Enhanced diagnosis of multi-drug-resistant microbes using group association modeling and machine learning
Open Access
- 25 March 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-15
Abstract
New solutions are needed to detect genotype-phenotype associations involved in microbial drug resistance. Herein, we describe a Group Association Model (GAM) that accurately identifies genetic variants linked to drug resistance and mitigates false-positive cross-resistance artifacts without prior knowledge. GAM analysis of 7,179 Mycobacterium tuberculosis (Mtb) isolates identifies gene targets for all analyzed drugs, revealing comparable performance but fewer cross-resistance artifacts than World Health Organization (WHO) mutation catalogue approach, which requires expert rules and precedents. GAM also reveals generalizability, demonstrating high predictive accuracy with 3,942 S. aureus isolates. GAM refinement by machine learning (ML) improves predictive accuracy with small or incomplete datasets. These findings were validated using 427 Mtb isolates from three sites, where GAM inputs are also found to be more suitable in ML prediction models than WHO inputs. GAM + ML could thus address the limitations of current drug resistance prediction methods to improve treatment decisions for drug-resistant microbial infections.Keywords
This publication has 54 references indexed in Scilit:
- Comparative performance of microbiological methods for the detection of tuberculous meningitis pathogens in cerebrospinal fluidDiagnostic Microbiology and Infectious Disease, 2023
- Beyond GWAS: from simple associations to functional insightsSeminars in Immunopathology, 2021
- Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics dataComputers in Biology and Medicine, 2020
- Replicability and Prediction: Lessons and Challenges from GWASTrends in Genetics, 2018
- Prevalence of mutations in genes associated with rifampicin and isoniazid resistance in Mycobacterium tuberculosis clinical isolatesJournal of Clinical Tuberculosis and Other Mycobacterial Diseases, 2017
- Genome-wide association and genomic prediction of resistance to maize lethal necrosis disease in tropical maize germplasmTheoretical and Applied Genetics, 2015
- The heterogeneous evolution of multidrug-resistant Mycobacterium tuberculosisTrends in Genetics, 2013
- Resistance to Antibiotics: Are We in the Post-Antibiotic Era?Archives of Medical Research, 2005
- Predictive non-linear modeling of complex data by artificial neural networksCurrent Opinion in Biotechnology, 2002
- Antibiotic resistance in microbesCellular and Molecular Life Sciences, 1999