The structural context of mutations in proteins predicts their effect on antibiotic resistance.
- 1Department of Biomedical Informatics, Harvard Medical School, Boston, United States.
- 2Manning College of Information and Computer Sciences, University of Massachusetts, Amherst, United States.
- 3Division of Pulmonary & Critical Care, Massachusetts General Hospital, Boston, United States.
Abstract
In Mycobacterium tuberculosis, a prevalent and deadly pathogen, resistance to antibiotics evolves primarily through non-synonymous mutations in proteins. Sequence-based analyses can uncover the genetic basis of antibiotic resistance, but these methods focus on primary sequence and often neglect other biological signals, such as protein structural information. We hypothesize that integrating the structural context of mutations improves the prediction of effects on function and phenotype. We curate high-confidence structural annotations for the M. tuberculosis proteome from 1350 crystallography and 2337 AlphaFold predictions, and mutations from over 31,000 M. tuberculosis isolates. We demonstrate that mutations in proteins known to cause resistance are clustered in 3D space, even in proteins where inactivating mutations at any position are thought to cause resistance. We find over 450 proteins in the M. tuberculosis proteome that display signals of clustered mutations, many of which have a known relationship with antibiotic resistance. We show that a supervised classifier trained on 3D distance to known resistance sites alone has an F1 score of 96.5% at classifying mutations as resistance-conferring on a held-out test set. This work demonstrates that protein structure provides useful information for categorizing which variants may cause antibiotic resistance, even when the majority of structures are AI-predicted.
Related
- Generic context-dependence governs clonal emergence of ciprofloxacin resistance mutations
- SMARCA4 MUTATIONS PROMOTE CHEMOTHERAPY RESISTANCE IN T-ACUTE LYMPHOBLASTIC LEUKEMIA THROUGH ALTERED CHROMATIN REMODELING AT AP1-ASSOCIATED REGULATORY REGIONS
- Knowledge and misconceptions about antibiotic use and antibiotic resistance among secondary school students in Riyadh, Saudi Arabia: implications for school- based antibiotic resistance education
- Metabolic signature of phosphoethanolamine and arginine pathways predicts prognosis and immunotherapy resistance in lung adenocarcinoma
- Machine learning predicts diuretic resistance via cardio hepato renal axis in heart failure comorbid with MASLD
BibTeX
@article{green2026structural,
title = {{The structural context of mutations in proteins predicts their effect on antibiotic resistance.}},
author = {Anna G Green and Mahbuba Tasmin and Roger Vargas and Maha Reda Farhat},
journal = {ELife},
year = {2026},
month = oct,
doi = {10.7554/elife.109450},
url = {https://europepmc.org/article/MED/42852653},
note = {CC BY},
}
RIS
TY - JOUR
TI - The structural context of mutations in proteins predicts their effect on antibiotic resistance.
AU - Anna G Green
AU - Mahbuba Tasmin
AU - Roger Vargas
AU - Maha Reda Farhat
PY - 2026
DA - 2026/10/09
JO - ELife
DO - 10.7554/elife.109450
UR - https://europepmc.org/article/MED/42852653
AB - In Mycobacterium tuberculosis, a prevalent and deadly pathogen, resistance to antibiotics evolves primarily through non-synonymous mutations in proteins. Sequence-based analyses can uncover the genetic basis of antibiotic resistance, but these methods focus on primary sequence and often neglect other biological signals, such as protein structural information. We hypothesize that integrating the structural context of mutations improves the prediction of effects on function and phenotype. We curate high-confidence structural annotations for the M. tuberculosis proteome from 1350 crystallography and 2337 AlphaFold predictions, and mutations from over 31,000 M. tuberculosis isolates. We demonstrate that mutations in proteins known to cause resistance are clustered in 3D space, even in proteins where inactivating mutations at any position are thought to cause resistance. We find over 450 proteins in the M. tuberculosis proteome that display signals of clustered mutations, many of which have a known relationship with antibiotic resistance. We show that a supervised classifier trained on 3D distance to known resistance sites alone has an F1 score of 96.5% at classifying mutations as resistance-conferring on a held-out test set. This work demonstrates that protein structure provides useful information for categorizing which variants may cause antibiotic resistance, even when the majority of structures are AI-predicted.
SN - 2050-084X
ER -