{"id":"https://openalex.org/W7171589076","doi":"https://doi.org/10.1145/3807503.3816808","title":"An application of genomic language models for antimicrobial resistance prediction in S. pneumoniae","display_name":"An application of genomic language models for antimicrobial resistance prediction in S. pneumoniae","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171589076","doi":"https://doi.org/10.1145/3807503.3816808"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3816808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816808","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3816808","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044296196","display_name":"Michael Aaron Sy","orcid":"https://orcid.org/0000-0001-9281-7592"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Sy","raw_affiliation_strings":["Epidemiology, University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0001-9281-7592","affiliations":[{"raw_affiliation_string":"Epidemiology, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126606079","display_name":"Tiancheng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiancheng Zhou","raw_affiliation_strings":["Department of Epidemiology, University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0009-0002-2667-3353","affiliations":[{"raw_affiliation_string":"Department of Epidemiology, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123747369","display_name":"Toni Betiku","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toni Betiku","raw_affiliation_strings":["University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0009-0004-4130-1261","affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068650337","display_name":"Daniel M. Czy\u017c","orcid":"https://orcid.org/0000-0002-7491-5292"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Czyz","raw_affiliation_strings":["Department of Microbiology and Cell Science, University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-7491-5292","affiliations":[{"raw_affiliation_string":"Department of Microbiology and Cell Science, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040939546","display_name":"Vidhu Kariyawasam","orcid":"https://orcid.org/0000-0003-3895-5673"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vidhu Kariyawasam","raw_affiliation_strings":["Division of Infectious Diseases and Global Medicine, University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-3895-5673","affiliations":[{"raw_affiliation_string":"Division of Infectious Diseases and Global Medicine, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004394877","display_name":"Simone Marini","orcid":"https://orcid.org/0000-0002-5704-3533"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simone Marini","raw_affiliation_strings":["Epidemiology, University of Florida, Gainesville, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-5704-3533","affiliations":[{"raw_affiliation_string":"Epidemiology, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/antibiotic-resistance","display_name":"Antibiotic resistance","score":0.4260999858379364},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.32440000772476196},{"id":"https://openalex.org/keywords/antimicrobial","display_name":"Antimicrobial","score":0.3212999999523163},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.31040000915527344},{"id":"https://openalex.org/keywords/acquired-resistance","display_name":"Acquired resistance","score":0.26899999380111694}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5246999859809875},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C94665300","wikidata":"https://www.wikidata.org/wiki/Q63391344","display_name":"Antibiotic resistance","level":3,"score":0.4260999858379364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4228000044822693},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.32440000772476196},{"id":"https://openalex.org/C4937899","wikidata":"https://www.wikidata.org/wiki/Q68541106","display_name":"Antimicrobial","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C2994294914","wikidata":"https://www.wikidata.org/wiki/Q1645075","display_name":"Acquired resistance","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C114851261","wikidata":"https://www.wikidata.org/wiki/Q12147416","display_name":"Drug resistance","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3816808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816808","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3816808","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3816808","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G157821705","display_name":null,"funder_award_id":"101807","funder_id":"https://openalex.org/F4320332932","funder_display_name":"Merck Sharp and Dohme"}],"funders":[{"id":"https://openalex.org/F4320332932","display_name":"Merck Sharp and Dohme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Lower":[0],"respiratory":[1],"tract":[2],"infections":[3],"remain":[4],"the":[5,47,74,104,122,169],"leading":[6],"cause":[7],"of":[8,25,131,137,168],"infection-related":[9],"deaths":[10,21],"globally,":[11],"with":[12,57,79],"Streptococcus":[13],"pneumoniae":[14,45],"pneumonia":[15],"accounting":[16],"for":[17,31,40,53,152],"over":[18],"1.25":[19],"million":[20],"annually.":[22],"Accurate":[23],"prediction":[24,42],"antibiotic":[26],"resistance":[27],"(AMR)":[28],"is":[29,174],"critical":[30],"appropriate":[32],"treatment":[33],"selection.":[34],"We":[35,61,156],"present":[36],"a":[37,128,175],"novel":[38],"approach":[39],"AMR":[41],"in":[43],"S.":[44],"leveraging":[46],"Hyena":[48,106],"genomic":[49,71,111,117],"language":[50],"model,":[51,107],"designed":[52],"long":[54],"sequences,":[55],"combined":[56],"deep":[58,159],"set":[59,136,160,172],"learning.":[60],"developed":[62],"two":[63],"antibiotic-based":[64],"predictive":[65],"models":[66,165],"based":[67],"on":[68],"publicly":[69],"available":[70,120],"data":[72,118,154],"from":[73,100,166],"Global":[75],"Pneumococcal":[76],"Sequencing":[77],"Project,":[78],"samples":[80],"labeled":[81],"as":[82],"Resistant":[83],"(R)":[84],"or":[85],"Susceptible":[86],"(S).":[87],"Specifically,":[88],"we":[89],"considered":[90],"Chloramphenicol":[91],"and":[92,148],"Clindamycin":[93],"(Table":[94],"1).":[95],"Genomic":[96],"embeddings":[97,181],"were":[98,119],"extracted":[99],"contig-level":[101],"assemblies":[102],"using":[103],"pre-trained":[105],"which":[108],"captures":[109],"long-range":[110],"dependencies":[112],"at":[113,121],"single-nucleotide":[114],"resolution.":[115],"As":[116],"contig":[123,180],"level,":[124],"each":[125,167],"sample":[126],"yielded":[127],"variable":[129],"number":[130],"embeddings,":[132],"i.e.,":[133],"an":[134],"unordered":[135],"embedding":[138],"vectors.":[139],"Traditional":[140],"machine":[141],"learning":[142,161,173],"approaches":[143],"require":[144],"fixed-length":[145],"feature":[146],"vectors,":[147],"are":[149],"therefore":[150,157],"ill-suited":[151],"this":[153],"format.":[155],"employed":[158],"architecture":[162],"to":[163],"learn":[164],"sets:":[170],"Deep":[171],"permutation-invariant":[176],"framework":[177],"aggregating":[178],"variable-length":[179],"into":[182],"sample-level":[183],"predictions":[184],"while":[185],"preserving":[186],"biologically":[187],"relevant":[188],"information.":[189]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}