially":[96],"lowering":[97],"resources":[98],"requirements,":[99],"provides":[103],"opportunity":[105],"effortless":[107],"parallelization":[108],"DNA":[110],"sequence":[111],"clustering,":[112],"independent":[116],"processing":[117],"each":[119],"subset":[120],"more":[122],"accurate":[123],"algorithms.":[124],"Our":[125],"results":[126],"show":[127],"our":[129],"algorithm,":[130],"which":[131],"implemented":[133],"program":[136],"called":[137],"SLYMFAST":[138],"used":[141],"cluster":[143,155],"few":[146],"hours":[147],"would":[150],"otherwise":[151],"take":[152],"weeks":[153],"without":[156],"first.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}