Leveraging large language models to predict antibiotic resistance in Mycobacterium tuberculosis
Bioinformatics · 01.07.2025 · 41 (Supplement_1) · i40-i48
DOI: 10.1093/bioinformatics/btaf232 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.07.2025. Verfasst von Conrad Testagrose und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, United States. Hauptthemen laut MEDLINE: Mycobacterium tuberculosis, Natural Language Processing, Drug Resistance, Bacterial. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, NIH, Artificial Intelligence and Complex Computational Research.
Abstract (Originalsprache)
Motivation 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 12 185 CRyPTIC isolates and their associated resistance profiles, utilizing natural language processing techniques to capture patterns and mutations linked to resistance. The model’s 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. Results We evaluate our model’s 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. Availability and implementation All source code is publicly available at https://github.com/ctestagrose/LLMTB.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, United States.
- Department of Epidemiology, University of Florida, Gainesville, FL 32601, United States.
ORCID-Profile: Simone Marini, Mattia Prosperi
Förderung
- NIAID NIH HHS
- NIH
- Artificial Intelligence and Complex Computational Research
- NSF
- SCH
- NIAID
Zitieren
APA
Testagrose, C., Pandey, S., Serajian, M., Marini, S., Prosperi, M., & Boucher, C. (2025). Leveraging large language models to predict antibiotic resistance in Mycobacterium tuberculosis. Bioinformatics, 41(Supplement_1), i40-i48. https://doi.org/10.1093/bioinformatics/btaf232
Vancouver
Testagrose C, Pandey S, Serajian M, Marini S, Prosperi M, Boucher C. Leveraging large language models to predict antibiotic resistance in Mycobacterium tuberculosis. Bioinformatics. 2025;41(Supplement_1):i40-i48. doi:10.1093/bioinformatics/btaf232
BibTeX
@article{Testagrose2025,
author = {Testagrose, Conrad and Pandey, Sakshi and Serajian, Mohammadali and Marini, Simone and Prosperi, Mattia and Boucher, Christina},
title = {Leveraging large language models to predict antibiotic resistance in Mycobacterium tuberculosis},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {Supplement_1},
pages = {i40--i48},
doi = {10.1093/bioinformatics/btaf232}
}
EUVIMED