{"id":"https://openalex.org/W4400678885","doi":"https://doi.org/10.1093/bioinformatics/btae452","title":"HyperGen: compact and efficient genome sketching using hyperdimensional vectors","display_name":"HyperGen: compact and efficient genome sketching using hyperdimensional vectors","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4400678885","doi":"https://doi.org/10.1093/bioinformatics/btae452","pmid":"https://pubmed.ncbi.nlm.nih.gov/39012512"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae452","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae452","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae452/58662658/btae452.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/40/7/btae452/58662658/btae452.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039571679","display_name":"Weihong Xu","orcid":"https://orcid.org/0000-0003-3766-3353"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weihong Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States"],"raw_orcid":"https://orcid.org/0000-0003-3766-3353","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051610657","display_name":"Po\u2010Kai Hsu","orcid":"https://orcid.org/0000-0001-7265-7077"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Kai Hsu","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, GA 30332, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, GA 30332, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008998282","display_name":"Niema Moshiri","orcid":"https://orcid.org/0000-0003-2209-8128"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niema Moshiri","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054894631","display_name":"Shimeng Yu","orcid":"https://orcid.org/0000-0002-0068-3652"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shimeng Yu","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, GA 30332, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, GA 30332, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112841571","display_name":"Tajana Rosing","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tajana Rosing","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California San Diego , La Jolla, CA 92093, United States","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039571679"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.8999,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85972322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"40","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9007999897003174,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9007999897003174,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.015200000256299973,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/computer-science","display_name":"Computer science","score":0.7128730416297913},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.57813560962677},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5467485189437866},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5293610692024231},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.524722158908844},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47149819135665894},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46997660398483276},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4118436574935913},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35884177684783936},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19049140810966492},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12777692079544067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128730416297913},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.57813560962677},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5467485189437866},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5293610692024231},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.524722158908844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47149819135665894},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46997660398483276},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4118436574935913},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35884177684783936},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19049140810966492},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12777692079544067},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae452","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae452","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae452/58662658/btae452.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:39012512","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39012512","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:escholarship.org:ark:/13030/qt41z9t2qk","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/41z9t2qk","pdf_url":"https://escholarship.org/content/qt41z9t2qk/qt41z9t2qk.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Computer applications in the biosciences : CABIOS, vol 40, iss 7","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11281827","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11281827","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11281827/pdf/btae452.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae452","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae452","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/7/btae452/58662658/btae452.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":[{"id":"https://openalex.org/G2200512414","display_name":null,"funder_award_id":"CCF-2112665","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400678885.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2070862086","https://openalex.org/W2104846587","https://openalex.org/W2105805010","https://openalex.org/W2107282968","https://openalex.org/W2124509324","https://openalex.org/W2155628349","https://openalex.org/W2206071891","https://openalex.org/W2519890620","https://openalex.org/W2753961085","https://openalex.org/W2884834061","https://openalex.org/W2889019390","https://openalex.org/W2950150251","https://openalex.org/W2951254987","https://openalex.org/W2952609831","https://openalex.org/W2987650093","https://openalex.org/W2992400060","https://openalex.org/W3019706413","https://openalex.org/W3036399271","https://openalex.org/W3118593453","https://openalex.org/W3198289887","https://openalex.org/W4206102744","https://openalex.org/W4226052879","https://openalex.org/W4241006348","https://openalex.org/W4289538051","https://openalex.org/W4304481015","https://openalex.org/W4317625860","https://openalex.org/W4376132205","https://openalex.org/W4381489623","https://openalex.org/W4382198841","https://openalex.org/W4383313785","https://openalex.org/W4386738327","https://openalex.org/W4386923678","https://openalex.org/W6806416903","https://openalex.org/W6854068008","https://openalex.org/W6854284202"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"MOTIVATION:":[0],"Genomic":[1],"distance":[2],"estimation":[3,107,124,149,179,217],"is":[4,27,96,171,194,227],"a":[5,28,140],"critical":[6],"workload":[7],"since":[8],"exact":[9],"computation":[10],"for":[11,59,104,150,200],"whole-genome":[12],"similarity":[13,36],"metrics":[14],"such":[15],"as":[16,234],"Average":[17],"Nucleotide":[18],"Identity":[19],"(ANI)":[20],"incurs":[21],"prohibitive":[22],"runtime":[23,54],"overhead.":[24],"Genome":[25],"sketching":[26,66,146,158,203],"fast":[29],"and":[30,56,98,147,159,181,204],"memory-efficient":[31,210],"solution":[32],"to":[33,84,173,184,243],"estimate":[34],"ANI":[35,61,106,123,148,178,216],"by":[37],"distilling":[38],"representative":[39],"k-mers":[40],"from":[41,131],"the":[42,79,115,144,197,231,245],"original":[43],"sequences.":[44],"In":[45,113],"this":[46],"work,":[47],"we":[48],"present":[49],"HyperGen":[50,77,120,142,170,193,208,226],"that":[51,68,192],"improves":[52],"accuracy,":[53],"performance,":[55],"memory":[57],"efficiency":[58],"large-scale":[60],"estimation.":[62],"Unlike":[63],"existing":[64],"genome":[65,71,152,165,202],"algorithms":[67],"convert":[69],"large":[70],"files":[72,212],"into":[73,87],"discrete":[74],"k-mer":[75],"hashes,":[76],"leverages":[78],"emerging":[80],"hyperdimensional":[81],"computing":[82],"(HDC)":[83],"encode":[85],"genomes":[86],"quasi-orthogonal":[88],"vectors":[89],"(Hypervector,":[90],"HV)":[91],"in":[92,119],"high-dimensional":[93],"space.":[94],"HV":[95,116],"compact":[97],"can":[99,248],"preserve":[100],"more":[101],"information,":[102],"allowing":[103],"accurate":[105],"while":[108,213],"reducing":[109],"required":[110],"sketch":[111,117,211],"sizes.":[112],"particular,":[114],"representation":[118],"allows":[121],"efficient":[122,145],"using":[125,163],"vector":[126],"multiplication,":[127],"which":[128],"naturally":[129],"benefits":[130],"highly":[132],"optimized":[133],"general":[134],"matrix":[135],"multiply":[136],"(GEMM)":[137],"routines.":[138],"As":[139],"result,":[141],"enables":[143],"massive":[151],"collections.":[153],"RESULTS:":[154],"We":[155],"evaluate":[156],"HyperGen's":[157],"database":[160,205],"search":[161],"performance":[162],"several":[164],"datasets":[166],"at":[167,239,251],"various":[168],"scales.":[169],"able":[172],"achieve":[174],"comparable":[175],"or":[176],"superior":[177],"error":[180],"linearity":[182],"compared":[183],"other":[185],"sketch-based":[186],"counterparts.":[187],"The":[188,241],"measurement":[189],"results":[190,247],"show":[191],"one":[195],"of":[196,225],"fastest":[198],"tools":[199],"both":[201],"search.":[206],"Meanwhile,":[207],"produces":[209],"ensuring":[214],"high":[215],"accuracy.":[218],"AVAILABILITY":[219],"AND":[220],"IMPLEMENTATION:":[221],"A":[222],"Rust":[223],"implementation":[224],"freely":[228],"available":[229],"under":[230],"MIT":[232],"license":[233],"an":[235],"open-source":[236],"software":[237],"project":[238],"https://github.com/wh-xu/Hyper-Gen.":[240],"scripts":[242],"reproduce":[244],"experimental":[246],"be":[249],"accessed":[250],"https://github.com/wh-xu/experiment-hyper-gen.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}