Arc Institute's Patrick Hsu on Building an App Store for Biology with AI

Summary

Arc Institute’s Patrick Hsu on Building an App Store for Biology with AI Patrick Hsu, co-founder of Arc Institute, discusses the opportunities for AI in biology beyond just drug development, and how Evo 2, their new biology foundation model, is enabling a broad ecosystem of applications. Evo 2 was trained on a vast dataset of genomic data to learn evolutionary patterns that would have taken years to find; as a result, the model can be used for applications from identifying mutations that cause disease to designing new molecular and even genome scale biological systems. Listen Now Summary Patrick Hsu, co-founder of the Arc Institute and Berkeley professor of bioengineering, brings a unique perspective on the convergence of AI and biology, emphasizing that machine learning’s potential extends far beyond drug discovery to understanding and programming fundamental biological systems. His insights reflect both the immediate possibilities and long-term vision for how AI will transform our understanding of life itself. - AI can model biological systems by learning from evolution’s natural experiments: The ability to predict the functional consequences of genetic mutations—from disease-causing variants to subtle physiological changes—represents a fundamental shift in how we can understand and manipulate biology. - Biology needs better predictive models: AI models like Evo 2 can overcome the time-consuming “guess and check” paradigm that dominates current research. While wet lab validation remains essential, AI models that can accurately simulate biological systems could dramatically accelerate the scientific process by allowing parallel testing of thousands of hypotheses. - The future of medicine will require integrating multiple data streams: Personalized health predictions and interventions will require learning from genetics as well as real-time biomarkers. Current fragmented approaches need to evolve into systems that can holistically model the interconnections between brain, body and behavior. - Success in computational biology requires true bilingual expertise: Arc Institute looks for people who deeply understand both machine learning and biological systems. While specialists in either field are common, the ability to bridge these domains and identify meaningful connections is rare but essential for breakthrough innovations. - Drug discovery is not the bottle…