An accurate and interpretable model to predict antimicrobial resistance in One Health settings

Understanding the genomic contributors to antimicrobial resistance (AMR) is essential for early detection of emerging AMR infections, a pressing global health threat in human and veterinary medicine. Here, whole genome sequencing and antibiotic susceptibility test data from Escherichia coli were used to identify AMR genotypes and phenotypes for 24 antibiotics. We test the strength of estimated genotype-to-phenotype relationships for 288 AMR genes and associated plasmid replicons with elastic net logistic regression. Model predictors were selected to evaluate different potential modes of AMR genotype translation into resistance phenotypes. We demonstrate that genotypes can be used to accurately predict resistance phenotypes, and there are unique predictors of resistance for different antibiotics within the same class. A model considering the presence of individual genes, total number of genes, a binary indicator of AMR gene group, and host animal most accurately predicted isolate resistance across all tested antibiotics (mean F 1 score = 98%, mean accuracy = 98.2%). ### Competing Interest Statement The authors have declared no competing interest.