{"id":"https://openalex.org/W2143796933","doi":"https://doi.org/10.1186/1471-2105-11-406","title":"MS4 - Multi-Scale Selector of Sequence Signatures: An alignment-free method for classification of biological sequences","display_name":"MS4 - Multi-Scale Selector of Sequence Signatures: An alignment-free method for classification of biological sequences","publication_year":2010,"publication_date":"2010-07-30","ids":{"openalex":"https://openalex.org/W2143796933","doi":"https://doi.org/10.1186/1471-2105-11-406","mag":"2143796933","pmid":"https://pubmed.ncbi.nlm.nih.gov/20673356"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-406","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-406","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-406","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033278582","display_name":"Eduardo Corel","orcid":"https://orcid.org/0000-0003-4410-9035"},"institutions":[{"id":"https://openalex.org/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]},{"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"]}],"countries":["DE","FR"],"is_corresponding":true,"raw_author_name":"Eduardo Corel","raw_affiliation_strings":["Georg-August-Universit\u00e4t, Institut f\u00fcr Mikrobiologie und Genetik, G\u00f6ttingen, Germany","Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georg-August-Universit\u00e4t, Institut f\u00fcr Mikrobiologie und Genetik, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]},{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041679690","display_name":"Florian Pitschi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Florian Pitschi","raw_affiliation_strings":["Partner Institute for Computational Biology, CAS-MPG, 320 Yue Yang Rd, 200031, Shanghai, China","Partner Institute for Computational Biology, CAS-MPG, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Partner Institute for Computational Biology, CAS-MPG, 320 Yue Yang Rd, 200031, Shanghai, China","institution_ids":["https://openalex.org/I4210121447"]},{"raw_affiliation_string":"Partner Institute for Computational Biology, CAS-MPG, Shanghai, China","institution_ids":["https://openalex.org/I4210121447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104962765","display_name":"Ivan Laprevotte","orcid":null},"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/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ivan Laprevotte","raw_affiliation_strings":["Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106182705","display_name":"Gilles Grasseau","orcid":null},"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/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Grasseau","raw_affiliation_strings":["Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027579787","display_name":"Gilles Didier","orcid":"https://orcid.org/0000-0003-0596-9112"},"institutions":[{"id":"https://openalex.org/I4210138206","display_name":"Institut de Math\u00e9matiques de Marseille","ror":"https://ror.org/042h2y225","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210138206","https://openalex.org/I4210141950","https://openalex.org/I4210142724"]},{"id":"https://openalex.org/I4210126368","display_name":"Institut de Recherche Dupuy de L\u00f4me","ror":"https://ror.org/03011gg73","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I2802204017","https://openalex.org/I4210095849","https://openalex.org/I4210126368","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4405260085"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Didier","raw_affiliation_strings":["Institut de Math\u00e9matiques de Luminy, UMR 6206, Luminy, Marseille, France","Institut de Math\u00e9matiques de Luminy, UMR 6206, Luminy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Math\u00e9matiques de Luminy, UMR 6206, Luminy, Marseille, France","institution_ids":["https://openalex.org/I4210138206"]},{"raw_affiliation_string":"Institut de Math\u00e9matiques de Luminy, UMR 6206, Luminy, France","institution_ids":["https://openalex.org/I4210126368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022701865","display_name":"Claudine Devauchelle","orcid":null},"institutions":[{"id":"https://openalex.org/I88467170","display_name":"Universit\u00e9 d'\u00c9vry Val-d'Essonne","ror":"https://ror.org/00e96v939","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954","https://openalex.org/I88467170"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claudine Devauchelle","raw_affiliation_strings":["Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Place des Terrasses, 91034, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire Statistique et G\u00e9nome (LSG), CNRS UMR 8071, INRA 1152, Universit\u00e9 d'Evry, Tour Evry2, Evry Cedex, France","institution_ids":["https://openalex.org/I88467170","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033278582"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I74656192","https://openalex.org/I88467170"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.6805,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70104142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":"1","first_page":"406","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3321000039577484,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3321000039577484,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.25619998574256897,"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":0.12700000405311584,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.5549717545509338},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5189987421035767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47737452387809753},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45634138584136963},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4488907754421234},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4375244975090027},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4280211627483368},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4275713264942169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4234154224395752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4040343165397644},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.3254029154777527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31529128551483154},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.17327851057052612},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15415233373641968},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12762349843978882},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09490928053855896}],"concepts":[{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.5549717545509338},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5189987421035767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47737452387809753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45634138584136963},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4488907754421234},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4375244975090027},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4280211627483368},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4275713264942169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4234154224395752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4040343165397644},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3254029154777527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31529128551483154},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.17327851057052612},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15415233373641968},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12762349843978882},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09490928053855896},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid 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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006678","descriptor_name":"HIV","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015302","descriptor_name":"Simian Immunodeficiency Virus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015754","descriptor_name":"Genes, nef","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015754","descriptor_name":"Genes, nef","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015754","descriptor_name":"Genes, nef","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016325","descriptor_name":"HIV Long Terminal Repeat","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016325","descriptor_name":"HIV Long Terminal Repeat","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016325","descriptor_name":"HIV Long Terminal Repeat","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":"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}],"locations_count":7,"locations":[{"id":"doi:10.1186/1471-2105-11-406","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-406","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-406","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20673356","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20673356","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:publications.goettingen-research-online.de:2/19426","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/19426","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"journal_article"},{"id":"pmh:oai:HAL:hal-01614124v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01614124","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 2010, 11 (1), &#x27E8;10.1186/1471-2105-11-406&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:48ed11f127784925a9e3449d08b2d3b1","is_oa":true,"landing_page_url":"https://doaj.org/article/48ed11f127784925a9e3449d08b2d3b1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss 1, p 406 (2010)","raw_type":"article"},{"id":"pmh:oai:goescholar:1/5666","is_oa":true,"landing_page_url":"http://resolver.sub.uni-goettingen.de/purl?gs-1/5666","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journalArticle"},{"id":"pmh:oai:pubmedcentral.nih.gov:2923138","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2923138","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-406","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-406","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-406","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143796933.pdf","grobid_xml":"https://content.openalex.org/works/W2143796933.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W70204868","https://openalex.org/W638753865","https://openalex.org/W1570643690","https://openalex.org/W1827957577","https://openalex.org/W1991330646","https://openalex.org/W2037179333","https://openalex.org/W2043797302","https://openalex.org/W2045895701","https://openalex.org/W2048887847","https://openalex.org/W2055298722","https://openalex.org/W2091134657","https://openalex.org/W2100152398","https://openalex.org/W2107248520","https://openalex.org/W2107282968","https://openalex.org/W2108079689","https://openalex.org/W2120772351","https://openalex.org/W2123170127","https://openalex.org/W2147996827","https://openalex.org/W2152331922"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726","https://openalex.org/W187239587","https://openalex.org/W2141411672"],"abstract_inverted_index":{"BACKGROUND:":[0],"While":[1],"multiple":[2,24],"alignment":[3],"is":[4,111,207,308],"the":[5,68,99,118,142,154,160,165,191,211,216,234,244,271],"first":[6],"step":[7],"of":[8,52,70,73,83,93,101,108,130,147,177,215,225,228,247,257,273,283],"usual":[9],"classification":[10,156,277],"schemes":[11],"for":[12,32,89,138,168,196,291,301,304],"biological":[13],"sequences,":[14],"alignment-free":[15,104,276],"methods":[16,29],"are":[17,30,200,260],"being":[18],"increasingly":[19],"used":[20],"as":[21,153],"alternatives":[22],"when":[23],"alignments":[25],"fail.":[26],"Subword-based":[27],"combinatorial":[28],"popular":[31],"their":[33],"low":[34],"algorithmic":[35],"complexity":[36],"(suffix":[37],"trees":[38],"...)":[39],"or":[40],"exhaustivity":[41],"(motif":[42],"search),":[43],"in":[44,141],"general":[45],"with":[46,233],"fixed":[47,74,81,128],"length":[48,183],"word":[49],"and/or":[50],"number":[51,82,176],"mismatches.":[53,84],"We":[54,132,218],"developed":[55],"previously":[56],"a":[57,80,102,114,127,134,173,255,274,298],"method":[58,115,251],"to":[59,97,112,181,189,205,263,286],"detect":[60],"local":[61],"similarities":[62,87,119],"(the":[63],"N-local":[64,122,166],"decoding)":[65],"based":[66],"on":[67,238],"occurrences":[69],"repeated":[71],"subwords":[72,184],"length,":[75],"which":[76,197,295,305],"does":[77],"not":[78,125],"impose":[79],"The":[85,106,193,250,279],"resulting":[86],"are,":[88],"some":[90],"\"good\"":[91],"values":[92,199],"N,":[94,148,170,195],"sufficiently":[95],"relevant":[96],"form":[98],"basis":[100,272],"reliable":[103,275],"classification.":[105,192],"aim":[107],"this":[109],"paper":[110],"develop":[113],"that":[116,136,185,220,231,259,267],"uses":[117],"detected":[120],"by":[121,164,210],"decoding":[123],"while":[124],"imposing":[126],"value":[129,146],"N.":[131],"present":[133],"procedure":[135],"selects":[137],"every":[139],"position":[140],"sequences":[143,230,258],"an":[144],"adaptive":[145],"and":[149,202],"we":[150,171],"implement":[151],"it":[152],"MS4":[155,252,284],"tool.":[157,278],"RESULTS:":[158],"Among":[159],"equivalence":[161],"classes":[162,179],"produced":[163],"decodings":[167],"all":[169],"select":[172],"(relatively)":[174],"small":[175],"\"relevant\"":[178],"corresponding":[180],"variable":[182],"carry":[186],"enough":[187],"information":[188,307],"perform":[190],"parameter":[194,281],"correct":[198],"data-dependent":[201],"thus":[203],"hard":[204,262],"guess,":[206],"here":[208],"replaced":[209],"average":[212],"repetitivity":[213],"kappa":[214,282],"sequences.":[217],"show":[219],"our":[221,268],"approach":[222,269],"yields":[223],"classifications":[224],"several":[226],"sets":[227,303],"HIV/SIV":[229],"agree":[232],"accepted":[235],"taxonomy,":[236],"even":[237,290],"usually":[239],"discarded":[240],"repetitive":[241],"regions":[242],"(like":[243],"non-coding":[245],"part":[246],"LTR).":[248],"CONCLUSIONS:":[249],"satisfactorily":[253],"classifies":[254],"set":[256],"notoriously":[261],"align.":[264],"This":[265],"suggests":[266],"forms":[270],"only":[280],"seems":[285],"give":[287],"reasonable":[288],"results":[289],"its":[292],"default":[293],"value,":[294],"can":[296],"be":[297],"great":[299],"advantage":[300],"sequence":[302],"little":[306],"available.":[309]},"counts_by_year":[{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
