IRG 2. Machine Learning-Enhanced Design and Automated Assembly of Architected Microgels and Vesicles for Biotechnology
Lead: David J. Mooney
Co-Lead: David A. Weitz
Primary Faculty Participants: Joanna Aizenberg, Katia Bertoldi, Michael P. Brenner, Jennifer A. Lewis, David R. Nelson, Kevin (Kit) Parker, and Zhigang Suo
This IRG will establish the design rules, ML models, and microfluidic-based AE platforms needed to rapidly create architected microgels and vesicles for biotechnology applications, including cell encapsulation, enzyme screening, drug delivery, and bioprinting.
To carry out the research, we bring together a multidisciplinary research team composed of faculty members from applied mathematics, biology, physics, chemistry, earth and planetary science, soft matter physics, and mechanical engineering with deep expertise in soft materials assembly (Lewis, Weitz, Whitesides), fracture mechanics (Holbrook, Rice, Suo), 4D confocal imaging and materials characterization (Spaepen, Vlassak), machine learning and computer simulation (Brenner, Colwell, Denolle, Frenkel, Kozinsky), and theory (Nelson) to focus on three goals that exploit data-driven science (Figure 1).
- Understand crystal nucleation in single and multi-component hard-sphere systems and use the knowledge gained to develop new routes for creating alloys.
- Investigate collective dislocation motion that underlies plastic deformation of materials.
- Explore fracture phenomena in mechanically soft systems to understand their toughening, dissipation, and failure mechanisms.