{"id":"https://openalex.org/W2124636403","doi":"https://doi.org/10.1093/bioinformatics/btn436","title":"Markov model plus <i>k</i>-word distributions: a synergy that produces novel statistical measures for sequence comparison","display_name":"Markov model plus <i>k</i>-word distributions: a synergy that produces novel statistical measures for sequence comparison","publication_year":2008,"publication_date":"2008-08-18","ids":{"openalex":"https://openalex.org/W2124636403","doi":"https://doi.org/10.1093/bioinformatics/btn436","mag":"2124636403","pmid":"https://pubmed.ncbi.nlm.nih.gov/18710871"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn436","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn436","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/20/2296/49052652/bioinformatics_24_20_2296.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/20/2296/49052652/bioinformatics_24_20_2296.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013729700","display_name":"Qi Dai","orcid":"https://orcid.org/0000-0003-2675-6511"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Dai","raw_affiliation_strings":["Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101141379","display_name":"Yanchun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanchun Yang","raw_affiliation_strings":["Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100762627","display_name":"Tianming Wang","orcid":"https://orcid.org/0000-0002-4499-4882"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianming Wang","raw_affiliation_strings":["Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China#TAB#","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013729700"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.1055,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.86988312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"20","first_page":"2296","last_page":"2302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9987000226974487,"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/sequence","display_name":"Sequence (biology)","score":0.7354171276092529},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.610640287399292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5761817693710327},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5501492619514465},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.45952826738357544},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.44944360852241516},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4172385632991791},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38723695278167725},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.37178704142570496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3293548822402954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3265039920806885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12689891457557678},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12099754810333252},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08093109726905823}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7354171276092529},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.610640287399292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5761817693710327},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5501492619514465},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.45952826738357544},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.44944360852241516},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4172385632991791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38723695278167725},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.37178704142570496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3293548822402954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3265039920806885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12689891457557678},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12099754810333252},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08093109726905823},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btn436","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn436","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/20/2296/49052652/bioinformatics_24_20_2296.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18710871","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18710871","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn436","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn436","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/20/2296/49052652/bioinformatics_24_20_2296.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1515594846","https://openalex.org/W1536719366","https://openalex.org/W1583197274","https://openalex.org/W1600463518","https://openalex.org/W1965555277","https://openalex.org/W1969234006","https://openalex.org/W1973243276","https://openalex.org/W1983087557","https://openalex.org/W1985645796","https://openalex.org/W1986908504","https://openalex.org/W1990565597","https://openalex.org/W2008386840","https://openalex.org/W2030609175","https://openalex.org/W2039644197","https://openalex.org/W2041397659","https://openalex.org/W2055043387","https://openalex.org/W2074964509","https://openalex.org/W2086683289","https://openalex.org/W2107430022","https://openalex.org/W2117017773","https://openalex.org/W2118475569","https://openalex.org/W2119488386","https://openalex.org/W2119581562","https://openalex.org/W2121297744","https://openalex.org/W2125598538","https://openalex.org/W2134581361","https://openalex.org/W2137101318","https://openalex.org/W2144575079","https://openalex.org/W2146058063","https://openalex.org/W2146396346","https://openalex.org/W2155653793","https://openalex.org/W2158714788","https://openalex.org/W2161444534","https://openalex.org/W2161865817","https://openalex.org/W2163097179","https://openalex.org/W2166162901","https://openalex.org/W2171963266","https://openalex.org/W2314939711","https://openalex.org/W3199943451","https://openalex.org/W3214380909","https://openalex.org/W4245668478","https://openalex.org/W4298849694","https://openalex.org/W6634860996","https://openalex.org/W6683971125","https://openalex.org/W6800717233"],"related_works":["https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377","https://openalex.org/W2186675474","https://openalex.org/W2387462590","https://openalex.org/W2056274461","https://openalex.org/W2368739446","https://openalex.org/W2010321967"],"abstract_inverted_index":{"MOTIVATION:":[0],"Many":[1],"proposed":[2,68],"statistical":[3,57,132,160],"measures":[4,58,69,133,174],"can":[5],"efficiently":[6],"compare":[7],"biological":[8],"sequences":[9,80,138,147],"to":[10,32,49,134,176],"further":[11],"infer":[12],"their":[13],"structures,":[14],"functions":[15],"and":[16,64,81,88,142],"evolutionary":[17],"information.":[18],"They":[19],"are":[20,183],"related":[21,78,145],"in":[22],"spirit":[23],"because":[24],"all":[25],"the":[26,34,37,86,127],"ideas":[27],"for":[28,59,136,164],"sequence":[29,60],"comparison":[30],"try":[31],"use":[33],"information":[35],"on":[36,76,103],"k-word":[38,47,178],"distributions,":[39],"Markov":[40,50,181],"model":[41,51,182],"or":[42,105],"both.":[43],"Motivated":[44],"by":[45,72],"adding":[46],"distributions":[48,179],"directly,":[52],"we":[53,96],"investigated":[54],"two":[55,112],"novel":[56],"comparison,":[61],"called":[62],"wre.k.r":[63],"S2.k.r.":[65],"RESULTS:":[66],"The":[67,114,151,167],"were":[70],"tested":[71],"similarity":[73,173],"search,":[74],"evaluation":[75],"functionally":[77,144],"regulatory":[79,146],"phylogenetic":[82,165],"analysis.":[83,166],"This":[84],"offers":[85],"systematic":[87],"quantitative":[89],"experimental":[90,168],"assessment":[91,169],"of":[92,130],"our":[93,98,109,131,159,172],"measures.":[94],"Moreover,":[95],"compared":[97],"achievements":[99],"with":[100],"these":[101],"based":[102],"alignment":[104],"alignment-free.":[106],"We":[107],"grouped":[108],"experiments":[110],"into":[111,180],"sets.":[113],"first":[115],"one,":[116],"performed":[117],"via":[118],"ROC":[119],"(receiver":[120],"operating":[121],"curve)":[122],"analysis,":[123],"aims":[124,154],"at":[125,155],"assessing":[126,156],"intrinsic":[128],"ability":[129],"search":[135],"similar":[137],"from":[139,148],"a":[140],"database":[141],"discriminate":[143],"unrelated":[149],"sequences.":[150],"second":[152],"one":[153],"how":[157],"well":[158],"measure":[161],"is":[162],"used":[163],"demonstrates":[170],"that":[171],"intending":[175],"incorporate":[177],"more":[184],"efficient.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}
