Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 3 min ago
Peer-reviewedCC BY-NC-NDhLife

LARGE: A large language model-based tool that unveils high-resolution temporal dynamics of the antibiotic resistome during human aging

  • Hang He1
  • Chenrui Duan2
  • Kui Deng3
  • Chang Su4
  • Zelei Miao5
  • Ke Zhang5
  • Yonghe Xia6
  • Jiahao Hong7
  • Yue Xi3
  • Yimin Zhu8
  • Dan Zhou8
  • Huijun Wang4
3 more authors
  • Yu-Ming Chen9
  • Stan Z. Li10
  • Ju-Sheng Zheng
10 affiliations
  1. 1Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Zhejiang, China
  2. 2School of Engineering, Westlake University, Zhejiang, China
  3. 3Guangdong Provincial Key Laboratory of Food, Nutrition and Health, Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangdong, China
  4. 4National Institute for Nutrition and Health, Chinese Center for Disease Control and Prevention, Beijing, China; Key Laboratory of Public Nutrition and Health, National Health Commission of the People's Republic of China, Beijing, China
  5. 5Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Zhejiang, China; Zhejiang Key Laboratory of Multi-Omics in Infection and Immunity, School of Medicine, Westlake University, Zhejiang, China
  6. 6Research Center for Industries of the Future, School of Life Sciences, Westlake University, Zhejiang, China
  7. 7School of Automation, Hangzhou Dianzi University, Zhejiang, China
  8. 8The Second Affiliated Hospital, School of Public Health, Zhejiang University School of Medicine, Zhejiang, China; The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang, China
  9. 9Guangdong Provincial Key Laboratory of Food, Nutrition and Health, Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangdong, China; Correspondence:
  10. 10School of Engineering, Westlake University, Zhejiang, China; Correspondence:
Read full textDOICite

Abstract

The gut microbiome undergoes profound changes during aging, including shifts in the microbial antibiotic resistome: the collective repertoire of antibiotic resistance genes (ARGs). We developed a language model-based ARG explorer (LARGE, https://large.lab.westlake.edu.cn ), which uses frozen ESM-2 and FGeneBERT encoders to embed protein sequences and three independent multilayer perceptron classifiers to predict resistance type, mechanism, and gene name. LARGE was trained on 34,008 ARG and 30,309 non-ARG sequences from the NCRD95 and UniProt databases and benchmarked against DeepARG, Resistance Gene Identifier (RGI), PLM-ARG, and ARGNet using F1-scores on multiple independent test sets. We applied LARGE to a longitudinal cohort (Guangzhou Nutrition and Health Study, n = 1078, mean baseline age 64.6 years) and validated key findings in independent cohorts (China Health and Nutrition Survey, n = 356; Zhejiang Metabolic Syndrome Cohort, n = 1361). Linear mixed-effects models were used to assess age-related ARG trajectories, and logistic regression examined associations with 13 chronic diseases. In benchmark testing, LARGE substantially outperformed all four tools, achieving superior F1-scores. In longitudinal cohorts, LARGE revealed declining ARG burdens in dominant resistance drug classes and identified 31 species with significant ARG changes. The ARGs of these 31 species were closely associated with multiple age-related chronic diseases, such as chronic kidney disease and coronary heart disease; a specific chronic kidney disease ARG score was consistently associated with disease risk in both discovery and validation cohorts. These findings highlight the pivotal role of aging in resistome evolution and potentially provide microbiome-targeted interventions to mitigate antibiotic resistance and promote healthy aging.

Related

  1. Chicken farming may influence the gut antibiotic resistome and microbiome of workers: a metagenomic analysis
    Yuqing Hao, Yuan Li, Ying Wang +3
    Animal MicrobiomePeer-reviewedCC BY-NC-ND 4.0Full textInfectious diseasePMC
  2. resLens: genomic language models to enhance antibiotic resistance gene detection
    Matthew Mollerus, Katharina Dittmar, Keith A. Crandall +1
    npj Antimicrobials and ResistancePeer-reviewedCC BY-NC-NDFull text6 citedGeneral medicineOpenAlex
  3. Salmonella aortitis without surgery or fluoroquinolones: Complete resolution with sequential antibiotic therapy
    Andrew Kim, Dinasha Navindi, Junho Kwon +4
    IDCasesPeer-reviewedCC BY-NC-ND 4.0Full textSurgery & anaesthesiaPMC
  4. Knowledge-Guided Large Language Model for Automatic Pediatric Dental Record Understanding and Safe Antibiotic Recommendation
    Zihan Han, Zhitao Shu, Caifeng Li
    Fundamental Scientific Reports in Multidisciplinary AreasPeer-reviewedCC BYFull text19 citedEpidemiology & public healthOpenAlex
  5. Bern Sleep-Wake Registry: temporal extraction of comorbidities from unstructured clinical text using a large language model
    I. Filchenko, F. Dennstaedt, K. Zub +6
    medRxivPreprintAll rights reservedFull textNeurologymedRxiv

Cite

BibTeXRIS
BibTeX
@article{he2026large,
  title = {{LARGE: A large language model-based tool that unveils high-resolution temporal dynamics of the antibiotic resistome during human aging}},
  author = {Hang He and Chenrui Duan and Kui Deng and Chang Su and Zelei Miao and Ke Zhang and Yonghe Xia and Jiahao Hong and Yue Xi and Yimin Zhu and Dan Zhou and Huijun Wang and Yu-Ming Chen and Stan Z. Li and Ju-Sheng Zheng},
  journal = {hLife},
  year = {2026},
  month = oct,
  doi = {10.1016/j.hlife.2026.08.002},
  url = {https://doi.org/10.1016/j.hlife.2026.08.002},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - LARGE: A large language model-based tool that unveils high-resolution temporal dynamics of the antibiotic resistome during human aging
AU  - Hang He
AU  - Chenrui Duan
AU  - Kui Deng
AU  - Chang Su
AU  - Zelei Miao
AU  - Ke Zhang
AU  - Yonghe Xia
AU  - Jiahao Hong
AU  - Yue Xi
AU  - Yimin Zhu
AU  - Dan Zhou
AU  - Huijun Wang
AU  - Yu-Ming Chen
AU  - Stan Z. Li
AU  - Ju-Sheng Zheng
PY  - 2026
DA  - 2026/10/24
JO  - hLife
DO  - 10.1016/j.hlife.2026.08.002
UR  - https://doi.org/10.1016/j.hlife.2026.08.002
AB  - The gut microbiome undergoes profound changes during aging, including shifts in the microbial antibiotic resistome: the collective repertoire of antibiotic resistance genes (ARGs). We developed a language model-based ARG explorer (LARGE, https://large.lab.westlake.edu.cn ), which uses frozen ESM-2 and FGeneBERT encoders to embed protein sequences and three independent multilayer perceptron classifiers to predict resistance type, mechanism, and gene name. LARGE was trained on 34,008 ARG and 30,309 non-ARG sequences from the NCRD95 and UniProt databases and benchmarked against DeepARG, Resistance Gene Identifier (RGI), PLM-ARG, and ARGNet using F1-scores on multiple independent test sets. We applied LARGE to a longitudinal cohort (Guangzhou Nutrition and Health Study, n = 1078, mean baseline age 64.6 years) and validated key findings in independent cohorts (China Health and Nutrition Survey, n = 356; Zhejiang Metabolic Syndrome Cohort, n = 1361). Linear mixed-effects models were used to assess age-related ARG trajectories, and logistic regression examined associations with 13 chronic diseases. In benchmark testing, LARGE substantially outperformed all four tools, achieving superior F1-scores. In longitudinal cohorts, LARGE revealed declining ARG burdens in dominant resistance drug classes and identified 31 species with significant ARG changes. The ARGs of these 31 species were closely associated with multiple age-related chronic diseases, such as chronic kidney disease and coronary heart disease; a specific chronic kidney disease ARG score was consistently associated with disease risk in both discovery and validation cohorts. These findings highlight the pivotal role of aging in resistome evolution and potentially provide microbiome-targeted interventions to mitigate antibiotic resistance and promote healthy aging.
SN  - 2949-9283
ER  -