The exponential growth of multi-omics data, driven by advances in genome sequencing and metabolomics, poses significant challenges in systematically linking bacterial genotypes to metabolic phenotypes. I am particularly interested in data-integrative modeling projects like Predicting Bacterial Nutrient Metabolism, which aim to apply Machine Learning and LLM-based embeddings to map genomic features to nutrient utilization, improving the scalability of functional inference and the precision of personalized dietary interventions.