AlphaFold cracked the code of protein structure. The next major frontier is decoding the dynamic behavior of the living cell itself. A fundamental challenge in modern biology is that of precise, engineered cellular control. Cells possess their own language for communicating with each other -- cell signaling -- which directs core biological processes like development and is frequently dysregulated in disease. Remarkably, biology achieves this complexity using a surprisingly concise vocabulary: only around 20 fundamental molecular signaling pathways have been identified to date. It is the combinations and orders in which they are used that underlies how such a small number of pathways can give rise to the staggering diversity of human cell types and states. In principle, because these pathways are readily manipulated by small molecules, they provide a potent mechanism through which we could control cellular decision-making. However, despite decades of effort, we have not yet deciphered the grammar of this language. Today, the effects of a given signal are largely determined through an empirical, trial-and-error process -- due to two compounding challenges: combinatorial complexity and context dependence. This talk outlines Cellular Intelligence's solution: the construction of the first Universal Virtual Cell-Signaling Model, a platform intended to compute how any cell state will change in response to external signals. By combining the paradigm of developmental biology -- nature's own proving ground -- with our proprietary multiplexing platform, we transform cell signaling from an empirical art into an engineering discipline built for therapeutic design. We aim to unlock high-impact applications: from guided cell therapies that replace lost tissues, to context-specific drug response prediction, to new ways of modeling disease as signaling network failures. Our goal is to understand, predict, and ultimately control cellular behavior.

As we move toward the “virtual cell” and ultimately the “virtual organism,” the AIxBIO ecosystem faces a fundamental challenge: where does biology actually compute? While our ability to measure molecular events has advanced dramatically, predicting how those signals translate into emergent, system-level outcomes remains a core bottleneck in programmable biology. This session brings together leaders across AI, synthetic biology, and medicine to explore the computational bottleneck, mapping where predictive power breaks down from molecules to cells to organisms. It will examine how to measure emergence at scale by generating causal, time-resolved, perturbation-rich datasets across diverse biological contexts, and how to close the reality gap with in vivo feedback, using next-generation sensors and real-world data to continuously calibrate and validate models in living systems.