{"id":"https://openalex.org/W4292961172","doi":"https://doi.org/10.1093/bioinformatics/btac564","title":"ntHash2: recursive spaced seed hashing for nucleotide sequences","display_name":"ntHash2: recursive spaced seed hashing for nucleotide sequences","publication_year":2022,"publication_date":"2022-08-24","ids":{"openalex":"https://openalex.org/W4292961172","doi":"https://doi.org/10.1093/bioinformatics/btac564","pmid":"https://pubmed.ncbi.nlm.nih.gov/36000872"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac564","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://doi.org/10.1093/bioinformatics/btac564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044309076","display_name":"Parham Kazemi","orcid":"https://orcid.org/0000-0002-2126-5644"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Parham Kazemi","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","Faculty of Science, University of British Columbia , Vancouver, BC V6T 1Z4, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2126-5644","affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","institution_ids":["https://openalex.org/I4210133112"]},{"raw_affiliation_string":"Faculty of Science, University of British Columbia , Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675804","display_name":"Johnathan Wong","orcid":"https://orcid.org/0000-0002-1687-8972"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Johnathan Wong","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039018062","display_name":"Vladimir Nikoli\u0107","orcid":"https://orcid.org/0000-0002-2992-9935"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vladimir Nikoli\u0107","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111786891","display_name":"Hamid Mohamadi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamid Mohamadi","raw_affiliation_strings":["Amazon Web Services Inc. , Seattle, WA 98109, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services Inc. , Seattle, WA 98109, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829017","display_name":"Ren\u00e9 L. Warren","orcid":"https://orcid.org/0000-0002-9890-2293"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ren\u00e9 L Warren","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9890-2293","affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017539699","display_name":"\u0130nan\u00e7 Birol","orcid":"https://orcid.org/0000-0003-0950-7839"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Inan\u00e7 Birol","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","Department of Medical Genetics, University of British Columbia , Vancouver, BC V6T 1Z3, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0950-7839","affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency , Vancouver, BC V5Z 4S6, Canada","institution_ids":["https://openalex.org/I4210133112"]},{"raw_affiliation_string":"Department of Medical Genetics, University of British Columbia , Vancouver, BC V6T 1Z3, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017539699","https://openalex.org/A5044309076"],"corresponding_institution_ids":["https://openalex.org/I141945490","https://openalex.org/I4210133112"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.7744,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91635329,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"38","issue":"20","first_page":"4812","last_page":"4813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.722100019454956,"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":0.722100019454956,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.060600001364946365,"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":0.040800001472234726,"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":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.807900607585907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204527854919434},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.6022375226020813},{"id":"https://openalex.org/keywords/universal-hashing","display_name":"Universal hashing","score":0.533944308757782},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4865761995315552},{"id":"https://openalex.org/keywords/linear-hashing","display_name":"Linear hashing","score":0.4542177617549896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4259960353374481},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4212051331996918},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39169812202453613},{"id":"https://openalex.org/keywords/perfect-hash-function","display_name":"Perfect hash function","score":0.23686790466308594},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.2200188934803009},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18057751655578613},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12093591690063477},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10091656446456909}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.807900607585907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204527854919434},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.6022375226020813},{"id":"https://openalex.org/C116058348","wikidata":"https://www.wikidata.org/wiki/Q846912","display_name":"Universal hashing","level":5,"score":0.533944308757782},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4865761995315552},{"id":"https://openalex.org/C36375716","wikidata":"https://www.wikidata.org/wiki/Q6553456","display_name":"Linear hashing","level":5,"score":0.4542177617549896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4259960353374481},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4212051331996918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39169812202453613},{"id":"https://openalex.org/C87431388","wikidata":"https://www.wikidata.org/wiki/Q2070573","display_name":"Perfect hash function","level":4,"score":0.23686790466308594},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.2200188934803009},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18057751655578613},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12093591690063477},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10091656446456909}],"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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012639","descriptor_name":"Seeds","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012639","descriptor_name":"Seeds","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012639","descriptor_name":"Seeds","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac564","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36000872","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36000872","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:pubmedcentral.nih.gov:9563681","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9563681","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac564","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4568173531","display_name":null,"funder_award_id":"2R01HG007182-04A1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2128591967","https://openalex.org/W2314046074","https://openalex.org/W2463091895","https://openalex.org/W2992957976","https://openalex.org/W3041800561"],"related_works":["https://openalex.org/W2811247857","https://openalex.org/W2334522381","https://openalex.org/W2084899141","https://openalex.org/W2076162755","https://openalex.org/W102859714","https://openalex.org/W1994360333","https://openalex.org/W2044784665","https://openalex.org/W1551533237","https://openalex.org/W2390631617","https://openalex.org/W4385261619"],"abstract_inverted_index":{"MOTIVATION:":[0],"Spaced":[1],"seeds":[2,66],"are":[3,125],"robust":[4],"alternatives":[5],"to":[6,59],"k-mers":[7],"in":[8,52],"analyzing":[9],"nucleotide":[10],"sequences":[11],"with":[12,50,78],"high":[13],"base":[14],"mismatch":[15],"rates.":[16],"Hashing":[17],"is":[18,57,111],"also":[19],"crucial":[20],"for":[21,34,46,89],"efficiently":[22],"storing":[23],"abundant":[24],"sequence":[25,48],"data.":[26],"Here,":[27],"we":[28,82],"introduce":[29],"ntHash2,":[30],"a":[31],"fast":[32],"algorithm":[33],"spaced":[35,65],"seed":[36],"hashing":[37,63,76,105],"that":[38],"can":[39],"be":[40],"integrated":[41],"into":[42],"various":[43,64],"bioinformatics":[44],"tools":[45],"efficient":[47],"analysis":[49],"applications":[51],"genome":[53],"research.":[54],"RESULTS:":[55],"ntHash2":[56,110],"up":[58],"2.1\u00d7":[60],"faster":[61,73],"at":[62,115,127],"than":[67,74],"the":[68,84,95,98,103],"previous":[69],"version":[70],"and":[71,93],"3.8\u00d7":[72],"conventional":[75],"algorithms":[77],"na\u00efve":[79],"adaptation.":[80],"Additionally,":[81],"reduced":[83],"collision":[85],"rate":[86],"of":[87,97],"ntHash":[88],"longer":[90],"k-mer":[91],"lengths":[92],"improved":[94],"uniformity":[96],"hash":[99],"distribution":[100],"by":[101],"modifying":[102],"canonical":[104],"mechanism.":[106],"AVAILABILITY":[107],"AND":[108],"IMPLEMENTATION:":[109],"freely":[112],"available":[113,126],"online":[114],"github.com/bcgsc/ntHash":[116],"under":[117],"an":[118],"MIT":[119],"license.":[120],"SUPPLEMENTARY":[121],"INFORMATION:":[122],"Supplementary":[123],"data":[124],"Bioinformatics":[128],"online.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}