{"id":"https://openalex.org/W2014459399","doi":"https://doi.org/10.1089/10665270050081397","title":"Efficient Detection of Unusual Words","display_name":"Efficient Detection of Unusual Words","publication_year":2000,"publication_date":"2000-02-01","ids":{"openalex":"https://openalex.org/W2014459399","doi":"https://doi.org/10.1089/10665270050081397","mag":"2014459399","pmid":"https://pubmed.ncbi.nlm.nih.gov/10890389"},"language":"en","primary_location":{"id":"doi:10.1089/10665270050081397","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270050081397","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","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/A5029039590","display_name":"Alberto Apostolico","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alberto Apostolico","raw_affiliation_strings":["Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova,          Italy","Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova,          Italy","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108798662","display_name":"Mary Ellen Bock","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Ellen Bock","raw_affiliation_strings":["Department of Statistics, Purdue University, West Lafayette, IN 47907"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN 47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042005042","display_name":"Stefano Lonardi","orcid":"https://orcid.org/0000-0002-2696-7274"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefano Lonardi","raw_affiliation_strings":["Department of Computer Sciences, Purdue University, West Lafayette, IN 47907"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, Purdue University, West Lafayette, IN 47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008626237","display_name":"Xuyan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuyan Xu","raw_affiliation_strings":["Department of Computer Sciences, Purdue University, West Lafayette, IN 47907"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, Purdue University, West Lafayette, IN 47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029039590"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.444,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.99092192,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"1-2","first_page":"71","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9962000250816345,"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":0.9936000108718872,"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":0.8393080234527588},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5520800948143005},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5343894958496094},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5325920581817627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5215689539909363},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5098215937614441},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5071835517883301},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4727429151535034},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.46853938698768616},{"id":"https://openalex.org/keywords/multiset","display_name":"Multiset","score":0.46341201663017273},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4608684480190277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.456061989068985},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4533807337284088},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.4252770245075226},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41828426718711853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41718408465385437},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.4105411767959595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28984183073043823},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28621506690979004},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.21822065114974976}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8393080234527588},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5520800948143005},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5343894958496094},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5325920581817627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5215689539909363},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5098215937614441},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5071835517883301},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4727429151535034},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.46853938698768616},{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.46341201663017273},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4608684480190277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.456061989068985},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4533807337284088},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.4252770245075226},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41828426718711853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41718408465385437},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4105411767959595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28984183073043823},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28621506690979004},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.21822065114974976},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D001483","descriptor_name":"Base Sequence","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":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004279","descriptor_name":"DNA, Viral","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004279","descriptor_name":"DNA, Viral","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004279","descriptor_name":"DNA, Viral","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","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":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D018259","descriptor_name":"Herpesvirus 1, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018259","descriptor_name":"Herpesvirus 1, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018259","descriptor_name":"Herpesvirus 1, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1089/10665270050081397","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270050081397","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:10890389","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10890389","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:docs.lib.purdue.edu:cstech-2385","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/cstech/1386","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science Technical Reports","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.8576","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.8576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/~stelo/papers/jcb.pdf","raw_type":"text"},{"id":"pmh:oai:www.research.unipd.it:11577/1363078","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/1363078","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W9273873","https://openalex.org/W1514324498","https://openalex.org/W1523480252","https://openalex.org/W1555430809","https://openalex.org/W1600463518","https://openalex.org/W1655990431","https://openalex.org/W2010808181","https://openalex.org/W2031782198","https://openalex.org/W2032231928","https://openalex.org/W2052890401","https://openalex.org/W2066797099","https://openalex.org/W2070857641","https://openalex.org/W2088082060","https://openalex.org/W2121252285","https://openalex.org/W2126536832","https://openalex.org/W2611477341","https://openalex.org/W2798300693","https://openalex.org/W4298343290"],"related_works":["https://openalex.org/W2070949798","https://openalex.org/W96331545","https://openalex.org/W2102450363","https://openalex.org/W2162655434","https://openalex.org/W2051304374","https://openalex.org/W3022344494","https://openalex.org/W1548907175","https://openalex.org/W1608420182","https://openalex.org/W1882920571","https://openalex.org/W2583658747"],"abstract_inverted_index":{"Words":[0],"that":[1,203,255,277,305,309],"are,":[2],"by":[3,127,182,245],"some":[4,78,171],"measure,":[5],"over-":[6,267],"or":[7,41,97,268],"underrepresented":[8,269],"in":[9,19,48,84,116,122,161,187,212,224,302,311,350],"the":[10,31,66,71,118,167,173,191,195,204,265,274,290,303,312,324,328,362],"context":[11],"of":[12,50,58,69,74,93,148,172,176,190,194,197,209,216,260,282,300,314,327,341,364],"larger":[13],"sequences":[14,124],"have":[15],"been":[16],"variously":[17],"implicated":[18],"biological":[20],"functions":[21],"and":[22,44,52,56,60,81,138,170,207,222,235,343,354,360],"mechanisms.":[23],"In":[24],"most":[25],"approaches":[26],"to":[27,34,86,108,140,273,289,323],"such":[28,79],"anomaly":[29],"detections,":[30],"words":[32,105,270,276,345],"(up":[33],"a":[35,75,90,101,110,128,134,141,162,198,213,246,283,298,307],"certain":[36],"length)":[37],"are":[38,45,125,271],"enumerated":[39],"more":[40,111,332],"less":[42],"exhaustively":[43],"individually":[46],"checked":[47],"terms":[49],"observed":[51],"expected":[53,205,233,263],"frequencies,":[54],"variances,":[55],"scores":[57],"discrepancy":[59],"significance":[61],"thereof.":[62],"Here":[63],"we":[64,201,253,337],"take":[65],"global":[67,339],"approach":[68],"annotating":[70],"suffix":[72,285],"tree":[73,155,329],"sequence":[76,215],"with":[77],"values":[80],"scores,":[82],"having":[83],"mind":[85],"use":[87],"it":[88],"as":[89,100,287],"collective":[91],"detector":[92],"all":[94,210],"unexpected":[95],"behaviors,":[96],"perhaps":[98],"just":[99],"preliminary":[102,365],"filter":[103],"for":[104,166,346],"suspicious":[106],"enough":[107],"undergo":[109],"accurate":[112],"scrutiny.":[113],"We":[114],"consider":[115],"depth":[117],"simple":[119],"probabilistic":[120,348],"model":[121],"which":[123],"produced":[126],"random":[129],"source":[130],"emitting":[131],"symbols":[132,218],"from":[133,262],"known":[135],"alphabet":[136],"independently":[137],"according":[139],"given":[142,214],"distribution.":[143],"Our":[144],"main":[145],"result":[146,179],"consists":[147],"showing":[149],"that,":[150],"within":[151],"this":[152],"model,":[153],"full":[154],"annotations":[156],"can":[157,219],"be":[158,220],"carried":[159],"out":[160],"time-and-space":[163],"optimal":[164],"fashion":[165],"mean,":[168],"variance":[169,208],"adopted":[174],"measures":[175,259],"significance.":[177],"This":[178,294],"is":[180,297,330],"achieved":[181],"an":[183,243,315],"ad":[184],"hoc":[185],"embedding":[186],"statistical":[188],"expressions":[189],"combinatorial":[192],"structure":[193],"periods":[196],"string.":[199],"Specifically,":[200],"show":[202,254],"value":[206],"substrings":[211],"n":[217],"computed":[221],"stored":[223],"(optimal)":[225],"O(n2)":[226],"overall":[227,351],"worst-case,":[228],"O":[229,238],"(n":[230],"log":[231],"n)":[232],"time":[234,240,353],"space.":[236],"The":[237],"(n2)":[239],"bound":[241],"constitutes":[242],"improvement":[244],"linear":[247,352],"factor":[248],"over":[249],"direct":[250],"methods.":[251],"Moreover,":[252],"under":[256],"several":[257],"accepted":[258],"deviation":[261],"frequency,":[264],"candidates":[266],"restricted":[272],"O(n)":[275],"end":[278],"at":[279],"internal":[280],"nodes":[281],"compact":[284],"tree,":[286],"opposed":[288],"theta(n2)":[291],"possible":[292],"substrings.":[293],"surprising":[295],"fact":[296],"consequence":[299],"properties":[301],"form":[304],"if":[306],"word":[308],"ends":[310],"middle":[313],"arc":[316],"is,":[317],"say,":[318],"overrepresented,":[319],"then":[320],"its":[321],"extension":[322],"nearest":[325],"node":[326],"even":[331],"so.":[333],"Based":[334],"on":[335],"this,":[336],"design":[338],"detectors":[340],"favored":[342],"unfavored":[344],"our":[347],"framework":[349],"space,":[355],"discuss":[356],"related":[357],"software":[358],"implementations":[359],"display":[361],"results":[363],"experiments.":[366]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}