(395n) Integrating Theoretical and AI-Approaches for Protein Engineering Education

With the rapid advancements in AI-driven protein design revolutionizing the fields of biomolecular engineering, particularly in therapeutics, industrial biocatalysis, and energy and sustainability, there is an increasing demand for enhanced pedagogical strategies to improve student learning in this dynamic landscape. To prepare students for effective engagement with these cutting-edge tools and concepts, it is crucial to implement innovative, research-based teaching approaches that connect foundational knowledge with real-world applications. In response, I have developed a graduate-level protein engineering course designed to incorporate a range of forward-thinking pedagogical strategies in AI-driven protein engineering, with the goal of deepening students' understanding of core principles and strengthening their ability to apply this knowledge to address practical, real-world challenges. To effectively disseminate knowledge of AI-driven protein engineering to students, I introduced key topics during the spring semester, including protein structure, folding, and engineering techniques, with an emphasis on directed evolution, rational design, and AI-aided design strategies. The course incorporated hands-on training modules featuring advanced tools such as MPNN, RFDiffusion, RFDiffusionAll-Atom, ChimeraX and AlphaFold 3, allowing students to visualize, predict, and optimize protein structures in real-time. Throughout the semester, students worked in teams to develop innovative protein engineering project proposals, which were presented and evaluated by an external review committee. Additional learning strategies included the analysis of case studies, journal club presentations, and student-led design challenges focused on solving real-world problems in biotechnology, sustainability and pharmaceuticals. These activities aimed to foster collaborative problem-solving and critical thinking, enhancing students' ability to apply theoretical knowledge to practical applications. Through this multi-faceted approach, students exhibited a thorough understanding of fundamental protein engineering principles and contemporary AI-assisted design tools. They successfully applied their knowledge in collaborative projects, critically analyzed real-world applications through case studies, and engaged with current research in journal clubs. The final project presentations showcased both technical expertise and creativity, demonstrating the effectiveness of the course structure in fostering knowledge acquisition and promoting translational problem-solving skills. In conclusion, the incorporation of hands-on AI tools, collaborative projects, and research-based learning in this graduate-level course greatly enhanced students conceptual understanding. It also empowered them to apply protein engineering strategies to address real-world challenges, underscoring the value of an innovative, integrated approach to education in this rapidly advancing field.