{"id":"https://openalex.org/W2953193622","doi":"https://doi.org/10.1089/cmb.2017.0113","title":"Shared Nearest Neighbor Clustering in a Locality Sensitive Hashing Framework","display_name":"Shared Nearest Neighbor Clustering in a Locality Sensitive Hashing Framework","publication_year":2017,"publication_date":"2017-09-27","ids":{"openalex":"https://openalex.org/W2953193622","doi":"https://doi.org/10.1089/cmb.2017.0113","mag":"2953193622","pmid":"https://pubmed.ncbi.nlm.nih.gov/28953425"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2017.0113","doi":"https://doi.org/10.1089/cmb.2017.0113","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2017.0113","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2016/12/15/093898.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sawsan Kanj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I4210096708","display_name":"G\u00e9nomique M\u00e9tabolique du Genoscope","ror":"https://ror.org/00xc55v17","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210096427","https://openalex.org/I4210096708","https://openalex.org/I4210113668","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I4210115028","display_name":"Genoscope","ror":"https://ror.org/028pnqf58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210115028"]},{"id":"https://openalex.org/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sawsan Kanj","raw_affiliation_strings":["CEA, Genoscope, Evry, France","CEA, LIST, Laboratoire d'Analyse de Donn\u00e9es et Intelligence des Syst\u00e8mes, Gif-sur-Yvette, France","CNRS-UMR 8030, Evry, France","Universit\u00e9 Paris-Saclay, Evry, France","Universit\u00e9 d'Evry, Evry, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA, Genoscope, Evry, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210115028"]},{"raw_affiliation_string":"CEA, LIST, Laboratoire d'Analyse de Donn\u00e9es et Intelligence des Syst\u00e8mes, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861"]},{"raw_affiliation_string":"CNRS-UMR 8030, Evry, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210096708"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Evry, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"Universit\u00e9 d'Evry, Evry, France","institution_ids":["https://openalex.org/I88467170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067751149","display_name":"Thomas Br\u00fcls","orcid":"https://orcid.org/0000-0003-3525-8979","observed_orcids":["https://orcid.org/0000-0003-3525-8979"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210096708","display_name":"G\u00e9nomique M\u00e9tabolique du Genoscope","ror":"https://ror.org/00xc55v17","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210096427","https://openalex.org/I4210096708","https://openalex.org/I4210113668","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I4210115028","display_name":"Genoscope","ror":"https://ror.org/028pnqf58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210115028"]},{"id":"https://openalex.org/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Br\u00fcls","raw_affiliation_strings":["CEA, Genoscope, Evry, France","CNRS-UMR 8030, Evry, France","Universit\u00e9 Paris-Saclay, Evry, France","Universit\u00e9 d'Evry, Evry, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA, Genoscope, Evry, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210115028"]},{"raw_affiliation_string":"CNRS-UMR 8030, Evry, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210096708"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Evry, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"Universit\u00e9 d'Evry, Evry, France","institution_ids":["https://openalex.org/I88467170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021608885","display_name":"St\u00e9phane Gazut","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Gazut","raw_affiliation_strings":["CEA, LIST, Laboratoire d'Analyse de Donn\u00e9es et Intelligence des Syst\u00e8mes, Gif-sur-Yvette, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEA, LIST, Laboratoire d'Analyse de Donn\u00e9es et Intelligence des Syst\u00e8mes, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210096708","https://openalex.org/I4210115028","https://openalex.org/I88467170"],"apc_list":null,"apc_paid":null,"fwci":1.2972,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84067608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":"2","first_page":"236","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9663000106811523,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9663000106811523,"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":0.01720000058412552,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/locality-sensitive-hashing","display_name":"locality-sensitive hashing","score":0.9919999837875366},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.7950000166893005},{"id":"https://openalex.org/keywords/genome-reconstruction","display_name":"genome reconstruction","score":0.6629999876022339},{"id":"https://openalex.org/keywords/environmental-metagenomes","display_name":"environmental metagenomes","score":0.335999995470047}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8171894550323486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840795874595642},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6101173162460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.563766598701477},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5493058562278748},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.49017009139060974},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.47409161925315857},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4585355222225189},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4538693130016327},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44672971963882446},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42023614048957825},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.36335188150405884},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35579347610473633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24026942253112793},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16949784755706787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1588563323020935},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1089/cmb.2017.0113","doi":"https://doi.org/10.1089/cmb.2017.0113","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2017.0113","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"doi:10.1101/093898","doi":"https://doi.org/10.1101/093898","is_oa":true,"landing_page_url":"https://doi.org/10.1101/093898","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2016/12/15/093898.full.pdf","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:28953425","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28953425","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,"listed_in":[],"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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":"Journal Article"},{"id":"pmh:oai:HAL:cea-01765667v1","doi":null,"is_oa":true,"landing_page_url":"https://cea.hal.science/cea-01765667","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Journal of Computational Biology, 2018, 25 (2), pp.236 - 250. ⟨10.1089/cmb.2017.0113⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1101/093898","doi":"https://doi.org/10.1101/093898","is_oa":true,"landing_page_url":"https://doi.org/10.1101/093898","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2016/12/15/093898.full.pdf","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Life on land","id":"https://metadata.un.org/sdg/15","score":0.6299999952316284}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953193622.pdf","grobid_xml":"https://content.openalex.org/works/W2953193622.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W26356079","https://openalex.org/W80917968","https://openalex.org/W87092222","https://openalex.org/W101045393","https://openalex.org/W114704759","https://openalex.org/W1501500081","https://openalex.org/W1507901999","https://openalex.org/W1524704912","https://openalex.org/W1536741282","https://openalex.org/W1566114229","https://openalex.org/W1579534339","https://openalex.org/W1586960429","https://openalex.org/W1633659671","https://openalex.org/W1660133578","https://openalex.org/W1673310716","https://openalex.org/W1679913846","https://openalex.org/W1917795079","https://openalex.org/W1977496278","https://openalex.org/W1977556410","https://openalex.org/W1987772085","https://openalex.org/W1997673861","https://openalex.org/W2003347102","https://openalex.org/W2012833704","https://openalex.org/W2019324975","https://openalex.org/W2020735245","https://openalex.org/W2045204781","https://openalex.org/W2049633694","https://openalex.org/W2059139185","https://openalex.org/W2079361215","https://openalex.org/W2089923519","https://openalex.org/W2090836891","https://openalex.org/W2103901746","https://openalex.org/W2109034006","https://openalex.org/W2116895571","https://openalex.org/W2121291798","https://openalex.org/W2122646534","https://openalex.org/W2125310307","https://openalex.org/W2132069633","https://openalex.org/W2138615112","https://openalex.org/W2140604849","https://openalex.org/W2141585940","https://openalex.org/W2144035851","https://openalex.org/W2146646206","https://openalex.org/W2147717514","https://openalex.org/W2149230623","https://openalex.org/W2150015221","https://openalex.org/W2155563453","https://openalex.org/W2159954944","https://openalex.org/W2160642098","https://openalex.org/W2162006472","https://openalex.org/W2164122986","https://openalex.org/W2164327068","https://openalex.org/W2170037597","https://openalex.org/W2319660501","https://openalex.org/W2325217181","https://openalex.org/W2397770138","https://openalex.org/W2406173735","https://openalex.org/W2498094064","https://openalex.org/W2515300444","https://openalex.org/W2515836512","https://openalex.org/W2550065181","https://openalex.org/W2598684926","https://openalex.org/W3003734944","https://openalex.org/W3004909842","https://openalex.org/W4231029117","https://openalex.org/W4232535768","https://openalex.org/W4235169531","https://openalex.org/W4236654676","https://openalex.org/W4244207479","https://openalex.org/W4244485282","https://openalex.org/W4245176872","https://openalex.org/W4246396312","https://openalex.org/W4250042253","https://openalex.org/W4300601563","https://openalex.org/W4378419402","https://openalex.org/W6607776381"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W3094967175","https://openalex.org/W2166822184","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280","https://openalex.org/W2754607325","https://openalex.org/W2901290148"],"abstract_inverted_index":{"We":[0,82],"present":[1],"a":[2,25,85,135,166],"new":[3,86],"algorithm":[4],"to":[5,13,58,74,143,153],"cluster":[6],"high-dimensional":[7],"sequence":[8,80],"data":[9,40,113],"and":[10,118,171],"its":[11],"application":[12],"the":[14,43,60,67,75,91,95,111,120],"field":[15],"of":[16,27,38,45,62,78,97,125,138,157,159,168],"metagenomics,":[17],"which":[18],"aims":[19],"at":[20],"reconstructing":[21],"individual":[22],"genomes":[23,28],"from":[24,30,146],"mixture":[26],"sampled":[29],"an":[31],"environmental":[32],"site,":[33],"without":[34],"any":[35],"prior":[36],"knowledge":[37],"reference":[39],"(genomes)":[41],"or":[42],"shape":[44],"clusters.":[46],"Such":[47],"problems":[48],"typically":[49],"cannot":[50],"be":[51,130,144],"solved":[52],"directly":[53],"with":[54,94],"classical":[55],"approaches":[56],"seeking":[57],"estimate":[59],"density":[61],"clusters,":[63],"for":[64],"example,":[65],"using":[66],"shared":[68],"nearest":[69],"neighbors":[70,133],"(SNN)":[71],"rule,":[72],"due":[73],"prohibitive":[76],"size":[77],"contemporary":[79],"datasets.":[81],"explore":[83],"here":[84],"approach":[87],"based":[88],"on":[89,123],"combining":[90],"SNN":[92,121],"rule":[93,122],"concept":[96],"locality":[98],"sensitive":[99],"hashing":[100],"(LSH).":[101],"The":[102],"proposed":[103],"method,":[104],"called":[105],"LSH-SNN,":[106],"works":[107],"by":[108],"randomly":[109],"splitting":[110],"input":[112],"into":[114],"smaller-sized":[115],"subsets":[116],"(buckets)":[117],"employing":[119],"each":[124],"these":[126],"buckets.":[127],"Links":[128],"can":[129,150],"created":[131],"among":[132],"sharing":[134],"sufficient":[136],"number":[137],"elements,":[139],"hence":[140],"allowing":[141],"clusters":[142],"grown":[145],"linked":[147],"elements.":[148],"LSH-SNN":[149],"scale":[151],"up":[152],"larger":[154],"datasets":[155],"consisting":[156],"millions":[158],"sequences,":[160],"while":[161],"achieving":[162],"high":[163],"accuracy":[164],"across":[165],"variety":[167],"sample":[169],"sizes":[170],"complexities.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2025-10-10T00:00:00"}