{"id":"https://openalex.org/W7124144263","doi":"https://doi.org/10.1109/icpads67057.2025.11323030","title":"GTree: A Trie-Based Alignment-Free Clustering Framework for Efficient DNA Data Storage and Enhanced Error Resilience","display_name":"GTree: A Trie-Based Alignment-Free Clustering Framework for Efficient DNA Data Storage and Enhanced Error Resilience","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124144263","doi":"https://doi.org/10.1109/icpads67057.2025.11323030"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5123002780","display_name":"Linxuan Han","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linxuan Han","raw_affiliation_strings":["Tianjin University,Center for Applied Mathematics,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Center for Applied Mathematics,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040998243","display_name":"Guanjin Qu","orcid":"https://orcid.org/0000-0002-3475-1975"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjin Qu","raw_affiliation_strings":["Tianjin University,Center for Applied Mathematics,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Center for Applied Mathematics,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027889798","display_name":"Zihui Yan","orcid":"https://orcid.org/0000-0002-3229-0204"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210089468","display_name":"Tianjin Synthetic Material Research Institute (China)","ror":"https://ror.org/005n4dc83","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089468"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihui Yan","raw_affiliation_strings":["School of Synthetic Biology and Biomanufacturing, Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Synthetic Biology and Biomanufacturing, Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743","https://openalex.org/I4210089468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121573968","display_name":"Huaming Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaming Wu","raw_affiliation_strings":["Tianjin University,Center for Applied Mathematics,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Center for Applied Mathematics,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.4934000074863434,"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/T12029","display_name":"DNA and Biological Computing","score":0.4934000074863434,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.16110000014305115,"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":0.04050000011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7490000128746033},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.48240000009536743},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.424699991941452},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.39660000801086426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616999745368958},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7490000128746033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5231999754905701},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.48240000009536743},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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":17,"referenced_works":["https://openalex.org/W1977556410","https://openalex.org/W2025383314","https://openalex.org/W2116699248","https://openalex.org/W2145853890","https://openalex.org/W2156125289","https://openalex.org/W2162980030","https://openalex.org/W2592122940","https://openalex.org/W2788257106","https://openalex.org/W2944582089","https://openalex.org/W2950589160","https://openalex.org/W3001660245","https://openalex.org/W3093968171","https://openalex.org/W3159176552","https://openalex.org/W4292092908","https://openalex.org/W4295453817","https://openalex.org/W4383955088","https://openalex.org/W4394997720"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,58,62,65,124,139,147],"rapid":[2],"advancements":[3],"in":[4,54,64,138],"information":[5],"technologies,":[6],"global":[7],"data":[8,16,91],"volumes":[9],"have":[10],"increased":[11],"exponentially.":[12],"Deoxyribonucleic":[13],"acid":[14],"(DNA)-based":[15],"storage":[17,26],"has":[18],"gained":[19],"significant":[20],"attention":[21],"due":[22],"to":[23,33,74,121,134],"its":[24,162],"superior":[25,163],"capacity":[27],"and":[28,51,98,115,158],"long-term":[29],"preservation":[30],"potential":[31],"compared":[32],"traditional":[34],"media.":[35],"However,":[36],"during":[37],"this":[38,78],"process,":[39],"DNA":[40,66,85,90],"sequences":[41,63],"may":[42],"be":[43],"affected":[44],"by":[45],"errors":[46],"such":[47],"as":[48],"deletions,":[49],"insertions,":[50],"substitutions,":[52],"resulting":[53],"altered":[55],"copies":[56],"of":[57,141,149],"original":[59],"sequence.":[60],"Furthermore,":[61],"pool":[67],"lack":[68],"inherent":[69],"order,":[70],"preventing":[71],"direct":[72],"access":[73],"specific":[75],"fragments.":[76],"In":[77],"paper,":[79],"we":[80,145],"propose":[81],"GTree,":[82],"a":[83,104],"trie-based":[84],"clustering":[86,136,152],"framework":[87],"tailored":[88],"for":[89],"storage.":[92],"GTree":[93,150],"achieves":[94],"both":[95,155],"high":[96],"accuracy":[97],"low":[99],"runtime":[100],"complexity.":[101],"It":[102],"introduces":[103],"lightweight":[105],"pre-screening":[106],"module":[107],"that":[108],"combines":[109],"Q-gram":[110],"feature":[111],"extraction,":[112],"MinHash":[113],"signatures,":[114],"Locality":[116],"Sensitive":[117],"Hashing":[118],"(LSH)":[119],"indexing":[120],"efficiently":[122],"reduce":[123],"comparison":[125],"space.":[126],"A":[127],"majority-label":[128],"voting":[129],"mechanism":[130],"is":[131],"also":[132],"integrated":[133],"enhance":[135],"robustness":[137],"presence":[140],"sequencing":[142],"errors.":[143],"Finally,":[144],"validate":[146],"performance":[148],"through":[151],"experiments":[153],"on":[154],"real":[156],"biological":[157],"simulated":[159],"datasets,":[160],"demonstrating":[161],"performance.":[164]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-15T00:00:00"}
