{"id":"https://openalex.org/W2126198043","doi":"https://doi.org/10.1093/bioinformatics/bth266","title":"How independent are the appearances of n-mers in different genomes?","display_name":"How independent are the appearances of n-mers in different genomes?","publication_year":2004,"publication_date":"2004-04-15","ids":{"openalex":"https://openalex.org/W2126198043","doi":"https://doi.org/10.1093/bioinformatics/bth266","mag":"2126198043","pmid":"https://pubmed.ncbi.nlm.nih.gov/15087315"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth266","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/15/2421/48906008/bioinformatics_20_15_2421.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/15/2421/48906008/bioinformatics_20_15_2421.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027121994","display_name":"Yuriy Fofanov","orcid":"https://orcid.org/0000-0003-4240-4313"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuriy Fofanov","raw_affiliation_strings":["Department of Computer Science, University of Houston, TX 77204-3010, USA. yfofanov@uh.edu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, TX 77204-3010, USA. yfofanov@uh.edu","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101088178","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-0005-7723"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011406637","display_name":"Charles Katili","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Katili","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065149831","display_name":"Jim J. Wang","orcid":"https://orcid.org/0000-0001-5082-8234"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jim Wang","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060154155","display_name":"Yuri Belosludtsev","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuri Belosludtsev","raw_affiliation_strings":["Vitruvius Biosciences, The Woodlands, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Vitruvius Biosciences, The Woodlands, TX, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053078595","display_name":"Thomas F. Powdrill","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Powdrill","raw_affiliation_strings":["Vitruvius Biosciences, The Woodlands, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Vitruvius Biosciences, The Woodlands, TX, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026744019","display_name":"Chetan Belapurkar","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chetan Belapurkar","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035723276","display_name":"Viacheslav Y. Fofanov","orcid":"https://orcid.org/0000-0001-7142-0764"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viacheslav Fofanov","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028415255","display_name":"Tong-Bin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong-Bin Li","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111632219","display_name":"S. M. Chumakov","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]},{"id":"https://openalex.org/I193181351","display_name":"Universidad de Guadalajara","ror":"https://ror.org/043xj7k26","country_code":"MX","type":"education","lineage":["https://openalex.org/I193181351"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Sergey Chumakov","raw_affiliation_strings":["Universidad de Guadalajara","University of Houston"],"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"Universidad de Guadalajara","institution_ids":["https://openalex.org/I193181351"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049887816","display_name":"B. Montgomery Pettitt","orcid":"https://orcid.org/0000-0003-4902-3046"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Montgomery Pettitt","raw_affiliation_strings":["[Univ. of Houston]"],"affiliations":[{"raw_affiliation_string":"[Univ. of Houston]","institution_ids":["https://openalex.org/I44461941"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618,"provenance":"doaj"},"apc_paid":null,"fwci":1.307,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":93,"citation_normalized_percentile":{"value":0.932763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"20","issue":"15","first_page":"2421","last_page":"2428"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9994,"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":0.9994,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9982,"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":0.9949,"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/multicellular-organism","display_name":"Multicellular organism","score":0.64619726},{"id":"https://openalex.org/keywords/identification","display_name":"Identification","score":0.48607424},{"id":"https://openalex.org/keywords/bacterial-genome-size","display_name":"Bacterial genome size","score":0.46017116}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.8816136},{"id":"https://openalex.org/C74318829","wikidata":"https://www.wikidata.org/wiki/Q36458","display_name":"Multicellular organism","level":3,"score":0.64619726},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.62580353},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48607424},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4691217},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4654271},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.46054336},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.46017116},{"id":"https://openalex.org/C137858568","wikidata":"https://www.wikidata.org/wiki/Q7239","display_name":"Organism","level":2,"score":0.45025575},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4498736},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21325907},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.07146388}],"mesh":[{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016172","descriptor_name":"DNA Fingerprinting","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016172","descriptor_name":"DNA Fingerprinting","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009841","descriptor_name":"Oligonucleotides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009841","descriptor_name":"Oligonucleotides","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth266","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/15/2421/48906008/bioinformatics_20_15_2421.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15087315","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth266","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/15/2421/48906008/bioinformatics_20_15_2421.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.64}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1978691113","https://openalex.org/W2015640371","https://openalex.org/W2038073070","https://openalex.org/W2040745248","https://openalex.org/W2047531378","https://openalex.org/W2048721314","https://openalex.org/W2068308871","https://openalex.org/W2101968807","https://openalex.org/W2110342329","https://openalex.org/W2129075788","https://openalex.org/W2140320695","https://openalex.org/W2467507445","https://openalex.org/W2485058775","https://openalex.org/W2906291206","https://openalex.org/W4244578732","https://openalex.org/W55083422"],"related_works":["https://openalex.org/W93506351","https://openalex.org/W4254238697","https://openalex.org/W3025873693","https://openalex.org/W2768690359","https://openalex.org/W2505404359","https://openalex.org/W2475096012","https://openalex.org/W2280157287","https://openalex.org/W2163903195","https://openalex.org/W2035423850","https://openalex.org/W1995226864"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Analysis":[2],"of":[3,6,39,49,53,55,58,62,83,99,112,114,122,131,136,151,154,180,184,193,200,210],"statistical":[4],"properties":[5],"DNA":[7,18],"sequences":[8],"is":[9,94,106,161,216],"important":[10],"for":[11,17,30],"evolutional":[12],"biology":[13],"as":[14,16,163,165],"well":[15],"probe":[19],"and":[20,76,196],"PCR":[21],"technologies.":[22],"These":[23],"technologies,":[24],"in":[25,36,71,101,116,139,156,173],"turn,":[26],"can":[27],"be":[28],"used":[29],"organism":[31],"identification,":[32],"which":[33,105],"implies":[34],"applications":[35],"the":[37,50,56,108,134,152,170,178,201],"diagnosis":[38],"infectious":[40],"diseases,":[41],"environmental":[42],"studies,":[43],"etc.":[44],"Results:":[45],"We":[46,88],"present":[47,95,172],"results":[48],"correlation":[51,150],"analysis":[52],"distributions":[54],"presence/absence":[57,135],"short":[59],"nucleotide":[60],"subsequences":[61],"different":[63,137,174,194],"length":[64],"(\u2018n-mers\u2019,":[65],"n":[66],"=":[67],"5":[68],"\u2013":[69],"20)":[70],"more":[72,119],"than":[73],"1500":[74],"microbial":[75],"virus":[77],"genomes,":[78],"together":[79],"with":[80,206],"five":[81],"genomes":[82,120,141,175,192,199],"multicellular":[84],"organisms":[85,125,195],"(including":[86],"human).":[87],"calculate":[89],"whether":[90],"a":[91,102,207],"given":[92,103],"n-mer":[93],"or":[96,118],"absent":[97],"(frequency":[98,121],"presence)":[100],"genome,":[104],"not":[107,128,143,162],"usually":[109],"calculated":[110],"number":[111],"appearances":[113],"n-mers":[115,155,171,185],"one":[117],"appearance).":[123],"For":[124,145],"that":[126],"are":[127,142],"close":[129,146],"relatives":[130],"each":[132],"other,":[133],"7\u201320mers":[138],"their":[140],"correlated.":[144],"biological":[147],"relatives,":[148],"some":[149],"presence":[153],"this":[157],"range":[158],"appears,":[159],"but":[160],"strong":[164],"expected.":[166],"Suppressed":[167],"correlations":[168],"among":[169],"leads":[176],"to":[177,190],"possibility":[179],"using":[181],"random":[182],"sets":[183],"(with":[186],"appropriately":[187],"chosen":[188],"n)":[189],"discriminate":[191],"possibly":[197],"individual":[198],"same":[202],"species":[203],"including":[204],"human":[205],"low":[208],"probability":[209],"error.":[211],"Supplementary":[212,214],"information:":[213],"data":[215],"available":[217],"at":[218],"http://www.bioinfo.uh.edu/publications/independence_genomes/.":[219]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2126198043","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2025-01-03T23:49:29.866726","created_date":"2016-06-24"}