Recent advances in generative AI and large-scale biological data are enabling a new paradigm for understanding living systems. In this talk, I will discuss our efforts toward building “virtual cells”, AI systems capable of modeling and predicting cellular behaviour across diverse biological contexts. I will present our work on scGPT, one of the first foundation models for single-cell biology, which demonstrated how transformer-based architectures trained on millions of cells can learn transferable representations of cellular states and gene programs across datasets and tasks. I will then discuss our recent work at Xaira Therapeutics on X-Cell, a large-scale virtual cell model trained on genome-wide perturbation datasets to predict cellular responses to genetic interventions in unseen biological contexts. X-Cell represents an important step from descriptive biological models toward causal and predictive cellular simulation. Finally, I will introduce emerging directions in biological reasoning systems such as BioReason, which integrate genomic foundation models with large language models to generate interpretable mechanistic hypotheses and support scientific discovery. Together, these efforts point toward a future in which AI-powered virtual cells enable in silico experimentation, accelerate therapeutic discovery, and transform our ability to understand and engineer biology.