Computational models are essential tools that can be used to simultaneously explain and guide biological intuition. With increasingly high-resolution, high-throughput, and dynamic experimental data, computational biologists are better equipped to develop informed models that aim to characterize complex cellular responses and direct experimental design. My lab operates at this evolving interface between chemical engineering and biology; we employ machine learning, dynamical systems, and agent-based modeling strategies to help explain biological observations, and to elucidate design principles that drive both individual cellular decisions and cell populations. In this presentation, I provide an overview of how machine learning can be used to resolve cell signaling pathways. I also introduce an agent-based model as an intuitive, modular, and flexible framework to study emergence of heterogeneous cell populations in context of solid tumor microenvironments. We use this framework to interrogate the inherent multiscale nature of cells—reinforcing how “the whole is greater than the sum of its parts”—and to predict cell population dynamics from the composition of simpler biological modules.