Biologics and engineered proteins have traditionally evolved through cycles of intuition, screening, and incremental optimization. Today, AI is transforming proteins into programmable systems; governed by learnable patterns across activity, stability, expression, specificity, manufacturability, and environmental performance. This shift is unlocking a new generation of biomolecules, from next-generation therapeutics to sustainable enzymes and functional biological systems, that would have been impossible to design by hand. In this session, leaders from biopharma, industrial biotech, machine learning, and protein engineering will explore how multiparameter optimization, generative modeling, and closed-loop experimental validation are reshaping biomolecular design across domains. From clinical biologics to planetary-scale applications, we examine the shift from trial-and-error to predictive, constraint-driven design, and what it means for R&D timelines, scalability, and real-world impact.

AI is rapidly transforming how therapeutic enzymes and protein drug candidates are discovered, engineered, and validated. Generative models can now propose millions of novel variants optimized for specificity, stability, and target engagement. But the true bottleneck is no longer design, it is screening at scale. As model-generated libraries expand exponentially, the need for faster, more predictive experimental systems has become critical to translate computational insights into clinically relevant performance. This session explores the emerging generation of integrated platforms that combine AI-guided design, high-throughput functional screening, automation, and advanced analytics to accelerate therapeutic protein discovery. From self-driving labs and multiplexed cellular assays to adaptive screening strategies that prioritize pharmacologically meaningful readouts over simple activity metrics, speakers will examine how next-gen infrastructure is reshaping enzyme optimization for drug development.