Standard bioreactors often lack the instrumentation required to rapidly monitor cell physiology, leaving critical gaps in our understanding of scale-up dynamics. This session presents active projects from the Schmidt Sciences’ Sensors for Biomanufacturing Program designed to address this challenge through novel sensing modalities. Spanning from near real-time intracellular measurements to non-invasive off-gas fingerprinting, the panel brings together technology developers and industrial bioprocess experts to discuss the translation of these tools from the lab to the plant floor. Together, we will critically evaluate the utility of high-dimensional metabolic data and explore the engineering requirements for integrating physics-based sensors and machine learning into existing biomanufacturing workflows.

Berkeley Lab develops new automation approaches to produce the large amounts of high-quality data that AI needs to solve significant problems in biology and enable new biomanufacturing capabilities. The Lab uses HTP approaches to generate AI-ready data and leverages that data in AI models to design microbial pathways, engineer host systems, optimize media formulations, generate functional plasmid origins, engineer plant transcriptional regulation, and predict solvent properties. The Lab's process development unit aims to generate complex biological data needed for virtual cell and other models by algorithm development companies.