{"id":"https://openalex.org/W1967843471","doi":"https://doi.org/10.1093/bib/bbt052","title":"Alignment-free genetic sequence comparisons: a review of recent approaches by word analysis","display_name":"Alignment-free genetic sequence comparisons: a review of recent approaches by word analysis","publication_year":2013,"publication_date":"2013-07-31","ids":{"openalex":"https://openalex.org/W1967843471","doi":"https://doi.org/10.1093/bib/bbt052","mag":"1967843471","pmid":"https://pubmed.ncbi.nlm.nih.gov/23904502"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbt052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbt052","pdf_url":"https://academic.oup.com/bib/article-pdf/15/6/890/425699/bbt052.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bib/article-pdf/15/6/890/425699/bbt052.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028954340","display_name":"Oliver Bonham-Carter","orcid":"https://orcid.org/0000-0001-9032-0398"},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"O. Bonham-Carter","raw_affiliation_strings":["\u2020 University of Nebraska, Omaha;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020 University of Nebraska, Omaha;","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019475957","display_name":"J. L. Steele","orcid":null},"institutions":[{"id":"https://openalex.org/I122266389","display_name":"University of Nebraska at Omaha","ror":"https://ror.org/04yrkc140","country_code":"US","type":"education","lineage":["https://openalex.org/I122266389"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Steele","raw_affiliation_strings":["\u2020 University of Nebraska, Omaha;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020 University of Nebraska, Omaha;","institution_ids":["https://openalex.org/I122266389"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036016911","display_name":"Dhundy Bastola","orcid":"https://orcid.org/0000-0003-1128-4451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Bastola","raw_affiliation_strings":["School of Interdisciplinary Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interdisciplinary Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":17.0369,"has_fulltext":false,"cited_by_count":136,"citation_normalized_percentile":{"value":0.99111135,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"15","issue":"6","first_page":"890","last_page":"905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.998199999332428,"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/word","display_name":"Word (group theory)","score":0.6917328834533691},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6474734544754028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5882933139801025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5490047931671143},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5010569095611572},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.49796104431152344},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4148631989955902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3736526072025299},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.34005147218704224},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.2771878242492676},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.27652910351753235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21721214056015015},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1548372209072113},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08643767237663269},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.07505229115486145}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6917328834533691},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6474734544754028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5882933139801025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5490047931671143},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5010569095611572},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.49796104431152344},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4148631989955902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3736526072025299},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34005147218704224},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2771878242492676},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27652910351753235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21721214056015015},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1548372209072113},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08643767237663269},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.07505229115486145}],"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":"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":"D007257","descriptor_name":"Information Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007257","descriptor_name":"Information Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007257","descriptor_name":"Information Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058974","descriptor_name":"Phylogeography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbt052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbt052","pdf_url":"https://academic.oup.com/bib/article-pdf/15/6/890/425699/bbt052.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:23904502","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23904502","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:3601705","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4296134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbt052","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbt052","pdf_url":"https://academic.oup.com/bib/article-pdf/15/6/890/425699/bbt052.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3858551904","display_name":null,"funder_award_id":"8P20GM103427","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8227563124","display_name":null,"funder_award_id":"5P20RR016469","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1967843471.pdf"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1639694146","https://openalex.org/W1965687515","https://openalex.org/W1968363797","https://openalex.org/W1971239653","https://openalex.org/W1977231825","https://openalex.org/W1982799052","https://openalex.org/W1985108724","https://openalex.org/W1986106281","https://openalex.org/W1986908504","https://openalex.org/W1987458030","https://openalex.org/W1988827980","https://openalex.org/W1990061958","https://openalex.org/W1991754655","https://openalex.org/W1995875735","https://openalex.org/W1997833643","https://openalex.org/W2001496424","https://openalex.org/W2002937977","https://openalex.org/W2004805642","https://openalex.org/W2006435065","https://openalex.org/W2008386840","https://openalex.org/W2010808181","https://openalex.org/W2013226864","https://openalex.org/W2015843229","https://openalex.org/W2016219933","https://openalex.org/W2020152253","https://openalex.org/W2022085922","https://openalex.org/W2022842463","https://openalex.org/W2023116290","https://openalex.org/W2024873496","https://openalex.org/W2024925477","https://openalex.org/W2041397659","https://openalex.org/W2041404167","https://openalex.org/W2045895701","https://openalex.org/W2051254500","https://openalex.org/W2051929999","https://openalex.org/W2055445955","https://openalex.org/W2058896194","https://openalex.org/W2061271738","https://openalex.org/W2064054988","https://openalex.org/W2073001584","https://openalex.org/W2074231493","https://openalex.org/W2081496922","https://openalex.org/W2081626815","https://openalex.org/W2085596190","https://openalex.org/W2087064593","https://openalex.org/W2088775137","https://openalex.org/W2093931624","https://openalex.org/W2095724872","https://openalex.org/W2100301262","https://openalex.org/W2103065948","https://openalex.org/W2107745473","https://openalex.org/W2114789243","https://openalex.org/W2116988150","https://openalex.org/W2117959411","https://openalex.org/W2119488386","https://openalex.org/W2123170127","https://openalex.org/W2124852384","https://openalex.org/W2126842951","https://openalex.org/W2127912200","https://openalex.org/W2131106408","https://openalex.org/W2134826720","https://openalex.org/W2136145671","https://openalex.org/W2137015675","https://openalex.org/W2138080747","https://openalex.org/W2141747524","https://openalex.org/W2146950091","https://openalex.org/W2150774511","https://openalex.org/W2155430004","https://openalex.org/W2157745386","https://openalex.org/W2158384625","https://openalex.org/W2158714788","https://openalex.org/W2158727584","https://openalex.org/W2171963266","https://openalex.org/W2334744046"],"related_works":["https://openalex.org/W1482324242","https://openalex.org/W1569283511","https://openalex.org/W4236193183","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2112284452","https://openalex.org/W2231795205","https://openalex.org/W2523632547","https://openalex.org/W1525517788","https://openalex.org/W2029374538"],"abstract_inverted_index":{"Modern":[0],"sequencing":[1],"and":[2,39,77,89,94,112,150,173,183],"genome":[3],"assembly":[4],"technologies":[5],"have":[6],"provided":[7],"a":[8,24,124],"wealth":[9],"of":[10,60,72,127,157,186],"data,":[11],"which":[12,130],"will":[13],"soon":[14],"require":[15],"an":[16,169,184],"analysis":[17,88,138,159,187],"by":[18,116,188],"comparison":[19],"for":[20,47],"discovery.":[21],"Sequence":[22],"alignment,":[23],"fundamental":[25],"task":[26],"in":[27],"bioinformatics":[28],"research,":[29],"may":[30],"be":[31],"used":[32],"but":[33],"with":[34],"some":[35],"caveats.":[36],"Seminal":[37],"techniques":[38,190],"methods":[40,64,103,134],"from":[41,84,132,139,191],"dynamic":[42,99],"programming":[43],"are":[44,65,92,104,110,113],"proving":[45],"ineffective":[46],"this":[48,120],"work":[49],"owing":[50],"to":[51,67,98,147],"their":[52,108],"inherent":[53,79],"computational":[54,128],"expense":[55],"when":[56],"processing":[57],"large":[58],"amounts":[59],"sequence":[61],"data.":[62],"These":[63,101],"prone":[66],"giving":[68],"misleading":[69],"information":[70,85],"because":[71],"genetic":[73,75],"recombination,":[74],"shuffling":[76],"other":[78],"biological":[80],"events.":[81],"New":[82],"approaches":[83],"theory,":[86],"frequency":[87,165],"data":[90,192],"compression":[91],"available":[93],"provide":[95,123,143,180],"powerful":[96],"alternatives":[97],"programming.":[100],"new":[102],"often":[105],"preferred,":[106],"as":[107,161],"algorithms":[109],"simpler":[111],"not":[114],"affected":[115],"synteny-related":[117],"problems.":[118],"In":[119],"review,":[121],"we":[122,179],"detailed":[125,181],"discussion":[126,182],"tools,":[129],"stem":[131],"alignment-free":[133,158],"based":[135],"on":[136],"statistical":[137],"word":[140],"frequencies.":[141],"We":[142],"several":[144,154],"clear":[145],"examples":[146],"demonstrate":[148],"applications":[149],"the":[151,174],"interpretations":[152],"over":[153],"different":[155],"areas":[156],"such":[160],"base-base":[162],"correlations,":[163],"feature":[164],"profiles,":[166],"compositional":[167],"vectors,":[168],"improved":[170],"string":[171],"composition":[172],"D2":[175],"statistic":[176],"metric.":[177],"Additionally,":[178],"example":[185],"Lempel-Ziv":[189],"compression.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
