{"id":"https://openalex.org/W2089453789","doi":"https://doi.org/10.1186/1471-2105-15-321","title":"An improved alignment-free model for dna sequence similarity metric","display_name":"An improved alignment-free model for dna sequence similarity metric","publication_year":2014,"publication_date":"2014-09-28","ids":{"openalex":"https://openalex.org/W2089453789","doi":"https://doi.org/10.1186/1471-2105-15-321","mag":"2089453789","pmid":"https://pubmed.ncbi.nlm.nih.gov/25261973"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-15-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-15-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-15-321","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/10.1186/1471-2105-15-321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101539799","display_name":"Junpeng Bao","orcid":"https://orcid.org/0000-0002-3866-5011"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junpeng Bao","raw_affiliation_strings":["Department of Computer Science and Technology Xi'an Jiaotong University, West Xianning Road, 710049 Xi'an, P,R, China. baojp@mail.xjtu.edu.cn","Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology Xi'an Jiaotong University, West Xianning Road, 710049 Xi'an, P,R, China. baojp@mail.xjtu.edu.cn","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007835307","display_name":"Ruiyu Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyu Yuan","raw_affiliation_strings":["Department of Computer Science and Technology Xi\u2019an Jiaotong University, West Xianning Road, 710049, Xi\u2019an, P.R. China","Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology Xi\u2019an Jiaotong University, West Xianning Road, 710049, Xi\u2019an, P.R. China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056069384","display_name":"Zhe Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Bao","raw_affiliation_strings":["Department of Computer Science and Technology Xi\u2019an Jiaotong University, West Xianning Road, 710049, Xi\u2019an, P.R. China","Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology Xi\u2019an Jiaotong University, West Xianning Road, 710049, Xi\u2019an, P.R. China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Department of Computer Science and Technology , Xi'an Jiaotong University , Xi'an, P.R. China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101539799"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.1383,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.77621879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"321","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5541999936103821,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5541999936103821,"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":0.2037000060081482,"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":0.04410000145435333,"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/computational-biology","display_name":"Computational biology","score":0.6324074268341064},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.571325421333313},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5707215666770935},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.5278563499450684},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5203406810760498},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5194715857505798},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5048432946205139},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.4971142113208771},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.4849279224872589},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46643877029418945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4399498999118805},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4093686044216156},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.40655454993247986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2462390661239624},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14282721281051636},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.14126786589622498},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10598984360694885}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6324074268341064},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.571325421333313},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5707215666770935},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.5278563499450684},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5203406810760498},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5194715857505798},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5048432946205139},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.4971142113208771},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.4849279224872589},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46643877029418945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4399498999118805},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4093686044216156},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.40655454993247986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2462390661239624},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14282721281051636},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.14126786589622498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10598984360694885},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","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":"D000465","descriptor_name":"Algorithms","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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","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},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-15-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-15-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-15-321","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:25261973","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25261973","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:pubmedcentral.nih.gov:4261891","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4261891","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:10.1186/1471-2105-15-321","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-15-321","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-15-321","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":[{"id":"https://openalex.org/G8237982606","display_name":"\u8de8\u8bed\u8a00\u6587\u672c\u590d\u5236\u68c0\u6d4b\u7814\u7a76","funder_award_id":"60903123","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8548236690","display_name":"\u7f51\u7edc\u73af\u5883\u4e0b\u8f6f\u4ef6\u8001\u5316\u6a21\u5f0f\u53ca\u518d\u751f\u65b9\u6cd5\u7814\u7a76","funder_award_id":"60933003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2089453789.pdf","grobid_xml":"https://content.openalex.org/works/W2089453789.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W8488631","https://openalex.org/W158216348","https://openalex.org/W1414199774","https://openalex.org/W1539117683","https://openalex.org/W1604683925","https://openalex.org/W1968363797","https://openalex.org/W1976772668","https://openalex.org/W1983087557","https://openalex.org/W1990442974","https://openalex.org/W1992114076","https://openalex.org/W1995534343","https://openalex.org/W2003309484","https://openalex.org/W2006836764","https://openalex.org/W2008714912","https://openalex.org/W2011399892","https://openalex.org/W2011505400","https://openalex.org/W2013357328","https://openalex.org/W2017722173","https://openalex.org/W2024291454","https://openalex.org/W2029195137","https://openalex.org/W2030774451","https://openalex.org/W2032345031","https://openalex.org/W2041624900","https://openalex.org/W2055043387","https://openalex.org/W2085498221","https://openalex.org/W2103156298","https://openalex.org/W2116988150","https://openalex.org/W2119488386","https://openalex.org/W2123170127","https://openalex.org/W2124351063","https://openalex.org/W2156125289","https://openalex.org/W2166162901","https://openalex.org/W2171963266"],"related_works":["https://openalex.org/W1486249959","https://openalex.org/W2885386129","https://openalex.org/W2051969447","https://openalex.org/W2948014085","https://openalex.org/W2141530749","https://openalex.org/W2004215917","https://openalex.org/W2468116983","https://openalex.org/W2103737249","https://openalex.org/W1974956921","https://openalex.org/W2111937814"],"abstract_inverted_index":{"BACKGROUND:":[0],"DNA":[1,18,22,31,53,95,136,160,167,209,278],"Clustering":[2],"is":[3,35,46,108,237,266,293,308],"an":[4,192,312],"important":[5],"technology":[6],"to":[7,51,133,173,239,300,310],"automatically":[8],"find":[9],"the":[10,21,38,94,105,111,135,149,174,245,259,269,285],"inherent":[11],"relationships":[12],"on":[13,66,212,272],"a":[14,47,59,62,125,143,166,182,297],"large":[15],"scale":[16],"of":[17,37,41,89,100,156,176,244,288],"sequences.":[19,161],"But":[20],"clustering":[23,137,210,246],"quality":[24],"can":[25,116,255],"still":[26],"be":[27,117,256],"improved":[28],"greatly.":[29],"The":[30,43,162,186,231,252,262,305],"sequences":[32,171,279],"similarity":[33],"metric":[34],"one":[36],"key":[39],"points":[40],"clustering.":[42],"alignment-free":[44,76,127,220],"methodology":[45],"very":[48],"popular":[49],"way":[50],"calculate":[52],"sequence":[54,60,168],"similarity.":[55],"It":[56,107],"normally":[57],"converts":[58,165],"into":[61,169,205],"feature":[63,184,187],"space":[64],"based":[65,194,271],"words'":[67],"probability":[68],"distribution":[69],"rather":[70],"than":[71,268,282],"directly":[72],"matches":[73],"strings.":[74],"Existing":[75],"models,":[77],"e.g.":[78],"k-tuple,":[79,225],"merely":[80],"employ":[81],"word":[82,150,200,273],"frequency":[83,201,274],"information":[84,91,132,155,204,264],"and":[85,104,153,179,202,215,229,248,316],"ignore":[86],"many":[87],"types":[88],"useful":[90],"contained":[92],"in":[93,242],"sequence,":[96],"such":[97],"as":[98],"classifications":[99],"nucleotide":[101,157,177],"bases,":[102,178],"position":[103,152,203],"like.":[106],"believed":[109],"that":[110,129,196,234],"better":[112,267],"data":[113],"mining":[114],"results":[115,247],"achieved":[118],"with":[119,217],"compounded":[120,131],"information.":[121],"Therefore,":[122],"we":[123],"present":[124],"new":[126],"model":[128,164,195,236,265,270,307],"employs":[130],"improve":[134],"quality.":[138],"RESULTS:":[139],"This":[140],"paper":[141],"proposes":[142],"Category-Position-Frequency":[144],"(CPF)":[145],"model,":[146],"which":[147,295],"utilizes":[148],"frequency,":[151],"classification":[154],"bases":[158],"from":[159,258],"CPF":[163,235,292,306],"three":[170],"according":[172],"categories":[175],"then":[180],"yields":[181],"12-dimension":[183],"vector.":[185],"values":[188],"are":[189],"computed":[190],"by":[191],"entropy":[193],"takes":[197],"both":[198],"local":[199],"account.":[206],"We":[207],"conduct":[208],"experiments":[211,232],"several":[213],"datasets":[214],"compare":[216],"some":[218],"mainstream":[219],"models":[221,241],"for":[222,291],"evaluation,":[223],"including":[224],"DMk,":[226],"TSM,":[227],"AMI":[228],"CV.":[230],"show":[233],"superior":[238],"other":[240],"terms":[243],"optimal":[249],"settings.":[250],"CONCLUSIONS:":[251],"following":[253],"conclusions":[254],"drawn":[257],"experiments.":[260],"(1)":[261],"hybrid":[263],"only.":[275],"(2)":[276],"For":[277],"no":[280],"more":[281],"5000":[283],"characters,":[284],"preferred":[286],"size":[287],"sliding":[289],"windows":[290],"two":[294],"provides":[296],"great":[298],"advantage":[299],"promote":[301],"system":[302],"performance.":[303],"(3)":[304],"able":[309],"obtain":[311],"efficient":[313],"stable":[314],"performance":[315],"broad":[317],"generalization.":[318]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}