{"id":"https://openalex.org/W4323366466","doi":"https://doi.org/10.1093/bioinformatics/btad219","title":"Locality-preserving minimal perfect hashing of <i>k</i>-mers","display_name":"Locality-preserving minimal perfect hashing of <i>k</i>-mers","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4323366466","doi":"https://doi.org/10.1093/bioinformatics/btad219","pmid":"https://pubmed.ncbi.nlm.nih.gov/37387137"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i534/50741423/btad219.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i534/50741423/btad219.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010860687","display_name":"Giulio Ermanno Pibiri","orcid":"https://orcid.org/0000-0003-0724-7092"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giulio Ermanno Pibiri","raw_affiliation_strings":["Ca\u2019 Foscari University of Venice , Venice 30172, Italy","ISTI-CNR , Pisa 56124, Italy"],"affiliations":[{"raw_affiliation_string":"Ca\u2019 Foscari University of Venice , Venice 30172, Italy","institution_ids":["https://openalex.org/I149461666"]},{"raw_affiliation_string":"ISTI-CNR , Pisa 56124, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041832087","display_name":"Y. Shibuya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yoshihiro Shibuya","raw_affiliation_strings":["University Gustave Eiffel , Marne-la-Vall\u00e9e 77454, France"],"affiliations":[{"raw_affiliation_string":"University Gustave Eiffel , Marne-la-Vall\u00e9e 77454, France","institution_ids":["https://openalex.org/I4210154111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001793115","display_name":"Antoine Limasset","orcid":"https://orcid.org/0000-0002-0669-4141"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Limasset","raw_affiliation_strings":["University of Lille, CRIStAL CNRS, UMR 9189 , Lille F-59000, France"],"affiliations":[{"raw_affiliation_string":"University of Lille, CRIStAL CNRS, UMR 9189 , Lille F-59000, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010860687"],"corresponding_institution_ids":["https://openalex.org/I122991210","https://openalex.org/I149461666"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.2352,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93227209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"39","issue":"Supplement_1","first_page":"i534","last_page":"i543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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":0.9995999932289124,"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/T12029","display_name":"DNA and Biological Computing","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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9936000108718872,"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/hash-function","display_name":"Hash function","score":0.7125833034515381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6513433456420898},{"id":"https://openalex.org/keywords/perfect-hash-function","display_name":"Perfect hash function","score":0.5944048166275024},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5271719694137573},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5168614983558655},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5010440349578857},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4780195951461792},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.46425989270210266},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46310585737228394},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4189395010471344},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41658711433410645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38330018520355225},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3646993637084961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29784220457077026},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2707972526550293},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08147695660591125}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7125833034515381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513433456420898},{"id":"https://openalex.org/C87431388","wikidata":"https://www.wikidata.org/wiki/Q2070573","display_name":"Perfect hash function","level":4,"score":0.5944048166275024},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5271719694137573},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5168614983558655},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5010440349578857},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4780195951461792},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.46425989270210266},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46310585737228394},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4189395010471344},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41658711433410645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38330018520355225},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3646993637084961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29784220457077026},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2707972526550293},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08147695660591125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btad219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i534/50741423/btad219.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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:37387137","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37387137","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:iris.unive.it:10278/5034708","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5034708","pdf_url":"https://iris.unive.it/bitstream/10278/5034708/1/ISMB2023.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10311298","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10311298","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10311298/pdf/btad219.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:HAL:hal-04288471v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04288471","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2023, 39 (Supplement_1), pp.i534-i543. &#x27E8;10.1093/bioinformatics/btad219&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:dnet:people______::678b161c040065e220eb81bf8fe86d08","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"BIOINFORMATICS (OXF., ONLINE), vol. 39","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad219","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad219","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i534/50741423/btad219.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4323366466.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2017185271","https://openalex.org/W2057223122","https://openalex.org/W2059417738","https://openalex.org/W2122316710","https://openalex.org/W2144560237","https://openalex.org/W2438121987","https://openalex.org/W2759261668","https://openalex.org/W2810834465","https://openalex.org/W3018162653","https://openalex.org/W3042377559","https://openalex.org/W3043768949","https://openalex.org/W3112768174","https://openalex.org/W3126102308","https://openalex.org/W3134947292","https://openalex.org/W3142668023","https://openalex.org/W3150463527","https://openalex.org/W3178314485","https://openalex.org/W4221076494","https://openalex.org/W4225502295","https://openalex.org/W4295087956","https://openalex.org/W4318193482","https://openalex.org/W4385656103","https://openalex.org/W6795900517"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2097286495","https://openalex.org/W2144265691","https://openalex.org/W2080388000","https://openalex.org/W2065331859","https://openalex.org/W2155123971","https://openalex.org/W1897694601","https://openalex.org/W1845395494","https://openalex.org/W62638829","https://openalex.org/W2033383639"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"these":[2],"premises,":[3],"we":[4],"initiate":[5],"the":[6,44,48,65,70],"study":[7],"of":[8,12,23,43],"a":[9,21,27,40],"new":[10],"type":[11],"locality-preserving":[13],"MPHF":[14],"designed":[15],"for":[16,33],"k-mers":[17],"extracted":[18],"consecutively":[19],"from":[20],"collection":[22],"strings.":[24],"We":[25],"design":[26],"construction":[28],"whose":[29],"space":[30],"usage":[31],"decreases":[32],"growing":[34],"k":[35],"and":[36,59],"discuss":[37],"experiments":[38],"with":[39,51],"practical":[41],"implementation":[42],"method:":[45],"in":[46,69],"practice,":[47],"functions":[49],"built":[50],"our":[52],"method":[53],"can":[54],"be":[55],"several":[56],"times":[57],"smaller":[58],"even":[60],"faster":[61],"to":[62],"query":[63],"than":[64],"most":[66],"efficient":[67],"MPHFs":[68],"literature.":[71]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2023-03-08T00:00:00"}
