Researchers from Columbia University and the Chan Zuckerberg Initiative have developed GREmLN, an AI-based virtual cell model that captures complex gene regulatory networks. Utilizing graph-based architectures, GREmLN outperforms previous models by reflecting biological causality rather than linear sequences, enhancing gene expression prediction and cell classification. Separately, Microsoft Research introduced BioEmu, a deep learning system accelerating protein dynamic simulations with accuracy comparable to traditional methods. These advances promise to transform target identification, therapeutics development, and understanding of cellular behavior in health and disease.