DMREF: Machine Learning-Enhanced Design and Scalable Manufacturing of Architected Hydrogel Composites with Tunable Properties

Non-Technical Description: This DMREF project focuses on the synthesis, assembly, and modeling of hydrogel materials that exhibit tunable flow behavior and mechanics during applied shear and quiescent conditions, respectively. The soft materials under study are of interest for in situ transcatheter bioprinting, an emerging biofabrication method under development for infilling patient-specific tissue defects without open surgical intervention. By integrating artificial intelligence (AI) with experiments, the research team seeks to establish a fundamental knowledge base to guide the design, synthesis, and development of hydrogel composites with controlled flow behavior and mechanics for in situ bioprinting. These foundational advances are enabling emerging biotechnology applications focused on customized tissue engineering, repair, and regeneration. Another central activity is the creation of the next generation of leaders in AI-driven materials design, discovery, and translation that enhance US competitiveness in biotechnology. Finally, education, outreach, and workforce development activities are spanning K-12, undergraduate, and graduate students, as well as the public. These activities introduce cutting-edge AI, materials science, and biotechnology advances through museum exhibits, research experiences for undergraduates, Rising Stars symposia for graduate students, and public lectures. Technical Description: This research focuses on creating machine-learning (ML) computational tools in concert with an experimental framework that guides the rational design, discovery, and deployment of hydrogel composites for in situ transcatheter bioprinting. The primary focus is to unravel the complex interplay between a highly coupled, multifaceted set of processing-structure-property (PSP) relations for this emerging class of biomaterials. Building upon this foundational understanding, the team seeks to create hydrogel matrices with controlled flow behavior, viscoelastic properties, multiscale porosity evolution, and mechanics for transcatheter bioprinting. Tabular Foundation Models (TFMs) are deployed in an iterative, human-in-the-loop structure for both predictive and generative computational tasks, including hydrogel composite design and data augmentation, predictive modeling of complex PSP relationships, and conditional inverse design of application-specific composites with quantified uncertainty. These predictive design tools guide the synthesis and in situ transcatheter printing of soft modular biomaterials for deep tissue repair, improving patient outcomes for emerging biotechnology applications. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.