{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:43:55Z","timestamp":1783417435274,"version":"3.54.6"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"NIAID","doi-asserted-by":"publisher","award":["R01AI14180"],"award-info":[{"award-number":["R01AI14180"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010514","name":"SCH","doi-asserted-by":"publisher","award":["INT-2013998"],"award-info":[{"award-number":["INT-2013998"]}],"id":[{"id":"10.13039\/100010514","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence and Complex Computational Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Antibiotic resistance in Mycobacterium tuberculosis (MTB) poses a significant challenge to global public health. Rapid and accurate prediction of antibiotic resistance can inform treatment strategies and mitigate the spread of resistant strains. In this study, we present a novel approach leveraging large language models (LLMs) to predict antibiotic resistance in MTB (LLMTB). Our model is trained and evaluated on genomic data from 12\u00a0185 CRyPTIC isolates and their associated resistance profiles, utilizing natural language processing techniques to capture patterns and mutations linked to resistance. The model\u2019s architecture integrates state-of-the-art transformer-based LLMs, enabling the analysis of complex genomic sequences and the extraction of critical features relevant to antibiotic resistance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We evaluate our model\u2019s performance using a comprehensive dataset of MTB strains, demonstrating its ability to achieve high performance in predicting resistance to various antibiotics. Unlike traditional machine learning methods, fine-tuning or few-shot learning opens avenues for LLMs to adapt to new or emerging drugs, thereby reducing reliance on extensive data curation. Beyond predictive accuracy, LLMTB uncovers deeper biological insights, identifying critical genes, intergenic regions, and novel resistance mechanisms. This method marks a transformative shift in resistance prediction and offers significant potential for enhancing diagnostic capabilities and guiding personalized treatment plans, ultimately contributing to the global effort to combat tuberculosis and antibiotic resistance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All source code is publicly available at https:\/\/github.com\/ctestagrose\/LLMTB.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf232","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:54Z","timestamp":1752584574000},"page":"i40-i48","source":"Crossref","is-referenced-by-count":4,"title":["Leveraging large language models to predict antibiotic resistance in <i>Mycobacterium tuberculosis<\/i>"],"prefix":"10.1093","volume":"41","author":[{"given":"Conrad","family":"Testagrose","sequence":"first","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , Gainesville, FL 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sakshi","family":"Pandey","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , Gainesville, FL 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammadali","family":"Serajian","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , Gainesville, FL 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-3533","authenticated-orcid":false,"given":"Simone","family":"Marini","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , Gainesville, FL 32601,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9021-5595","authenticated-orcid":false,"given":"Mattia","family":"Prosperi","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , Gainesville, FL 32601,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Boucher","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , Gainesville, FL 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509024509700_btaf232-B1","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1128\/aac.42.5.1295","article-title":"Mechanisms of resistance to amikacin and kanamycin in mycobacterium tuberculosis","volume":"42","author":"Alangaden","year":"1998","journal-title":"Antimicrob Agents Chemother"},{"key":"2025071509024509700_btaf232-B2","doi-asserted-by":"publisher","author":"Ansel","year":"2024","DOI":"10.1145\/3620665.3640366"},{"key":"2025071509024509700_btaf232-B3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/1476-0711-4-9","article-title":"Acquisition of rifabutin resistance by a rifampicin resistant mutant of Mycobacterium tuberculosis involves an unusual spectrum of mutations and elevated frequency","volume":"4","author":"Anthony","year":"2005","journal-title":"Ann Clin Microbiol Antimicrob"},{"key":"2025071509024509700_btaf232-B4","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1089\/cmb.2012","article-title":"SPAdes: a new genome assembly algorithm and its applications to Single-Cell sequencing","volume":"19","author":"Bankevich","year":"2012","journal-title":"J Comput Biol"},{"key":"2025071509024509700_btaf232-B5","doi-asserted-by":"crossref","first-page":"3491","DOI":"10.1093\/jac\/dkaa345","article-title":"ResFinder 4.0 for predictions of phenotypes from genotypes","volume":"75","author":"Bortolaia","year":"2020","journal-title":"J Antimicrob Chemother"},{"key":"2025071509024509700_btaf232-B6","doi-asserted-by":"publisher","first-page":"80","DOI":"10.4161\/fly.19695","article-title":"A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3","volume":"6","author":"Cingolani","year":"2012","journal-title":"Fly (Austin)"},{"key":"2025071509024509700_btaf232-B7","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1186\/s12859-018-2336-6","article-title":"Rapid and precise alignment of raw reads against redundant databases with kma","volume":"19","author":"Clausen","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2025071509024509700_btaf232-B8","author":"Devlin","year":"2019"},{"key":"2025071509024509700_btaf232-B9","doi-asserted-by":"publisher","author":"Garrison","year":"2012","DOI":"10.48550\/arXiv.1207.3907"},{"key":"2025071509024509700_btaf232-B10","doi-asserted-by":"publisher","first-page":"2107","DOI":"10.1093\/jac\/dks178","article-title":"Role of eis mutations in the development of kanamycin resistance in Mycobacterium tuberculosis isolates from the Moscow region","volume":"67","author":"Gikalo","year":"2012","journal-title":"J Antimicrob Chemother"},{"key":"2025071509024509700_btaf232-B11","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1054\/drup.1998.0068","article-title":"Mechanisms of fluoroquinolone resistance","volume":"2","author":"Hooper","year":"1999","journal-title":"Drug Resist Updat"},{"key":"2025071509024509700_btaf232-B12","doi-asserted-by":"crossref","first-page":"191","DOI":"10.12688\/wellcomeopenres.15603.1","article-title":"Antibiotic resistance prediction for Mycobacterium tuberculosis from genome sequence data with mykrobe","volume":"4","author":"Hunt","year":"2019","journal-title":"Wellcome Open Res"},{"key":"2025071509024509700_btaf232-B13","first-page":"656","article-title":"BLAT\u2014the BLAST-like alignment tool","volume":"12","author":"Kent","year":"2002","journal-title":"Genome Res"},{"key":"2025071509024509700_btaf232-B14","doi-asserted-by":"publisher","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: the DrugBank knowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025071509024509700_btaf232-B15","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1093\/bioinformatics\/btr509","article-title":"A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2025071509024509700_btaf232-B16","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2025071509024509700_btaf232-B17","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with burrows\u2013wheeler transform","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2025071509024509700_btaf232-B18","doi-asserted-by":"publisher","author":"Loshchilov","year":"2017","DOI":"10.48550\/arXiv.1608.03983"},{"key":"2025071509024509700_btaf232-B19","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The genome analysis toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2025071509024509700_btaf232-B20","doi-asserted-by":"publisher","author":"Miyato","year":"2016","DOI":"10.48550\/arXiv.1605.07725"},{"key":"2025071509024509700_btaf232-B21","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1093\/cid\/cix992","article-title":"Bedaquiline resistance: its emergence, mechanism, and prevention","volume":"66","author":"Nguyen","year":"2018","journal-title":"Clin Infect Dis"},{"key":"2025071509024509700_btaf232-B22","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13073-019-0650-x","article-title":"Integrating informatics tools and portable sequencing technology for rapid detection of resistance to anti-tuberculous drugs","volume":"11","author":"Phelan","year":"2019","journal-title":"Genome Med"},{"key":"2025071509024509700_btaf232-B23","doi-asserted-by":"publisher","author":"Procop","DOI":"10.1128\/microbiolspec.TNMI7-0022-2016"},{"key":"2025071509024509700_btaf232-B24","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1007\/BF01691135","article-title":"Significance of ahpC promoter mutations for the prediction of isoniazid resistance in Mycobacterium tuberculosis","volume":"17","author":"Rinder","year":"1998","journal-title":"Eur J Clin Microbiol Infect Dis"},{"key":"2025071509024509700_btaf232-B25","first-page":"2980","author":"Ross","year":"2017"},{"key":"2025071509024509700_btaf232-B26","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.cmi.2016.10.022","article-title":"Mycobacterium tuberculosis drug-resistance testing: challenges, recent developments and perspectives","volume":"23","author":"Sch\u00f6n","year":"2017","journal-title":"Clin Microbiol Infect"},{"key":"2025071509024509700_btaf232-B27","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1016\/j.cmi.2020.07.036","article-title":"Antimicrobial susceptibility testing of Mycobacterium tuberculosis complex isolates\u2014the EUCAST broth microdilution reference method for MIC determination","volume":"26","author":"Sch\u00f6n","year":"2020","journal-title":"Clin Microbiol Infect"},{"key":"2025071509024509700_btaf232-B28","doi-asserted-by":"crossref","first-page":"2068","DOI":"10.1093\/bioinformatics\/btu153","article-title":"Prokka: rapid prokaryotic genome annotation","volume":"30","author":"Seemann","year":"2014","journal-title":"Bioinformatics"},{"key":"2025071509024509700_btaf232-B29","doi-asserted-by":"crossref","first-page":"i39","DOI":"10.1093\/bioinformatics\/btae243","article-title":"Scalable de novo classification of antibiotic resistance of mycobacterium tuberculosis","volume":"40","author":"Serajian","year":"2024","journal-title":"Bioinformatics"},{"key":"2025071509024509700_btaf232-B30","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1186\/1471-2164-15-881","article-title":"KvarQ: targeted and direct variant calling from fastq reads of bacterial genomes","volume":"15","author":"Steiner","year":"2014","journal-title":"BMC Genomics"},{"key":"2025071509024509700_btaf232-B31","doi-asserted-by":"crossref","first-page":"6614","DOI":"10.1093\/nar\/gkw569","article-title":"NCBI prokaryotic genome annotation pipeline","volume":"44","author":"Tatusova","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025071509024509700_btaf232-B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pbio.3001721","article-title":"A data compendium associating the genomes of 12,289 Mycobacterium tuberculosis isolates with quantitative resistance phenotypes to 13 antibiotics","volume":"20","author":"The CRyPTIC Consortium","year":"2022","journal-title":"PLOS Biol"},{"key":"2025071509024509700_btaf232-B33","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1056\/NEJMoa1800474","article-title":"Prediction of susceptibility to first-line tuberculosis drugs by DNA sequencing","volume":"379","author":"Allix-B\u00e9guec","year":"2018","journal-title":"New England J Med"},{"key":"2025071509024509700_btaf232-B34","author":"Vaswani","year":"2017"},{"key":"2025071509024509700_btaf232-B35","doi-asserted-by":"crossref","first-page":"e112963","DOI":"10.1371\/journal.pone.0112963","article-title":"Pilon: an integrated tool for comprehensive microbial variant detection and genome assembly improvement","volume":"9","author":"Walker","year":"2014","journal-title":"PLoS ONE"},{"key":"2025071509024509700_btaf232-B36","doi-asserted-by":"crossref","first-page":"11189","DOI":"10.1093\/nar\/gks918","article-title":"LoFreq: a sequence-quality aware, ultra-sensitive variant caller for uncovering cell-population heterogeneity from high-throughput sequencing datasets","volume":"40","author":"Wilm","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2025071509024509700_btaf232-B37","doi-asserted-by":"crossref","first-page":"2796","DOI":"10.1038\/ncomms3796","article-title":"VapC20 of Mycobacterium tuberculosis cleaves the sarcin\u2013ricin loop of 23S rRNA and mediates translation arrest","volume":"4","author":"Winther","year":"2013","journal-title":"Nature Commun"},{"key":"2025071509024509700_btaf232-B38","volume-title":"Catalogue of Mutations in Mycobacterium tuberculosis Complex and Their Association with Drug Resistance","author":"World Health Organization","year":"2021"},{"key":"2025071509024509700_btaf232-B39","author":"World Health Organization","year":"2023"},{"key":"2025071509024509700_btaf232-B40","volume-title":"Global Tuberculosis Report 2024","author":"World Health Organization","year":"2024"},{"key":"2025071509024509700_btaf232-B41","doi-asserted-by":"crossref","first-page":"2764","DOI":"10.1093\/jac\/dkx217","article-title":"PointFinder: a novel web tool for WGS-based detection of antimicrobial resistance associated with chromosomal point mutations in bacterial pathogens","volume":"72","author":"Zankari","year":"2017","journal-title":"J Antimicrob Chemother"},{"key":"2025071509024509700_btaf232-B42","doi-asserted-by":"publisher","first-page":"20004","DOI":"10.1073\/pnas.0907925106","article-title":"Overexpression of the chromosomally encoded aminoglycoside acetyltransferase eis confers kanamycin resistance in Mycobacterium tuberculosis","volume":"106","author":"Zaunbrecher","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025071509024509700_btaf232-B43","doi-asserted-by":"crossref","first-page":"20004","DOI":"10.1073\/pnas.0907925106","article-title":"Overexpression of the chromosomally encoded aminoglycoside acetyltransferase eis confers kanamycin resistance in mycobacterium tuberculosis","volume":"106","author":"Zaunbrecher","year":"2009","journal-title":"Proc Natl Acad Sci USA"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i40\/63745704\/btaf232.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i40\/63745704\/btaf232.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:59Z","timestamp":1752584579000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i40\/8199408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":43,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf232","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}