{"id":"https://openalex.org/W2567311044","doi":"https://doi.org/10.1093/bioinformatics/btw699","title":"Statistical significance based on length and position of the local score in a model of i.i.d. sequences","display_name":"Statistical significance based on length and position of the local score in a model of i.i.d. sequences","publication_year":2016,"publication_date":"2016-11-08","ids":{"openalex":"https://openalex.org/W2567311044","doi":"https://doi.org/10.1093/bioinformatics/btw699","mag":"2567311044","pmid":"https://pubmed.ncbi.nlm.nih.gov/28035025"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw699","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw699","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/5/654/25148440/btw699.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/33/5/654/25148440/btw699.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010749331","display_name":"Agn\u00e8s Lagnoux","orcid":"https://orcid.org/0000-0002-6841-5814"},"institutions":[{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I84500057","display_name":"Institut de Math\u00e9matiques de Toulouse","ror":"https://ror.org/014vp6c30","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I196454796","https://openalex.org/I4210092408","https://openalex.org/I4210126056","https://openalex.org/I4210141950","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I84500057"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Agn\u00e8s Lagnoux","raw_affiliation_strings":["Institut de Math\u00e9matiques de Toulouse, UMR5219, Universit\u00e9 de Toulouse 2 Jean Jaur\u00e8s, 5 all\u00e9es Antonio Machado, Toulouse, Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Math\u00e9matiques de Toulouse, UMR5219, Universit\u00e9 de Toulouse 2 Jean Jaur\u00e8s, 5 all\u00e9es Antonio Machado, Toulouse, Cedex, France","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I84500057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016754365","display_name":"Sabine Mercier","orcid":"https://orcid.org/0000-0002-1820-6889"},"institutions":[{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I84500057","display_name":"Institut de Math\u00e9matiques de Toulouse","ror":"https://ror.org/014vp6c30","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I196454796","https://openalex.org/I4210092408","https://openalex.org/I4210126056","https://openalex.org/I4210141950","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I84500057"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sabine Mercier","raw_affiliation_strings":["Institut de Math\u00e9matiques de Toulouse, UMR5219, Universit\u00e9 de Toulouse 2 Jean Jaur\u00e8s, 5 all\u00e9es Antonio Machado, Toulouse, Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Math\u00e9matiques de Toulouse, UMR5219, Universit\u00e9 de Toulouse 2 Jean Jaur\u00e8s, 5 all\u00e9es Antonio Machado, Toulouse, Cedex, France","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I84500057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104752581","display_name":"Pierre Vallois","orcid":"https://orcid.org/0000-0002-2123-0142"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I3017839442","display_name":"Institut \u00c9lie Cartan de Lorraine","ror":"https://ror.org/04rvw8791","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I3017839442","https://openalex.org/I4210141950","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Vallois","raw_affiliation_strings":["Institut Elie Cartan, UMR7502 CNRS, INRIA-BIGS, Universit\u00e9 de Lorraine, Vandoeuvre-l\u00e8s-Nancy Cedex, France","Biology, genetics and statistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Elie Cartan, UMR7502 CNRS, INRIA-BIGS, Universit\u00e9 de Lorraine, Vandoeuvre-l\u00e8s-Nancy Cedex, France","institution_ids":["https://openalex.org/I3017839442","https://openalex.org/I1326498283","https://openalex.org/I90183372","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Biology, genetics and statistics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.3482,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70055689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"5","first_page":"654","last_page":"660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.30640000104904175,"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":0.30640000104904175,"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/T10885","display_name":"Gene expression and cancer classification","score":0.09179999679327011,"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/T13500","display_name":"Probability and Statistical Research","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6707803606987},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.634257972240448},{"id":"https://openalex.org/keywords/goodness-of-fit","display_name":"Goodness of fit","score":0.6305491924285889},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5716328024864197},{"id":"https://openalex.org/keywords/score","display_name":"Score","score":0.5327218770980835},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5003604888916016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48139312863349915},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4546833038330078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45126062631607056},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4468492269515991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38453832268714905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33567529916763306},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10894408822059631},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.0966392457485199}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6707803606987},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.634257972240448},{"id":"https://openalex.org/C132480984","wikidata":"https://www.wikidata.org/wiki/Q2034239","display_name":"Goodness of fit","level":2,"score":0.6305491924285889},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5716328024864197},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.5327218770980835},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5003604888916016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48139312863349915},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4546833038330078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45126062631607056},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4468492269515991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38453832268714905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33567529916763306},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10894408822059631},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.0966392457485199},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018709","descriptor_name":"Statistics, Nonparametric","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018709","descriptor_name":"Statistics, Nonparametric","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018709","descriptor_name":"Statistics, Nonparametric","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btw699","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw699","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/5/654/25148440/btw699.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:28035025","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28035025","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},{"id":"pmh:oai:HAL:hal-01301246v2","is_oa":true,"landing_page_url":"https://hal.science/hal-01301246","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2017, 33 (5), pp.654-660. ⟨10.1093/bioinformatics/btw699⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw699","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw699","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/5/654/25148440/btw699.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2567311044.pdf","grobid_xml":"https://content.openalex.org/works/W2567311044.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1548843388","https://openalex.org/W1555619877","https://openalex.org/W1600463518","https://openalex.org/W1944595174","https://openalex.org/W1968363797","https://openalex.org/W1972571116","https://openalex.org/W1975304761","https://openalex.org/W1982944739","https://openalex.org/W2018468534","https://openalex.org/W2031085230","https://openalex.org/W2034052397","https://openalex.org/W2034123395","https://openalex.org/W2037789468","https://openalex.org/W2039666964","https://openalex.org/W2040157033","https://openalex.org/W2041397659","https://openalex.org/W2041976742","https://openalex.org/W2054111854","https://openalex.org/W2055043387","https://openalex.org/W2066597806","https://openalex.org/W2069315666","https://openalex.org/W2085270174","https://openalex.org/W2094519647","https://openalex.org/W2132885727","https://openalex.org/W2145293832","https://openalex.org/W2147580512","https://openalex.org/W2153967340","https://openalex.org/W2155395626","https://openalex.org/W2222124350","https://openalex.org/W2531690742","https://openalex.org/W4247984180","https://openalex.org/W4320858973","https://openalex.org/W6660226927","https://openalex.org/W6660917627","https://openalex.org/W6663924171","https://openalex.org/W6763745462"],"related_works":["https://openalex.org/W1541538682","https://openalex.org/W3004218185","https://openalex.org/W2955895218","https://openalex.org/W4390241083","https://openalex.org/W4245457074","https://openalex.org/W2323735050","https://openalex.org/W2097522327","https://openalex.org/W2347733609","https://openalex.org/W2050686036","https://openalex.org/W2912990606"],"abstract_inverted_index":{"Motivation:":[0],"The":[1],"local":[2,40,68,76,90],"score":[3,41,69,77],"of":[4,24,35,53,62,84],"a":[5,10,50],"biological":[6,17],"sequence":[7,86],"analysis":[8],"is":[9,27],"mathematical":[11],"tool":[12],"largely":[13],"used":[14],"to":[15,88],"analyse":[16],"sequences.":[18],"Consequently,":[19],"determining":[20],"an":[21],"accurate":[22],"estimation":[23],"its":[25],"distribution":[26,42],"crucial.":[28],"Results:":[29],"First,":[30],"we":[31,57,80],"study":[32,81],"the":[33,39,60,63,67,71,85,89],"accuracy":[34],"classical":[36,72],"results":[37],"on":[38,75],"in":[43],"independent":[44],"and":[45],"identically":[46],"distributed":[47],"model":[48],"using":[49],"Kolmogorov-Smirnov":[51],"goodness":[52],"fit":[54],"test.":[55],"Second,":[56],"highlight":[58],"how":[59],"length":[61],"segment":[64],"that":[65],"realizes":[66],"improves":[70],"setting":[73],"based":[74],"only.":[78],"Finally,":[79],"which":[82],"part":[83],"contributes":[87],"score.":[91],"Contact:":[92],"mercier@univ-tlse2.fr.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}