Multi-omics-driven predictive modelling of antimicrobial resistance emergence in African food value chains under climate change scenarios

Antimicrobial resistance (AMR) poses a critical threat to food safety, particularly in African food systems where surveillance infrastructure is limited and climate change is accelerating microbial adaptation. Traditional microbiological risk assessment approaches fail to capture the biological complexity of AMR emergence across food value chains. This study developed an integrated multi-omics and machine learning framework to predict AMR emergence across Nigerian food value chains under projected climate scenarios. A cross-sectional study was conducted across Delta, Benin, and Port Harcourt, collecting 487 food and 192 environmental samples. Multi-omics profiling encompassing genomics, metagenomics, transcriptomics, proteomics, and metabolomics was integrated with CMIP6 climate projections. Machine learning algorithms including XGBoost, Random Forest, and Support Vector Machines were trained and externally validated using explainable AI methods. Quantitative microbial risk assessment incorporated omics-derived parameters. XGBoost achieved superior performance (AUROC 0.942, sensitivity 0.91, specificity 0.89), representing a 16.3% improvement over single-omics approaches. Beta-lactamase and tetracycline resistance genes predominated, with carbapenemase genes detected in 8.6% of samples. Temperature was the strongest predictor of ARG abundance (β = 0.42). Climate projections indicated 47–82% increases in Vibrio prevalence under SSP5–8.5. This framework enables predictive, climate-resilient food safety surveillance, supporting evidence-based decision making and One Health governance in low- and middle-income countries.