{"id":"https://openalex.org/W3001034374","doi":"https://doi.org/10.1109/tcbb.2020.2968323","title":"Efficient Compression and Indexing for Highly Repetitive DNA Sequence Collections","display_name":"Efficient Compression and Indexing for Highly Repetitive DNA Sequence Collections","publication_year":2020,"publication_date":"2020-01-21","ids":{"openalex":"https://openalex.org/W3001034374","doi":"https://doi.org/10.1109/tcbb.2020.2968323","mag":"3001034374","pmid":"https://pubmed.ncbi.nlm.nih.gov/31985436"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2020.2968323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2968323","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5072102175","display_name":"Hongwei Huo","orcid":"https://orcid.org/0000-0002-5436-1851"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongwei Huo","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-5436-1851","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100463037","display_name":"Xiaoyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Chen","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-2400","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103941606","display_name":"Xu Guo","orcid":"https://orcid.org/0000-0003-3183-6516"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Guo","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003340402","display_name":"Jeffrey Scott Vitter","orcid":"https://orcid.org/0000-0001-7970-6118"},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Scott Vitter","raw_affiliation_strings":["Department of Computer & Information Science, The University of Mississippi, University, MS, USA"],"raw_orcid":"https://orcid.org/0000-0001-7970-6118","affiliations":[{"raw_affiliation_string":"Department of Computer & Information Science, The University of Mississippi, University, MS, USA","institution_ids":["https://openalex.org/I368840534"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072102175"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.6769,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75681914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"6","first_page":"2394","last_page":"2408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9957000017166138,"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/T12029","display_name":"DNA and Biological Computing","score":0.9847999811172485,"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/substring","display_name":"Substring","score":0.8667870759963989},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5783953666687012},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.562828004360199},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.538323163986206},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5031577944755554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4995136260986328},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36929750442504883},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33250153064727783},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15116149187088013},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11527547240257263},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06842881441116333}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8667870759963989},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5783953666687012},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.562828004360199},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.538323163986206},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5031577944755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4995136260986328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36929750442504883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33250153064727783},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15116149187088013},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11527547240257263},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06842881441116333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2020.2968323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2968323","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31985436","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31985436","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1054641142","display_name":"\u5927\u89c4\u6a21\u5e8f\u5217\u6570\u636e\u96c6\u7684\u538b\u7f29\u7d22\u5f15\u4e0e\u641c\u7d22\u7b97\u6cd5\u7814\u7a76","funder_award_id":"61373044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5571002835","display_name":null,"funder_award_id":"61741215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6064937260","display_name":null,"funder_award_id":"CCF-1017623","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1528475610","https://openalex.org/W1647671624","https://openalex.org/W1989227656","https://openalex.org/W1998127289","https://openalex.org/W2000466469","https://openalex.org/W2040818482","https://openalex.org/W2041306584","https://openalex.org/W2046137036","https://openalex.org/W2048491355","https://openalex.org/W2072021854","https://openalex.org/W2093080729","https://openalex.org/W2096258819","https://openalex.org/W2101247207","https://openalex.org/W2101881908","https://openalex.org/W2110553099","https://openalex.org/W2127912200","https://openalex.org/W2131106408","https://openalex.org/W2137892587","https://openalex.org/W2159647614","https://openalex.org/W2159906372","https://openalex.org/W2165255717","https://openalex.org/W2165734724","https://openalex.org/W2170727800","https://openalex.org/W2170899819","https://openalex.org/W2291149938","https://openalex.org/W2295453219","https://openalex.org/W2295471909","https://openalex.org/W2302703011","https://openalex.org/W2547407764","https://openalex.org/W2560975170","https://openalex.org/W2616562168","https://openalex.org/W2951070849","https://openalex.org/W2991364609","https://openalex.org/W6636915900","https://openalex.org/W6660558136","https://openalex.org/W6678795934","https://openalex.org/W6698092701"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W2998448420","https://openalex.org/W1974038726","https://openalex.org/W1953626159","https://openalex.org/W1598224733","https://openalex.org/W4304731099","https://openalex.org/W4280502676","https://openalex.org/W3095240633","https://openalex.org/W75168880","https://openalex.org/W841163430"],"abstract_inverted_index":{"In":[0,197],"this":[1],"paper,":[2],"we":[3,36,199,226],"focus":[4],"upon":[5],"the":[6,78,85,97,104,114,207,214,242,247,260],"important":[7],"problem":[8],"of":[9,24,31,84,107,146],"indexing":[10],"and":[11,113,121,167,213,256],"searching":[12],"highly":[13,236],"repetitive":[14,237],"DNA":[15],"sequence":[16,86],"collections.":[17],"Given":[18],"a":[19,125,201,221],"collection":[20],"<inline-formula><tex-math":[21,25,28,33,39,44,63,73,79,87,100,110,117,122,134,138,147,154,172,176,180,210,217],"notation=\"LaTeX\">$\\mathcal":[22,29,40,64,74,88,111,118,139,148,155,177,181,211,218],"{G}$</tex-math></inline-formula>":[23,41,92,119,152,178,219],"notation=\"LaTeX\">$t$</tex-math></inline-formula>":[26],"sequences":[27,115,215],"{S}_{i}$</tex-math></inline-formula>":[30],"length":[32,133],"notation=\"LaTeX\">$n$</tex-math></inline-formula>":[34],"each,":[35],"can":[37,130,227],"represent":[38],"succinctly":[42],"in":[43,116,153,175,179,216,220,253],"notation=\"LaTeX\">$2n\\mathcal":[45],"{H}_{k}(\\mathcal":[46,75],"{T})":[47],"+":[48,55,59,67,144,159,186],"\\mathcal":[49,91,151],"{O}(n^{\\prime":[50],"}\\":[51],"{\\log":[52,163],"\\log":[53,164,193],"n})":[54],"o(q":[56],"n^{\\prime":[57,69],"})":[58],"o(tn)$</tex-math></inline-formula>":[60],"bits":[61],"using":[62],"{O}(t":[65],"n^{2}":[66],"q":[68],"})$</tex-math></inline-formula>":[70],"time,":[71],"where":[72,171],"{T})$</tex-math></inline-formula>":[76],"is":[77,94,103,124,267],"notation=\"LaTeX\">$k$</tex-math></inline-formula>":[80],"th-order":[81],"empirical":[82],"entropy":[83],"{T}":[89],"\\in":[90,150],"that":[93,246],"used":[95],"as":[96],"reference":[98],"sequence,":[99],"notation=\"LaTeX\">$n^{\\prime":[101],"}$</tex-math></inline-formula>":[102],"total":[105],"number":[106],"variations":[108,208],"between":[109,209],"{T}$</tex-math></inline-formula>":[112,212],",":[120],"notation=\"LaTeX\">$q$</tex-math></inline-formula>":[123],"small":[126],"fixed":[127],"constant.":[128],"We":[129],"restore":[131],"any":[132],"notation=\"LaTeX\">$":[135],"{len}$</tex-math></inline-formula>":[136],"substring":[137],"{S}[":[140],"{sp},":[141],"\\dots,":[142],"{sp}":[143],"{len}-1]$</tex-math></inline-formula>":[145],"{S}":[149],"{O}\\bigl":[156,182],"(n_{s}^{\\prime":[157],"}":[158],"{len}(\\log":[160],"n)^{2}":[161],"/":[162],"n}\\bigr)$</tex-math></inline-formula>":[165],"time":[166,258],"report":[168],"all":[169],"positions":[170],"notation=\"LaTeX\">$P$</tex-math></inline-formula>":[173],"occurs":[174],"(m":[183],"\\cdot":[184,188,190],"t":[185,189],"{occ}":[187],"(\\log":[191],"n)^{2}/\\log":[192],"n":[194],"\\bigr)$</tex-math></inline-formula>":[195],"time.":[196],"addition,":[198],"propose":[200],"dynamic":[202],"programming":[203],"method":[204,249],"to":[205,231],"find":[206],"space-efficient":[222],"way,":[223],"with":[224],"which":[225],"build":[228],"succinct":[229],"structures":[230],"enable":[232],"efficient":[233],"search.":[234],"For":[235],"sequences,":[238],"experimental":[239],"results":[240],"on":[241],"tested":[243],"data":[244],"demonstrate":[245],"proposed":[248],"has":[250],"significant":[251],"advantages":[252],"space":[254],"usage":[255],"retrieval":[257],"over":[259],"current":[261],"state-of-the-art":[262],"methods.":[263],"The":[264],"source":[265],"code":[266],"available":[268],"online.":[269]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}