{"id":"https://openalex.org/W7222943471","doi":"https://doi.org/10.1093/nargab/lqag124","title":"CAMELLIA: an alignment-free pipeline integrating k -mer feature selection and supervised classification for genomic sequence subtyping","display_name":"CAMELLIA: an alignment-free pipeline integrating k -mer feature selection and supervised classification for genomic sequence subtyping","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7222943471","doi":"https://doi.org/10.1093/nargab/lqag124","pmid":"https://pubmed.ncbi.nlm.nih.gov/42898811","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13678207"},"language":"en","primary_location":{"id":"doi:10.1093/nargab/lqag124","doi":"https://doi.org/10.1093/nargab/lqag124","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nargab/lqag124","pdf_url":"https://academic.oup.com/nargab/article-pdf/8/4/lqag124/72085441/lqag124.pdf","source":{"id":"https://openalex.org/S4210241000","display_name":"NAR Genomics and Bioinformatics","issn_l":"2631-9268","issn":["2631-9268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-20","russia-white-list-2","vabb-shw"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NAR Genomics and Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/nargab/article-pdf/8/4/lqag124/72085441/lqag124.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017969752","display_name":"Tatiana Mari Saita","orcid":"https://orcid.org/0000-0002-5891-4724","observed_orcids":["https://orcid.org/0000-0002-5891-4724"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tatiana Mari Saita","raw_affiliation_strings":["Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,"],"raw_orcid":"https://orcid.org/0000-0002-5891-4724","affiliations":[{"raw_affiliation_string":"Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064448644","display_name":"Matheus Henrique Pimenta-Zanon","orcid":"https://orcid.org/0000-0003-0698-6360","observed_orcids":["https://orcid.org/0000-0003-0698-6360"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Matheus Henrique Pimenta-Zanon","raw_affiliation_strings":["Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,","Departamento de Gen\u00e9tica Escola Superior de Agricultura \u2018Luiz de Queiroz\u2019, Universidade de S\u00e3o Paulo , P\u00e1dua Dias Av., 11, 13418-900, S\u00e3o Paulo ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,","institution_ids":["https://openalex.org/I1283613182"]},{"raw_affiliation_string":"Departamento de Gen\u00e9tica Escola Superior de Agricultura \u2018Luiz de Queiroz\u2019, Universidade de S\u00e3o Paulo , P\u00e1dua Dias Av., 11, 13418-900, S\u00e3o Paulo ,","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058319433","display_name":"Artur T. L. Queiroz","orcid":"https://orcid.org/0000-0003-4908-9993","observed_orcids":["https://orcid.org/0000-0003-4908-9993"]},"institutions":[{"id":"https://openalex.org/I4405286606","display_name":"Instituto Gon\u00e7alo Moniz","ror":"https://ror.org/02kqr5716","country_code":"BR","type":"government","lineage":["https://openalex.org/I4405286606","https://openalex.org/I52325"]},{"id":"https://openalex.org/I52325","display_name":"Funda\u00e7\u00e3o Oswaldo Cruz","ror":"https://ror.org/04jhswv08","country_code":"BR","type":"facility","lineage":["https://openalex.org/I52325"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Artur Trancoso Lopo de\u00a0Queiroz","raw_affiliation_strings":["Laborat\u00f3rio de Pesquisas Cl\u00ednicas e Translacionais, Instituto Gon\u00e7alo Moniz, Funda\u00e7\u00e3o Oswaldo Cruz (FIOCRUZ) , Rua Waldemar Falc\u00e3o, 121, Salvador, 40296-710, Bahia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio de Pesquisas Cl\u00ednicas e Translacionais, Instituto Gon\u00e7alo Moniz, Funda\u00e7\u00e3o Oswaldo Cruz (FIOCRUZ) , Rua Waldemar Falc\u00e3o, 121, Salvador, 40296-710, Bahia ,","institution_ids":["https://openalex.org/I4405286606","https://openalex.org/I52325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070163783","display_name":"Gl\u00e1ucia Maria Bressan","orcid":"https://orcid.org/0000-0001-6996-3129","observed_orcids":["https://orcid.org/0000-0001-6996-3129"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Glaucia Maria Bressan","raw_affiliation_strings":["Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077226712","display_name":"Fabr\u00edcio Martins Lopes","orcid":"https://orcid.org/0000-0002-8786-3313","observed_orcids":["https://orcid.org/0000-0002-8786-3313"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Fabricio Martins Lopes","raw_affiliation_strings":["Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,"],"raw_orcid":"https://orcid.org/0000-0002-8786-3313","affiliations":[{"raw_affiliation_string":"Associated Graduate Program in Bioinformatics (PPGAB), Universidade Tecnol\u00f3gica Federal do Paran\u00e1 (UTFPR) , Alberto Carazzai, 1640, Corn\u00e9lio Proc\u00f3pio, 86300-000, Paran\u00e1 ,","institution_ids":["https://openalex.org/I1283613182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077226712"],"corresponding_institution_ids":["https://openalex.org/I1283613182"],"apc_list":{"value":2766,"currency":"USD","value_usd":2766},"apc_paid":{"value":2766,"currency":"USD","value_usd":2766},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73527979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"4","first_page":"lqag124","last_page":"lqag124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.4740999937057495,"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":0.4740999937057495,"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":0.4587000012397766,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.05570000037550926,"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/hiv-1-subtypes","display_name":"HIV-1 subtypes","score":0.953000009059906},{"id":"https://openalex.org/keywords/explainable-machine-learning","display_name":"explainable machine learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/intraspecific-sequence-variation","display_name":"intraspecific sequence variation","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6013000011444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5626000165939331},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C83852419","wikidata":"https://www.wikidata.org/wiki/Q2713292","display_name":"Subtyping","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2689000070095062},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.25369998812675476}],"mesh":[{"descriptor_ui":"D000098429","descriptor_name":"Classification 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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D028244","descriptor_name":"Camellia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/nargab/lqag124","doi":"https://doi.org/10.1093/nargab/lqag124","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nargab/lqag124","pdf_url":"https://academic.oup.com/nargab/article-pdf/8/4/lqag124/72085441/lqag124.pdf","source":{"id":"https://openalex.org/S4210241000","display_name":"NAR Genomics and Bioinformatics","issn_l":"2631-9268","issn":["2631-9268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-20","russia-white-list-2","vabb-shw"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NAR Genomics and Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13678207","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13678207/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13678207/pdf/lqag124.pdf","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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NAR Genom Bioinform","raw_type":"Text"},{"id":"pmid:42898811","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42898811","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,"listed_in":[],"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":"NAR genomics and bioinformatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/nargab/lqag124","doi":"https://doi.org/10.1093/nargab/lqag124","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nargab/lqag124","pdf_url":"https://academic.oup.com/nargab/article-pdf/8/4/lqag124/72085441/lqag124.pdf","source":{"id":"https://openalex.org/S4210241000","display_name":"NAR Genomics and Bioinformatics","issn_l":"2631-9268","issn":["2631-9268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-20","russia-white-list-2","vabb-shw"],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NAR Genomics and Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1207375514","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G1329410657","display_name":null,"funder_award_id":"#440412/2022-6","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G488846330","display_name":null,"funder_award_id":"408312/2023-8","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5197439037","display_name":null,"funder_award_id":"440412/2022-6","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G7228074931","display_name":null,"funder_award_id":"2025/10318-5","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G899135499","display_name":null,"funder_award_id":"035/2019","funder_id":"https://openalex.org/F4320322772","funder_display_name":"Funda\u00e7\u00e3o Arauc\u00e1ria"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322772","display_name":"Funda\u00e7\u00e3o Arauc\u00e1ria","ror":"https://ror.org/02r7nkw81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222943471.pdf","grobid_xml":"https://content.openalex.org/works/W7222943471.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1967934074","https://openalex.org/W1970994589","https://openalex.org/W1971876518","https://openalex.org/W2011425267","https://openalex.org/W2016390392","https://openalex.org/W2019216543","https://openalex.org/W2020939898","https://openalex.org/W2029173860","https://openalex.org/W2047870719","https://openalex.org/W2049017883","https://openalex.org/W2081651733","https://openalex.org/W2089497633","https://openalex.org/W2104401897","https://openalex.org/W2116049022","https://openalex.org/W2118539769","https://openalex.org/W2124351063","https://openalex.org/W2125230147","https://openalex.org/W2128260028","https://openalex.org/W2129103781","https://openalex.org/W2138486754","https://openalex.org/W2157702265","https://openalex.org/W2158666214","https://openalex.org/W2158714788","https://openalex.org/W2171963266","https://openalex.org/W2302501749","https://openalex.org/W2461193710","https://openalex.org/W2507450194","https://openalex.org/W2582743722","https://openalex.org/W2620845153","https://openalex.org/W2732139758","https://openalex.org/W2759289851","https://openalex.org/W2760876988","https://openalex.org/W2806980026","https://openalex.org/W2903314774","https://openalex.org/W2943381976","https://openalex.org/W2962807110","https://openalex.org/W2989220201","https://openalex.org/W3101667854","https://openalex.org/W4205491024","https://openalex.org/W4213190829","https://openalex.org/W4243072198","https://openalex.org/W4378803232","https://openalex.org/W4382490702","https://openalex.org/W4385937543","https://openalex.org/W4388000873","https://openalex.org/W4394675060","https://openalex.org/W4398250113","https://openalex.org/W4399274778","https://openalex.org/W4401200522","https://openalex.org/W4403146631","https://openalex.org/W4404473230","https://openalex.org/W4404821554","https://openalex.org/W4404889095","https://openalex.org/W4405670661","https://openalex.org/W4405727880","https://openalex.org/W4407931621","https://openalex.org/W4409585627","https://openalex.org/W4412493829","https://openalex.org/W4416260664","https://openalex.org/W7133235585"],"related_works":["https://openalex.org/W2900835943","https://openalex.org/W220856771","https://openalex.org/W3096509803","https://openalex.org/W2943381976","https://openalex.org/W2761430568","https://openalex.org/W6960287830","https://openalex.org/W7098727416","https://openalex.org/W7168008211","https://openalex.org/W1999786367","https://openalex.org/W4413369812"],"abstract_inverted_index":{"Scalable":[0],"analysis":[1,65],"of":[2],"biological":[3],"sequences":[4,119],"is":[5],"essential":[6],"for":[7,62,104,185,194],"functional":[8],"characterization,":[9],"biomarker":[10],"discovery,":[11],"and":[12,14,25,66,73,87,129,136,139,156,178,189],"therapeutic":[13],"vaccine":[15],"development.":[16],"Alignment-based":[17],"pipelines":[18],"often":[19],"fail":[20],"to":[21,169],"capture":[22],"intraspecific":[23],"variation":[24],"become":[26],"computationally":[27],"limited":[28],"on":[29],"large":[30],"datasets,":[31],"while":[32],"alignment-free":[33,52],"methods":[34],"treat":[35],"each":[36],"class":[37,109,151],"as":[38,94,102],"homogeneous,":[39],"ignoring":[40],"sample":[41],"heterogeneity.":[42],"We":[43,158],"present":[44],"CAMELLIA":[45,68,116,146,180],"(Combining":[46],"AlignMent-free":[47],"fEature":[48],"seLection":[49],"cLassIficAtion),":[50],"an":[51,112],"framework":[53],"that":[54],"combines":[55],"feature":[56,154,166],"selection":[57,155],"with":[58],"explainable":[59],"machine":[60],"learning":[61],"genomic":[63,186],"sequence":[64,187],"classification.":[67],"identifies":[69],"subgroups":[70,76],"within":[71],"classes":[72],"ensures":[74],"underrepresented":[75],"are":[77,92,100],"captured":[78],"by":[79],"the":[80],"selected":[81,165],"features,":[82],"yielding":[83],"a":[84,182,191],"more":[85],"accurate":[86,108],"scalable":[88],"data-driven":[89],"representation.":[90],"Sequences":[91],"represented":[93],"graphs,":[95],"from":[96],"which":[97],"structural":[98,148],"patterns":[99,149],"extracted":[101],"features":[103],"supervised":[105],"classifiers,":[106],"enabling":[107],"discrimination.":[110],"In":[111],"HIV-1":[113],"case":[114],"study,":[115],"accurately":[117],"classified":[118],"into":[120],"eight":[121],"subtypes,":[122],"reduced":[123],"processing":[124],"time":[125],"versus":[126],"MEGA":[127],"(MUSCLE)":[128],"FAMSA,":[130],"matched":[131],"CASTOR-KRFE":[132],"under":[133],"identical":[134],"splits,":[135],"outperformed":[137],"COMET":[138],"REGA":[140],"in":[141],"accuracy.":[142],"Beyond":[143],"predictive":[144],"performance,":[145],"recovered":[147],"beyond":[150],"labels,":[152],"improving":[153],"interpretability.":[157],"further":[159],"examined":[160],"feature-count":[161],"sensitivity,":[162],"showing":[163],"how":[164],"numbers":[167],"relate":[168],"underfitting":[170],"or":[171],"noise-driven":[172],"overfitting.":[173],"By":[174],"balancing":[175],"scalability,":[176],"accuracy,":[177],"interpretability,":[179],"offers":[181],"new":[183,192],"lens":[184],"classification":[188],"sets":[190],"standard":[193],"data-driven,":[195],"heterogeneity-aware":[196],"analysis.":[197]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-20T00:00:00"}
