{"id":"https://openalex.org/W3189231637","doi":"https://doi.org/10.1145/3459930.3469521","title":"LSHvec","display_name":"LSHvec","publication_year":2021,"publication_date":"2021-07-30","ids":{"openalex":"https://openalex.org/W3189231637","doi":"https://doi.org/10.1145/3459930.3469521","mag":"3189231637"},"language":"en","primary_location":{"id":"doi:10.1145/3459930.3469521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459930.3469521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","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/A5051631233","display_name":"Lizhen Shi","orcid":"https://orcid.org/0000-0002-8776-4470"},"institutions":[{"id":"https://openalex.org/I32480017","display_name":"Florida Polytechnic University","ror":"https://ror.org/01e5mdj42","country_code":"US","type":"education","lineage":["https://openalex.org/I32480017"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lizhen Shi","raw_affiliation_strings":["Florida Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Florida Polytechnic University","institution_ids":["https://openalex.org/I32480017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427353","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0002-5777-6876"},"institutions":[{"id":"https://openalex.org/I4210136420","display_name":"Tallahassee Orthopedic Clinic","ror":"https://ror.org/03fc2zn41","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210136420"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Chen","raw_affiliation_strings":["Tallahassee"],"affiliations":[{"raw_affiliation_string":"Tallahassee","institution_ids":["https://openalex.org/I4210136420"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051631233"],"corresponding_institution_ids":["https://openalex.org/I32480017"],"apc_list":null,"apc_paid":null,"fwci":0.5631,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.6425321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987999796867371,"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":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9918000102043152,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9907000064849854,"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/metagenomics","display_name":"Metagenomics","score":0.802055299282074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.763850212097168},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6447314023971558},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6297059059143066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5876193642616272},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5723143219947815},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5506771802902222},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5318187475204468},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4937826097011566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.492603600025177},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.47201651334762573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45060962438583374},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4458179175853729},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4312267303466797},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.41781190037727356},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.348554402589798},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.3462785482406616},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.336142897605896},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.29063040018081665},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11114007234573364}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.802055299282074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763850212097168},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6447314023971558},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6297059059143066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5876193642616272},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5723143219947815},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5506771802902222},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5318187475204468},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4937826097011566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492603600025177},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.47201651334762573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45060962438583374},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4458179175853729},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4312267303466797},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.41781190037727356},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.348554402589798},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3462785482406616},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.336142897605896},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.29063040018081665},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11114007234573364},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459930.3469521","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459930.3469521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W2060300932","https://openalex.org/W2096128575","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2484065175","https://openalex.org/W2493916176","https://openalex.org/W2527795289","https://openalex.org/W2791796577","https://openalex.org/W2806639262","https://openalex.org/W2904450217","https://openalex.org/W2950686248","https://openalex.org/W2952204926"],"related_works":["https://openalex.org/W2896411932","https://openalex.org/W2993300079","https://openalex.org/W3031457336","https://openalex.org/W2734503711","https://openalex.org/W3127787589","https://openalex.org/W4288102732","https://openalex.org/W2949267551","https://openalex.org/W2944092870","https://openalex.org/W3102086967","https://openalex.org/W3189231637"],"abstract_inverted_index":{"Drawing":[0],"from":[1],"the":[2,13,33,65,74,83,134,163,168,202,222,230],"analogy":[3],"between":[4],"natural":[5,19],"language":[6,20],"and":[7,40,161,193,216,236],"\"genomic":[8],"sequence":[9,48],"language\",":[10],"we":[11,109,132],"explored":[12],"applicability":[14],"of":[15,36,67,76,97,225,233],"word":[16,37,53],"embeddings":[17,206],"in":[18,27,38,46,79,90,229,249],"processing":[21],"(NLP)":[22],"to":[23,61,87,123,139,166,242],"represent":[24],"DNA":[25],"reads":[26,187],"Metagenomics":[28],"studies.":[29],"Here,":[30],"k-mer":[31,56,121,141,151,205],"is":[32,58,70,184,240],"equivalent":[34],"concept":[35],"NLP":[39],"it":[41],"has":[42],"been":[43],"widely":[44],"used":[45,210],"analyzing":[47],"data.":[49],"However,":[50],"directly":[51],"replacing":[52],"embedding":[54,57],"with":[55,136,147,188,196],"problematic":[59],"due":[60],"two":[62],"reasons:":[63],"First,":[64],"number":[66,75],"distinct":[68],"k-mers":[69,99,128],"far":[71],"more":[72],"than":[73,175],"different":[77],"words":[78],"our":[80],"vocabulary,":[81],"making":[82],"model":[84,104,113],"too":[85],"huge":[86],"be":[88,208],"stored":[89],"memory.":[91],"Second,":[92],"sequencing":[93,190,198],"errors":[94],"create":[95],"lots":[96],"novel":[98],"(noise),":[100],"which":[101],"significantly":[102],"degrade":[103],"performance.":[105],"In":[106,200],"this":[107],"work,":[108],"introduce":[110],"LSHvec,":[111],"a":[112],"that":[114,150,182,238,246],"leverages":[115],"Locality":[116],"Sensitive":[117],"Hashing":[118],"(LSH)":[119],"for":[120,211],"encoding":[122,152,178],"overcome":[124],"these":[125],"challenges.":[126],"After":[127],"are":[129],"LSH":[130,154],"encoded,":[131],"adopt":[133],"skip-gram":[135],"negative":[137],"sampling":[138],"learn":[140],"embeddings.":[142],"Experiments":[143],"on":[144,186],"metagenomic":[145,213],"datasets":[146,245],"labels":[148],"demonstrate":[149,221],"using":[153,176],"can":[155,207],"not":[156],"only":[157],"accelerate":[158],"training":[159,253],"time":[160],"reduce":[162],"memory":[164],"requirements":[165],"store":[167],"model,":[169],"but":[170],"also":[171],"achieve":[172],"higher":[173],"accuracy":[174],"alternative":[177],"methods.":[179],"We":[180,220],"validate":[181],"LSHvec":[183,226,239],"robust":[185],"high":[189],"error":[191],"rates":[192],"works":[194],"well":[195],"any":[197],"technologies.":[199],"addition,":[201],"trained":[203],"low-dimensional":[204],"potentially":[209],"accurate":[212],"read":[214],"clustering":[215],"taxonomic":[217],"classification.":[218],"Finally,":[219],"unprecedented":[223],"capability":[224],"by":[227],"participating":[228],"second":[231],"round":[232],"CAMI":[234],"challenges":[235],"show":[237],"able":[241],"handle":[243],"metagenome":[244],"exceed":[247],"Terabytes":[248],"size":[250],"through":[251],"distributed":[252],"across":[254],"multiple":[255],"nodes.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-08-16T00:00:00"}