{"id":"https://openalex.org/W4409157277","doi":"https://doi.org/10.1109/bibm62325.2024.10947604","title":"Toward Fine-Tuning Large Language Models in Ontology of Microbial Phenotypes Construction","display_name":"Toward Fine-Tuning Large Language Models in Ontology of Microbial Phenotypes Construction","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4409157277","doi":"https://doi.org/10.1109/bibm62325.2024.10947604"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10947604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10947604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5084219000","display_name":"Anushuya Baidya","orcid":"https://orcid.org/0000-0002-1613-9862"},"institutions":[{"id":"https://openalex.org/I189957204","display_name":"University of South Dakota","ror":"https://ror.org/0043h8f16","country_code":"US","type":"education","lineage":["https://openalex.org/I189957204"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anushuya Baidya","raw_affiliation_strings":["University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA"],"affiliations":[{"raw_affiliation_string":"University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA","institution_ids":["https://openalex.org/I189957204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036103687","display_name":"Tuyen Do","orcid":"https://orcid.org/0000-0002-1817-4565"},"institutions":[{"id":"https://openalex.org/I189957204","display_name":"University of South Dakota","ror":"https://ror.org/0043h8f16","country_code":"US","type":"education","lineage":["https://openalex.org/I189957204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuyen Do","raw_affiliation_strings":["University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA"],"affiliations":[{"raw_affiliation_string":"University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA","institution_ids":["https://openalex.org/I189957204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003549657","display_name":"Etienne Z. Gnimpi\u00e9ba","orcid":"https://orcid.org/0000-0002-5338-084X"},"institutions":[{"id":"https://openalex.org/I189957204","display_name":"University of South Dakota","ror":"https://ror.org/0043h8f16","country_code":"US","type":"education","lineage":["https://openalex.org/I189957204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Etienne Z. Gnimpieba","raw_affiliation_strings":["University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA"],"affiliations":[{"raw_affiliation_string":"University of South Dakota,Dept. of Biomedical Engineering,Vermillion,SD,USA","institution_ids":["https://openalex.org/I189957204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084219000"],"corresponding_institution_ids":["https://openalex.org/I189957204"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22847263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6913","last_page":"6920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9829000234603882,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9829000234603882,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9136000275611877,"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/computer-science","display_name":"Computer science","score":0.7075925469398499},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.6602694988250732},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4065777659416199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3569839298725128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075925469398499},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6602694988250732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4065777659416199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3569839298725128},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10947604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10947604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2115294179","https://openalex.org/W2261812172","https://openalex.org/W2548195627","https://openalex.org/W2911262481","https://openalex.org/W2963026768","https://openalex.org/W2965373594","https://openalex.org/W2970476646","https://openalex.org/W2979826702","https://openalex.org/W4385245566","https://openalex.org/W4385485146","https://openalex.org/W4388144297","https://openalex.org/W4390971125","https://openalex.org/W4390971148","https://openalex.org/W4390992049","https://openalex.org/W6606796992","https://openalex.org/W6689832025","https://openalex.org/W6757817989","https://openalex.org/W6768851824","https://openalex.org/W6863813566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Ontologies":[0],"are":[1],"crucial":[2],"for":[3,110,115,120,137],"organizing":[4],"domainspecific":[5],"knowledge":[6],"in":[7,65,90],"biomedical":[8,66,154],"fields,":[9],"but":[10],"their":[11],"manual":[12],"construction":[13],"is":[14],"time-consuming.":[15],"This":[16,140],"study":[17],"explores":[18],"the":[19,36,75,143,164],"automation":[20],"of":[21,38,79,145,166],"ontology":[22,57,121,138,149],"learning":[23,150],"using":[24,95],"large":[25],"language":[26],"models":[27,97,127],"(LLMs)":[28],"like":[29,156],"BERT,":[30],"RoBERTa,":[31],"and":[32,55,68,77,82,98,118,133,151,160],"DistilBERT,":[33],"focusing":[34],"on":[35,103],"Ontology":[37],"Microbial":[39],"Phenotypes":[40],"(OMP).":[41],"We":[42,87],"investigate":[43],"three":[44],"key":[45,80],"tasks:":[46],"(1)":[47],"entity":[48,70,111],"extraction,":[49,112],"(2)":[50],"relation":[51,116],"extraction":[52],"between":[53],"entities,":[54],"(3)":[56],"verification.":[58,122,139],"These":[59],"tasks":[60],"align":[61],"with":[62],"broader":[63],"applications":[64,155],"annotation":[67],"named":[69],"recognition":[71],"(NER)":[72],"by":[73],"enabling":[74],"identification":[76],"structuring":[78],"terms":[81],"relationships":[83],"within":[84],"microbial":[85],"phenotypes.":[86],"evaluate":[88],"LLMs":[89,119,146],"two":[91],"scenarios:":[92],"baseline":[93],"performance":[94,100],"pre-trained":[96],"fine-tuned":[99,126],"after":[101],"training":[102],"OMP-specific":[104],"data.":[105],"Our":[106],"approach":[107],"integrates":[108],"spaCy":[109],"Llama":[113],"2":[114],"identification,":[117],"Experiments":[123],"reveal":[124],"that":[125],"significantly":[128],"improve":[129],"accuracy,":[130],"precision,":[131],"recall,":[132],"F1":[134],"scores,":[135],"particularly":[136],"research":[141],"highlights":[142],"potential":[144],"to":[147],"enhance":[148],"support":[152],"related":[153],"biofilm":[157],"analysis,":[158],"annotation,":[159],"NER,":[161],"while":[162],"emphasizing":[163],"value":[165],"expert":[167],"curation.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}