Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 11 min ago
Peer-reviewedCC BY-NC-NDnpj Antimicrobials and Resistance

resLens: genomic language models to enhance antibiotic resistance gene detection

  • Matthew Mollerus1
  • Katharina Dittmar1
  • Keith A. Crandall1
  • Ali Rahnavard2
  1. 1Computational Biology Institute, Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, The George Washington University, Washington, DC, USA
  2. 2Computational Biology Institute, Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, The George Washington University, Washington, DC, USA. [email protected]
Open at sourcePDFDOICite

Abstract

The rise of antibiotic resistance necessitates advanced tools to detect and analyze antibiotic resistance genes (ARGs). We present resLens, a family of genomic language models that leverage latent genomic representations to enhance ARG detection and analysis. Unlike alignment-based methods constrained by reference databases, resLens fine-tunes a pre-trained DNA language model on curated ARG datasets, achieving competitive or superior performance in classifying resistance genes across multiple evaluation scenarios, including when ARGs exhibit sequences and mechanisms of resistance dissimilar to those in reference datasets.

Related

  1. Resolving the Genomic Context of Clinically Relevant Antibiotic Resistance Genes in Wastewater with Ligation-Mediated PCR
    M. E. O'Brien, B. Ahern, P. Brase +12
    medRxivPreprintCC BYFull textEpidemiology & public healthmedRxiv
  2. Molecular Detection Technologies for Helicobacter pylori Antibiotic Resistance: Current Status and Clinical Implications.
    Zhenyu Wang, Jun Lin, Xuanni Zhang +3
    Current microbiologyPeer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaEurope PMC
  3. Knowledge and misconceptions about antibiotic use and antibiotic resistance among secondary school students in Riyadh, Saudi Arabia: implications for school- based antibiotic resistance education
    Sarah R. Alharbi, Lama Alzamil, Sara Alfaqeeh +4
    Frontiers in public healthPeer-reviewedCC BYFull textEpidemiology & public healthEurope PMC
  4. Beliefs and Behaviours related to Antibiotic Use and Antimicrobial Resistance in Poland: General Population Survey
    I. Palacz-Poborczyk, J. Kuzminska, A. Luszczynska +1
    medRxivPreprintAll rights reservedFull text1 citedEpidemiology & public healthmedRxiv
  5. Collateral effects of bacteriophage resistance on antibiotic sensitivity in Pseudomonas aeruginosa
    L. R. Baars, K. Nagel, L. B. Zwep +2
    bioRxivPreprintAll rights reservedFull textPharmacology & toxicologybioRxiv

Cite

BibTeXRIS
BibTeX
@article{mollerus2026reslens,
  title = {{resLens: genomic language models to enhance antibiotic resistance gene detection}},
  author = {Matthew Mollerus and Katharina Dittmar and Keith A. Crandall and Ali Rahnavard},
  journal = {npj Antimicrobials and Resistance},
  year = {2026},
  month = may,
  doi = {10.1038/s44259-026-00219-2},
  url = {https://doi.org/10.1038/s44259-026-00219-2},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - resLens: genomic language models to enhance antibiotic resistance gene detection
AU  - Matthew Mollerus
AU  - Katharina Dittmar
AU  - Keith A. Crandall
AU  - Ali Rahnavard
PY  - 2026
DA  - 2026/05/21
JO  - npj Antimicrobials and Resistance
DO  - 10.1038/s44259-026-00219-2
UR  - https://doi.org/10.1038/s44259-026-00219-2
AB  - The rise of antibiotic resistance necessitates advanced tools to detect and analyze antibiotic resistance genes (ARGs). We present resLens, a family of genomic language models that leverage latent genomic representations to enhance ARG detection and analysis. Unlike alignment-based methods constrained by reference databases, resLens fine-tunes a pre-trained DNA language model on curated ARG datasets, achieving competitive or superior performance in classifying resistance genes across multiple evaluation scenarios, including when ARGs exhibit sequences and mechanisms of resistance dissimilar to those in reference datasets.
SN  - 2731-8745
ER  -