{"id":"https://openalex.org/W7131432636","doi":"https://doi.org/10.1109/icdm65498.2025.00095","title":"Effective and Efficient Similarity Search for DNA Sequences Through de Bruijn Sum Graph Embedding","display_name":"Effective and Efficient Similarity Search for DNA Sequences Through de Bruijn Sum Graph Embedding","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7131432636","doi":"https://doi.org/10.1109/icdm65498.2025.00095"},"language":null,"primary_location":{"id":"doi:10.1109/icdm65498.2025.00095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","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/A5069100479","display_name":"Zhaochong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaochong Yu","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126841109","display_name":"Zihang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Yang","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102823200","display_name":"Chris Ding","orcid":"https://orcid.org/0009-0009-3374-1941"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chris Ding","raw_affiliation_strings":["College of Data Science, The Chinese University of Hong Kong,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Data Science, The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041571735","display_name":"Chao Zeng","orcid":"https://orcid.org/0000-0003-4889-5731"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chao Zeng","raw_affiliation_strings":["Waseda University,Faculty of Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Faculty of Science and Engineering","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102135480","display_name":"Feijuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164332","display_name":"Shenzhen Second People's Hospital","ror":"https://ror.org/05c74bq69","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210164332"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feijuan Huang","raw_affiliation_strings":["Hospital of Shenzhen University, Shenzhen Second People's Hospital, Medical Innovation Technology Transformation Center of Shenzhen Second People's Hospital, Shenzhen University, Shenzhen Translational Medicine Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hospital of Shenzhen University, Shenzhen Second People's Hospital, Medical Innovation Technology Transformation Center of Shenzhen Second People's Hospital, Shenzhen University, Shenzhen Translational Medicine Institute","institution_ids":["https://openalex.org/I4210164332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123674053","display_name":"Yuanzhe Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhe Cai","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"873","last_page":"882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.7638999819755554,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.7638999819755554,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.053199999034404755,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.0502999983727932,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.6988999843597412},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.6322000026702881},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5108000040054321},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/bit-array","display_name":"Bit array","score":0.4523000121116638},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4415999948978424},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4293999969959259},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.40369999408721924},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.375}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.6988999843597412},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5108000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47209998965263367},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C150807984","wikidata":"https://www.wikidata.org/wiki/Q1992074","display_name":"Bit array","level":3,"score":0.4523000121116638},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4036000072956085},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.375},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C46011968","wikidata":"https://www.wikidata.org/wiki/Q830527","display_name":"Best-first search","level":4,"score":0.33730000257492065},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm65498.2025.00095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm65498.2025.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2015292449","https://openalex.org/W2034337154","https://openalex.org/W2041391522","https://openalex.org/W2087064593","https://openalex.org/W2142678478","https://openalex.org/W2154851992","https://openalex.org/W2157539385","https://openalex.org/W2170551349","https://openalex.org/W2611554670","https://openalex.org/W2789843538","https://openalex.org/W2950954328","https://openalex.org/W2962756421","https://openalex.org/W2962807110","https://openalex.org/W2963469388","https://openalex.org/W2970298096","https://openalex.org/W2971559821","https://openalex.org/W2998702515","https://openalex.org/W3029205155","https://openalex.org/W3092136311","https://openalex.org/W3099584446","https://openalex.org/W3105816068","https://openalex.org/W3127238141","https://openalex.org/W3131334373","https://openalex.org/W3136521802","https://openalex.org/W3196481040","https://openalex.org/W4206471648","https://openalex.org/W4225328503","https://openalex.org/W4242221364","https://openalex.org/W4281253663","https://openalex.org/W4293430819","https://openalex.org/W4294591310","https://openalex.org/W4306317682","https://openalex.org/W4384341779","https://openalex.org/W4404821554","https://openalex.org/W4406419344"],"related_works":[],"abstract_inverted_index":{"Similarity":[0],"search":[1,40,58,151,195,207],"of":[2,86,96],"DNA":[3,31,57,88],"sequences":[4],"is":[5,82,232],"widely":[6],"used":[7],"in":[8,68,109,163,184,234],"many":[9],"genomic":[10],"analyses,":[11],"such":[12],"as":[13,66],"pathogen":[14],"detection,":[15],"gene":[16],"function":[17],"annotation,":[18],"and":[19,29,37,55,100,211],"evolutionary":[20],"relationship":[21],"discovery.":[22],"Today,":[23],"sequencing":[24],"technologies":[25],"are":[26],"generating":[27],"more":[28,30,35,182],"sequences.":[32],"This":[33,70],"requires":[34],"accurate":[36,54],"efficient":[38,56],"sequence":[39,47,118,141],"methods":[41],"that":[42,60,189],"scale":[43],"well":[44,62],"to":[45,63,104,120,144,198,203,209],"large":[46,64],"databases.":[48],"Here,":[49],"we":[50],"present":[51],"a":[52,83,102,121,130,145,153,224],"new":[53],"algorithm":[59,71],"scales":[61],"data":[65,155,226],"shown":[67],"experiments.":[69],"involves":[72],"three":[73],"innovative":[74],"techniques:":[75],"(i)":[76,193],"de":[77,124],"Bruijn":[78,125],"sum":[79,126],"graph,":[80,127],"which":[81,128,157],"natural":[84],"representation":[85],"multiple":[87],"sequences,":[89],"(ii)":[90,205],"sampling":[91,112],"from":[92,133],"equilibrium":[93],"distribution":[94],"instead":[95],"traditional":[97],"uniform":[98],"distribution,":[99],"(iii)":[101,212],"technique":[103],"solve":[105],"the":[106,114,134,149,164],"sink":[107],"difficulty":[108],"random":[110],"walk":[111],"on":[113,123,223],"directed":[115],"graph.":[116],"A":[117,139],"corresponds":[119,143],"path":[122,135],"generates":[129],"vector":[131,146,154,165],"pooled":[132],"node":[136],"embedding":[137],"vectors.":[138],"query":[140],"similarly":[142],"embedding.":[147,230],"Thus,":[148],"similarity":[150],"becomes":[152],"search,":[156],"can":[158],"be":[159],"implemented":[160],"very":[161],"efficiently":[162],"database.":[166],"We":[167],"compare":[168],"our":[169,190],"implementation":[170,191],"with":[171],"MMseqs2":[172],"(the":[173,177],"most":[174],"accurate),":[175],"Bowtie2":[176],"fastest),":[178],"DNA2Vec,":[179],"etc":[180],"(see":[181],"details":[183],"experiments).":[185],"Extensive":[186],"experiments":[187],"show":[188],"achieves":[192],"superior":[194],"accuracy":[196,201],"(up":[197],"3.5%":[199],"Top-1":[200],"improvement)":[202],"MMseqs2,":[204],"comparable":[206],"speed":[208],"Bowtie2,":[210],"26.5":[213],"times":[214],"faster":[215],"than":[216],"DNA2Vec":[217],"(146":[218],"min":[219],"vs.":[220],"3,869":[221],"min)":[222],"32GB":[225],"for":[227],"learning":[228],"k-mer":[229],"Code":[231],"provided":[233],"https://github.com/caiyuanzhe/SeqGraph2Vec/.":[235]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-26T00:00:00"}