{"id":"https://openalex.org/W1996963499","doi":"https://doi.org/10.1109/bibm.2012.6392649","title":"LSH-Div: Species diversity estimation using locality sensitive hashing","display_name":"LSH-Div: Species diversity estimation using locality sensitive hashing","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1996963499","doi":"https://doi.org/10.1109/bibm.2012.6392649","mag":"1996963499"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2012.6392649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2012.6392649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051492611","display_name":"Zeehasham Rasheed","orcid":"https://orcid.org/0009-0005-2688-6473"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeehasham Rasheed","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA","Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006581225","display_name":"Huzefa Rangwala","orcid":"https://orcid.org/0000-0003-0435-0035"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huzefa Rangwala","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA","Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089029917","display_name":"Daniel Barbar\u00e1","orcid":"https://orcid.org/0000-0002-2830-1038"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Barbara","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, VA, USA","Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA 22030, USA#TAB#","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":8.5838,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.97602645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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":0.9994000196456909,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.8886067271232605},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6585607528686523},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6404397487640381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5993035435676575},{"id":"https://openalex.org/keywords/species-richness","display_name":"Species richness","score":0.5288240313529968},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4937168061733246},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44563862681388855},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.4244413375854492},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.2264956533908844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2165706753730774},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1943431794643402},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.12536495923995972},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12035802006721497}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8886067271232605},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6585607528686523},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6404397487640381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5993035435676575},{"id":"https://openalex.org/C53565203","wikidata":"https://www.wikidata.org/wiki/Q17146659","display_name":"Species richness","level":2,"score":0.5288240313529968},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4937168061733246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44563862681388855},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4244413375854492},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.2264956533908844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2165706753730774},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1943431794643402},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.12536495923995972},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12035802006721497},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2012.6392649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2012.6392649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1558982506","https://openalex.org/W2017425843","https://openalex.org/W2059237622","https://openalex.org/W2073548709","https://openalex.org/W2087671769","https://openalex.org/W2107974372","https://openalex.org/W2108718991","https://openalex.org/W2109034006","https://openalex.org/W2113601822","https://openalex.org/W2114413252","https://openalex.org/W2128114769","https://openalex.org/W2130077037","https://openalex.org/W2147717514","https://openalex.org/W2152885278","https://openalex.org/W2156619206","https://openalex.org/W2158795865","https://openalex.org/W2162315106","https://openalex.org/W2406173735","https://openalex.org/W4231601595","https://openalex.org/W4236748729","https://openalex.org/W4238536565","https://openalex.org/W6633575141"],"related_works":["https://openalex.org/W2022250864","https://openalex.org/W4385061579","https://openalex.org/W1855418621","https://openalex.org/W1968126718","https://openalex.org/W195123958","https://openalex.org/W2000601968","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764"],"abstract_inverted_index":{"Metagenome":[0],"sequencing":[1],"projects":[2],"attempt":[3],"to":[4,31,91,127],"determine":[5],"the":[6,20,36,72,79,121,135,157,161],"collective":[7],"DNA":[8],"of":[9,23,35,59,74,106,137,142],"organisms,":[10],"co-existing":[11],"as":[12,92],"communities":[13],"across":[14],"different":[15],"environments.":[16],"Computational":[17],"approaches":[18],"analyze":[19],"large":[21],"volumes":[22],"sequence":[24,76],"data":[25,113],"obtained":[26,119],"from":[27,120],"these":[28],"ecological":[29],"samples,":[30],"provide":[32],"an":[33],"understanding":[34],"species":[37,49,101],"diversity,":[38],"content":[39],"and":[40,97,114,145],"abundance.":[41],"In":[42],"this":[43],"work":[44],"we":[45,70,82],"present":[46],"a":[47,60],"scalable,":[48],"diversity":[50,130],"estimation":[51,131],"algorithm":[52,64,108],"that":[53],"achieves":[54],"computational":[55,143],"efficiency":[56],"by":[57],"use":[58],"locality":[61],"sensitive":[62],"hashing":[63],"(LSH).":[65],"Using":[66,78],"fixed-length,":[67],"gapless":[68],"subsequences,":[69],"improve":[71],"sensitivity":[73],"pairwise":[75],"comparisons.":[77],"LSH-based":[80],"function,":[81],"first":[83],"group":[84],"similar":[85],"sequences":[86],"into":[87],"bins":[88],"commonly":[89],"referred":[90],"operational":[93],"taxonomic":[94],"units":[95],"(OTUs)":[96],"then":[98],"compute":[99],"several":[100],"diversity/richness":[102],"metrics.":[103],"The":[104,149],"performance":[105],"our":[107,125,138],"is":[109,154,167],"evaluated":[110],"on":[111],"synthetic":[112],"eight":[115],"targeted":[116],"metagenome":[117],"samples":[118],"seawater.":[122],"We":[123,133],"compare":[124],"results":[126],"three":[128],"state-of-the-art":[129],"algorithms.":[132],"demonstrate":[134],"strength":[136],"approach":[139],"in":[140],"terms":[141],"runtime":[144],"effective":[146],"OTU":[147],"assignments.":[148],"source":[150],"code":[151],"for":[152],"LSH-Div":[153],"available":[155,168],"at":[156,169],"supplementary":[158],"website":[159],"under":[160],"GNU":[162],"GPL":[163],"license.":[164],"Supplementary":[165],"material":[166],"http://www.cs.gmu.edu/~mlbio/LSH-DIV.":[170]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}