{"id":"https://openalex.org/W4417251069","doi":"https://doi.org/10.1109/bibe66822.2025.00069","title":"GeneticPieces2vec: Deep Learning Method for DNA Sequence Representation","display_name":"GeneticPieces2vec: Deep Learning Method for DNA Sequence Representation","publication_year":2025,"publication_date":"2025-11-06","ids":{"openalex":"https://openalex.org/W4417251069","doi":"https://doi.org/10.1109/bibe66822.2025.00069"},"language":null,"primary_location":{"id":"doi:10.1109/bibe66822.2025.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe66822.2025.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003768443","display_name":"Juan Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101058","display_name":"Palm Research Center","ror":"https://ror.org/0198za406","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210101058"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Juan Sebastian Malag\u00f3n Torres","raw_affiliation_strings":["Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia"],"affiliations":[{"raw_affiliation_string":"Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia","institution_ids":["https://openalex.org/I4210101058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049633442","display_name":"Sebasti\u00e1n Parra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101058","display_name":"Palm Research Center","ror":"https://ror.org/0198za406","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210101058"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Sebastian Ariza Parra","raw_affiliation_strings":["Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia"],"affiliations":[{"raw_affiliation_string":"Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia","institution_ids":["https://openalex.org/I4210101058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035301625","display_name":"David Rozo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101058","display_name":"Palm Research Center","ror":"https://ror.org/0198za406","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210101058"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"David Octavio Botero Rozo","raw_affiliation_strings":["Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia"],"affiliations":[{"raw_affiliation_string":"Systems biology team, Oil palm research center,Bogot&#x00E1;,Colombia","institution_ids":["https://openalex.org/I4210101058"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084451114","display_name":"Iv\u00e1n D\u00edaz","orcid":"https://orcid.org/0000-0001-9056-2047"},"institutions":[{"id":"https://openalex.org/I4210101058","display_name":"Palm Research Center","ror":"https://ror.org/0198za406","country_code":"ID","type":"facility","lineage":["https://openalex.org/I4210101058"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ivan Maurico Ayala Diaz","raw_affiliation_strings":["Biology and breeding group, Oil palm research center,Bogot&#x00E1;,Colombia"],"affiliations":[{"raw_affiliation_string":"Biology and breeding group, Oil palm research center,Bogot&#x00E1;,Colombia","institution_ids":["https://openalex.org/I4210101058"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003768443"],"corresponding_institution_ids":["https://openalex.org/I4210101058"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38138037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"373","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3887999951839447,"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":0.3887999951839447,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.31189998984336853,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.09139999747276306,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/representation","display_name":"Representation (politics)","score":0.6528000235557556},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5454999804496765},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4074000120162964},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.396699994802475},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.39239999651908875},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3878999948501587}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7330999970436096},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6528000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6198999881744385},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.39239999651908875},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.28940001130104065},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe66822.2025.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe66822.2025.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2043338013","https://openalex.org/W2119180969","https://openalex.org/W2158698691","https://openalex.org/W2313931749","https://openalex.org/W2626606138","https://openalex.org/W2911930496","https://openalex.org/W2952209472","https://openalex.org/W2963866978","https://openalex.org/W3003471562","https://openalex.org/W3092047717","https://openalex.org/W3182369052","https://openalex.org/W3206152519","https://openalex.org/W3211269552","https://openalex.org/W4205472758","https://openalex.org/W4220901655","https://openalex.org/W4225350157","https://openalex.org/W4285172194","https://openalex.org/W4307841610","https://openalex.org/W4310112262","https://openalex.org/W4378172771","https://openalex.org/W4378907379","https://openalex.org/W4389452928","https://openalex.org/W4389542870","https://openalex.org/W4390129347","https://openalex.org/W4393324833","https://openalex.org/W4400057149","https://openalex.org/W4404593891","https://openalex.org/W4405870017","https://openalex.org/W4406461044","https://openalex.org/W4407182771","https://openalex.org/W4409386715","https://openalex.org/W4410254428"],"related_works":[],"abstract_inverted_index":{"The":[0,114],"representation":[1,61],"of":[2,32,74,128],"genetic":[3],"information":[4],"plays":[5],"a":[6,60,138],"critical":[7],"role":[8],"in":[9,106,149],"predictive":[10,95],"and":[11,24,39,52,80,110,124],"explanatory":[12],"models":[13],"within":[14],"genomics.":[15],"Traditional":[16],"approaches":[17],"such":[18],"as":[19],"Genome-Wide":[20],"Association":[21],"Studies":[22],"(GWAS)":[23],"Genomic":[25],"Selection":[26],"(GS)":[27],"rely":[28],"on":[29,85],"discrete":[30],"encodings":[31],"variants,":[33],"often":[34],"overlooking":[35],"the":[36,91,125],"structural,":[37],"functional,":[38],"contextual":[40],"complexity":[41],"inherent":[42],"to":[43,142],"genomic":[44,82,108],"sequences.":[45],"This":[46],"limits":[47],"capturing":[48],"biologically":[49,139],"relevant":[50],"interactions":[51],"functional":[53],"signals.":[54],"In":[55],"response,":[56],"we":[57],"propose":[58],"GeneticPieces2Vec,":[59],"learning":[62],"model":[63,92],"inspired":[64],"by":[65],"natural":[66],"language":[67],"processing":[68],"techniques,":[69],"which":[70],"generates":[71],"low-dimensional":[72],"embeddings":[73,116],"gene":[75],"sequences":[76],"while":[77],"preserving":[78],"local":[79],"global":[81],"context.":[83],"Trained":[84],"6.4":[86],"million":[87],"oil":[88],"palm":[89],"sequences,":[90],"shows":[93],"high":[94],"accuracy":[96],"(<tex":[97],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{A":[99],"U":[100],"C}":[101],"\\boldsymbol{=}":[102],"\\mathbf{0.":[103],"9":[104],"6}$</tex>)":[105],"identifying":[107],"contexts":[109],"meaningful":[111],"biological":[112],"patterns.":[113],"resulting":[115],"exhibit":[117],"significant":[118],"associations":[119],"with":[120,146],"both":[121],"population":[122],"structure":[123],"physicochemical":[126],"properties":[127],"translated":[129],"amino":[130],"acids.":[131],"These":[132],"findings":[133],"suggest":[134],"that":[135],"GeneticPieces2Vec":[136],"offers":[137],"enriched":[140],"alternative":[141],"traditional":[143],"variant":[144,150],"calling,":[145],"promising":[147],"applications":[148],"analysis.":[151]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-11T00:00:00"}
