Accelerating the design of lattice structures using machine learning.

Lattices remain an attractive class of structures due to their design versatility; however, rapidly designing lattice structures with tailored or optimal mechanical properties remains a significant challenge. With each added design variable, the design space quickly becomes intractable. To address this challenge, research efforts have sought to combine computational approaches with machine learning (ML)-based approaches to reduce the computational cost of the design process and accelerate mechanical design. While these efforts have made substantial progress, significant challenges remain in (1) building and interpreting the ML-based surrogate models and (2) iteratively and efficiently curating training datasets for optimization tasks. Here, we address the first challenge by combining ML-based surrogate modeling and Shapley additive explanation (SHAP) analysis to interpret the impact of each design variable. We find that our ML-based surrogate models achieve excellent prediction capabilities (R2 > 0.95) and SHAP values aid in uncovering design variables influencing performance. We address the second challenge by utilizing active learning-based methods, such as Bayesian optimization, to explore the design space and report a 5 × reduction in simulations relative to grid-based search. Collectively, these results underscore the value of building intelligent design systems that leverage ML-based methods for uncovering key design variables and accelerating design.

A perfused multi-well bioreactor platform to assess tumor organoid response to a chemotherapeutic gradient.

There is an urgent need to develop new therapies for colorectal cancer that has metastasized to the liver and, more fundamentally, to develop improved preclinical platforms of colorectal cancer liver metastases (CRCLM) to screen therapies for efficacy. To this end, we developed a multi-well perfusable bioreactor capable of monitoring CRCLM patient-derived organoid response to a chemotherapeutic gradient. CRCLM patient-derived organoids were cultured in the multi-well bioreactor for 7 days and the subsequently established gradient in 5-fluorouracil (5-FU) concentration resulted in a lower IC50 in the region near the perfusion channel versus the region far from the channel. We compared behaviour of organoids in this platform to two commonly used PDO culture models: organoids in media and organoids in a static (no perfusion) hydrogel. The bioreactor IC50 values were significantly higher than IC50 values for organoids cultured in media whereas only the IC50 for organoids far from the channel were significantly different than organoids cultured in the static hydrogel condition. Using finite element simulations, we showed that the total dose delivered, calculated using area under the curve (AUC) was similar between platforms, however normalized viability was lower for the organoid in media condition than in the static gel and bioreactor. Our results highlight the utility of our multi-well bioreactor for studying organoid response to chemical gradients and demonstrate that comparing drug response across these different platforms is nontrivial.