{"id":"https://openalex.org/W2961460076","doi":"https://doi.org/10.1093/bioinformatics/btz354","title":"Locality-sensitive hashing for the edit distance","display_name":"Locality-sensitive hashing for the edit distance","publication_year":2019,"publication_date":"2019-05-09","ids":{"openalex":"https://openalex.org/W2961460076","doi":"https://doi.org/10.1093/bioinformatics/btz354","mag":"2961460076","pmid":"https://pubmed.ncbi.nlm.nih.gov/31510667"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz354","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i127/28913668/btz354.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i127/28913668/btz354.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014004628","display_name":"Dan DeBlasio","orcid":"https://orcid.org/0000-0003-4110-4431"},"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":"Dan DeBlasio","raw_affiliation_strings":["Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014159929","display_name":"Prashant Pandey","orcid":"https://orcid.org/0000-0001-5576-0320"},"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":"Prashant Pandey","raw_affiliation_strings":["Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","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":true,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009407234","https://openalex.org/A5113653378"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.339,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.9547229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"14","first_page":"i127","last_page":"i135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.4092999994754791,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.4092999994754791,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.19580000638961792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0869000032544136,"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/locality","display_name":"Locality","score":0.8424318432807922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980903148651123},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6550186276435852},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6547026634216309},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5264195799827576},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3244222402572632},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3143974542617798},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2317819893360138},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19596856832504272}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8424318432807922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980903148651123},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6550186276435852},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6547026634216309},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5264195799827576},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3244222402572632},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3143974542617798},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2317819893360138},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19596856832504272},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz354","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i127/28913668/btz354.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":"pmid:31510667","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31510667","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:europepmc.org:5588723","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6612865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz354","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz354","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i127/28913668/btz354.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/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"}],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2961460076.pdf","grobid_xml":"https://content.openalex.org/works/W2961460076.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1579534339","https://openalex.org/W1635391495","https://openalex.org/W1647671624","https://openalex.org/W1968570655","https://openalex.org/W1992950355","https://openalex.org/W2027506564","https://openalex.org/W2055693471","https://openalex.org/W2055906546","https://openalex.org/W2066852475","https://openalex.org/W2066885472","https://openalex.org/W2069893028","https://openalex.org/W2088101210","https://openalex.org/W2103441770","https://openalex.org/W2117683095","https://openalex.org/W2147717514","https://openalex.org/W2170551349","https://openalex.org/W2485242605","https://openalex.org/W2582361049","https://openalex.org/W2784788330","https://openalex.org/W2911708124","https://openalex.org/W2950150251","https://openalex.org/W2952609831","https://openalex.org/W3102863871","https://openalex.org/W4247053599","https://openalex.org/W6636915900","https://openalex.org/W6642105907","https://openalex.org/W6664513800","https://openalex.org/W6677735697"],"related_works":["https://openalex.org/W2135779989","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W144856782","https://openalex.org/W3108918257","https://openalex.org/W2080135560","https://openalex.org/W3136593074","https://openalex.org/W3016124764","https://openalex.org/W2147226516"],"abstract_inverted_index":{"MOTIVATION:":[0],"Sequence":[1],"alignment":[2,62],"is":[3,22,42,158,174,217],"a":[4,15,35,85,95,119,139,159,205],"central":[5],"operation":[6],"in":[7,110,126,171,194],"bioinformatics":[8],"pipeline":[9],"and,":[10],"despite":[11],"many":[12,78],"improvements,":[13],"remains":[14],"computationally":[16],"challenging":[17],"problem.":[18],"Locality-sensitive":[19],"hashing":[20],"(LSH)":[21],"one":[23],"method":[24,122,157],"used":[25,137,165],"to":[26,33,44,83,115,166,178,187,213],"estimate":[27],"the":[28,53,71,105,116,153,162,168,179,183,188,192,195,202,215],"likelihood":[29],"of":[30,55,97,108,118,161,182,191,201],"two":[31],"sequences":[32,56,93,184],"have":[34,60],"proper":[36],"alignment.":[37],"Using":[38],"an":[39,68,144],"LSH,":[40],"it":[41],"possible":[43],"separate,":[45],"with":[46],"high":[47],"probability":[48],"and":[49,99],"relatively":[50],"low":[51],"computation,":[52],"pairs":[54],"that":[57,65,172],"do":[58,100],"not":[59,76,101,176],"high-quality":[61],"from":[63],"those":[64],"may.":[66],"Therefore,":[67],"LSH":[69,90,121,128,145,164],"reduces":[70],"overall":[72],"computational":[73],"requirement":[74],"while":[75],"introducing":[77],"false":[79],"negatives":[80],"(i.e.":[81],"omitting":[82],"report":[84],"valid":[86],"alignment).":[87],"However,":[88],"current":[89],"methods":[91,129],"treat":[92],"as":[94,138,204],"bag":[96],"k-mers":[98,109,193],"take":[102],"into":[103],"account":[104],"relative":[106,189],"ordering":[107],"sequences.":[111,196],"In":[112],"addition,":[113],"due":[114],"lack":[117],"practical":[120],"for":[123,130,152],"edit":[124,154],"distance,":[125],"practice,":[127],"Jaccard":[131,169],"similarity":[132,135],"or":[133],"Hamming":[134],"are":[136,225],"proxy.":[140],"RESULTS:":[141],"We":[142,197],"present":[143,198],"method,":[146],"called":[147],"Order":[148],"Min":[149],"Hash":[150],"(OMH),":[151],"distance.":[155],"This":[156],"refinement":[160],"minHash":[163],"approximate":[167],"similarity,":[170],"OMH":[173,203],"sensitive":[175],"only":[177],"k-mer":[180],"contents":[181],"but":[185],"also":[186],"order":[190],"theoretical":[199],"guarantees":[200],"gapped":[206],"LSH.":[207],"AVAILABILITY":[208],"AND":[209],"IMPLEMENTATION:":[210],"The":[211],"code":[212],"generate":[214],"results":[216],"available":[218,226],"at":[219,227],"http://github.com/Kingsford-Group/omhismb2019.":[220],"SUPPLEMENTARY":[221],"INFORMATION:":[222],"Supplementary":[223],"data":[224],"Bioinformatics":[228],"online.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
