- Preprint Article
- 10.21203/rs.3.rs-8779521/v1
Hybrid Deep Learning–Based Rapid Broad-Spectrum Antimicrobial Susceptibility Testing from Whole-Genome Assemblies
- Feb 05, 2026
- Research Square
- Linda Osaghale + 4 more +4
Abstract Antimicrobial resistance (AMR) is a global public health threat. Mortality and poor treatment outcomes are the hallmark consequences of AMR. Conventional antimicrobial susceptibility testing (AST) is slow, limited in coverage, and dependent on laboratory infrastructure, creating delays in clinical decision-making. In this study, we developed a hybrid deep learning framework for broad-spectrum antimicrobial resistance prediction by analyzing bacterial genome assemblies and paired antimicrobial susceptibility outcomes. Genome assemblies were encoded using 6-mer frequency representations and engineering antimicrobial susceptibility phenotypes into genome–antibiotic pairs for binary prediction. The proposed model integrates convolutional neural networks (CNNs) for local sequence feature extraction, bidirectional long short-term memory (BiLSTM) networks to capture long-range genomic dependencies, and an attention mechanism to improve interpretability. Model evaluation achieved an accuracy of 0.71 and AUROC of 0.77 at a resistance decision threshold of 0.55, with balanced accuracy of 0.70 and AUPRC of 0.49. The results demonstrate variable predictive performance across antibiotics and organism groups, supporting the need for subgroup-level evaluation and threshold tuning. This study demonstrates that a hybrid CNN–BiLSTM–Attention model can rapidly predict antimicrobial resistance from genome-derived k-mer features while incorporating organism and antibiotic metadata for broad-spectrum AST prediction. The framework provides a scalable approach for genome-based susceptibility prediction and supports further development toward clinically deployable AMR decision-support tools.
Read more