{"id":"https://openalex.org/W1602255397","doi":null,"title":"Compression of strings with approximate repeats.","display_name":"Compression of strings with approximate repeats.","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W1602255397","mag":"1602255397","pmid":"https://pubmed.ncbi.nlm.nih.gov/9783204"},"language":"en","primary_location":{"id":"pmid:9783204","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9783204","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,"listed_in":[],"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":"Proceedings. International Conference on Intelligent Systems for Molecular Biology","raw_type":"Journal Article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["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/A5065385022","display_name":"Lloyd Allison","orcid":"https://orcid.org/0000-0002-9020-3164","observed_orcids":["https://orcid.org/0000-0002-9020-3164"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"L Allison","raw_affiliation_strings":["School of Computer Science and Software Engineering, Monash University, Australia. lloyd,time,trevor@cs.monash.edu.au"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Monash University, Australia. lloyd,time,trevor@cs.monash.edu.au","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083460367","display_name":"Timothy C Edgoose","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T Edgoose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110209287","display_name":"Trevor I. Dix","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T I Dix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.178,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.85483871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"8","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00019999999494757503,"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":0.0,"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/string-compression","display_name":"string compression","score":0.9549999833106995},{"id":"https://openalex.org/keywords/dna-sequence-analysis","display_name":"DNA sequence analysis","score":0.5329999923706055},{"id":"https://openalex.org/keywords/expectation-maximization-estimation","display_name":"expectation-maximization estimation","score":0.6570000052452087},{"id":"https://openalex.org/keywords/approximate-algorithms","display_name":"approximate algorithms","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9743244051933289},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7505754232406616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5178656578063965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49039602279663086},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.4538215398788452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42449167370796204},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4196435511112213},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4140547811985016},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.19858914613723755},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13709154725074768},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005914","descriptor_name":"Globins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010947","descriptor_name":"Plants, Toxic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011338","descriptor_name":"Probability Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012091","descriptor_name":"Repetitive Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014026","descriptor_name":"Nicotiana","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017344","descriptor_name":"Genes, Insect","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018744","descriptor_name":"DNA, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":4,"locations":[{"id":"pmid:9783204","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9783204","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,"listed_in":[],"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":"Proceedings. International Conference on Intelligent Systems for Molecular Biology","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.5170","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.5170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csse.monash.edu.au/~lloyd/tildeStrings/Compress/1998ISMB.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.506.4154","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.506.4154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/ISMB/1998/ISMB98-002.pdf","raw_type":"text"},{"id":"mag:1602255397","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9783204","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W162171762","https://openalex.org/W170307911","https://openalex.org/W180026964","https://openalex.org/W1894205160","https://openalex.org/W1969678783","https://openalex.org/W1970231722","https://openalex.org/W1985105823","https://openalex.org/W1999905104","https://openalex.org/W2005097301","https://openalex.org/W2010961546","https://openalex.org/W2014753445","https://openalex.org/W2044532497","https://openalex.org/W2049633694","https://openalex.org/W2068448872","https://openalex.org/W2077574412","https://openalex.org/W2077770566","https://openalex.org/W2085668020","https://openalex.org/W2086699924","https://openalex.org/W2089319476","https://openalex.org/W2107745473","https://openalex.org/W2108808477","https://openalex.org/W2110381504","https://openalex.org/W2114953535","https://openalex.org/W2124871568","https://openalex.org/W2135625884","https://openalex.org/W2151325537"],"related_works":["https://openalex.org/W2124871568","https://openalex.org/W2144514096","https://openalex.org/W2108278098","https://openalex.org/W7099256532","https://openalex.org/W2114953535","https://openalex.org/W7098686002","https://openalex.org/W7097061614","https://openalex.org/W3213273699","https://openalex.org/W7097468692","https://openalex.org/W1585379378"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,21,49,91,120,135,143],"model":[3,16,76,89,151],"for":[4,41,48,130],"strings":[5,131],"of":[6,39,82,94,112,132,138,140,169],"characters":[7,141],"that":[8,20],"is":[9,34,128,147,152],"loosely":[10],"based":[11],"on":[12],"the":[13,18,30,37,53,69,75,80,83,86,102,113,167],"Lempel":[14],"Ziv":[15],"with":[17],"addition":[19],"repeated":[22],"substring":[23],"can":[24,98],"be":[25,99],"an":[26,106],"approximate":[27,157],"match":[28],"to":[29,36,63,155,177],"original":[31],"substring;":[32],"this":[33,78],"close":[35],"situation":[38],"DNA,":[40],"example.":[42],"Typically":[43],"there":[44],"are":[45,123],"many":[46,58],"explanations":[47,73],"given":[50,103],"string":[51,104],"under":[52,74,85],"model,":[54],"some":[55],"optimal":[56,65],"and":[57,96,119,142,175],"suboptimal.":[59],"Rather":[60],"than":[61,134],"commit":[62],"one":[64],"explanation,":[66],"we":[67],"sum":[68],"probabilities":[70],"over":[71],"all":[72],"because":[77],"gives":[79],"probability":[81],"data":[84],"model.":[87],"The":[88,150],"has":[90],"small":[92],"number":[93],"parameters":[95],"these":[97],"estimated":[100],"from":[101,172],"by":[105],"expectation-maximization":[107],"(EM)":[108],"algorithm.":[109],"Each":[110],"iteration":[111],"EM":[114],"algorithm":[115,146],"takes":[116],"O(n2)":[117,126],"time":[118],"few":[121,136],"iterations":[122],"typically":[124],"sufficient.":[125],"complexity":[127],"impractical":[129],"more":[133],"tens":[137],"thousands":[139],"faster":[144],"approximation":[145],"also":[148],"given.":[149],"further":[153],"extended":[154],"include":[156,166],"reverse":[158],"complementary":[159],"repeats":[160],"when":[161],"analyzing":[162],"DNA":[163,179],"strings.":[164,180],"Tests":[165],"recovery":[168],"parameter":[170],"estimates":[171],"known":[173],"sources":[174],"applications":[176],"real":[178]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}