Improving extracellular vesicles production through a Bayesian optimization-based experimental design

Process development for the production of mesenchymal stromal cell-derived extracellular vesicles in conventional 2D systems

BACKGROUND

In recent years, the importance of extracellular vesicles (EVs) derived from mesenchymal stromal cells (MSCs) has increased significantly. For their widespread use, a standardized EV manufacturing is needed which often includes conventional, static 2D systems. For these system critical process parameters need to be determined.

METHODS

We studied the impact of process parameters on MSC proliferation, MSC-derived particle production including EVs, EV- and MSC-specific marker expression, and particle functionality in a HaCaT cell migration assay.

RESULTS

We found that cell culture growth surface and media affected MSCs and their secretory behavior. Interestingly, the materials that promoted MSC proliferation did not necessarily result in the most functional MSC-derived particles. In addition, we found that MSCs seeded at 4 × 103 cells cm-2 produced particles with improved functional properties compared to higher seeding densities. MSCs in a highly proliferative state did not produce the most particles, although these particles were significantly more effective in promoting HaCaT cell migration. The same correlation was found when investigating the cultivation temperature. A physiological temperature of 37°C was not optimal for particle yield, although it resulted in the most functional particles. We observed a proliferation-associated particle production and found potential correlations between particle production and glucose consumption, enabling the estimation of final particle yields.

CONCLUSIONS

Our findings suggest that parameters, which must be defined prior to each individual cultivation and do not require complex and expensive equipment, can significantly increase MSC-derived particle production including EVs. Integrating these parameters into a standardized EV process development paves the way for robust and efficient EV manufacturing for early clinical phases.

Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses

Modern machine learning has the potential to fundamentally change the way bioprocesses are developed. In particular, horizontal knowledge transfer methods, which seek to exploit data from historical processes to facilitate process development for a new product, provide an opportunity to rethink current workflows. In this work, we first assess the potential of two knowledge transfer approaches, meta learning and one-hot encoding, in combination with Gaussian process (GP) models. We compare their performance with GPs trained only on data of the new process, that is, local models. Using simulated mammalian cell culture data, we observe that both knowledge transfer approaches exhibit test set errors that are approximately halved compared to those of the local models when two, four, or eight experiments of the new product are used for training. Subsequently, we address the question whether experiments for a new product could be designed more effectively by exploiting existing knowledge. In particular, we suggest to specifically design a few runs for the novel product to calibrate knowledge transfer models, a task that we coin calibration design. We propose a customized objective function to identify a set of calibration design runs, which exploits differences in the process evolution of historical products. In two simulated case studies, we observed that training with calibration designs yields similar test set errors compared to common design of experiments approaches. However, the former requires approximately four times fewer experiments. Overall, the results suggest that process development could be significantly streamlined when systematically carrying knowledge from one product to the next.

Bayesian cell therapy process optimization

Optimizing complex bioprocesses poses a significant challenge in several fields, particularly in cell therapy manufacturing. The development of customized, closed, and automated processes is crucial for their industrial translation and for addressing large patient populations at a sustainable price. Limited understanding of the underlying biological mechanisms, coupled with highly resource-intensive experimentation, are two contributing factors that make the development of these next-generation processes challenging. Bayesian optimization (BO) is an iterative experimental design methodology that addresses these challenges, but has not been extensively tested in situations that require parallel experimentation with significant experimental variability. In this study, we present an evaluation of noisy, parallel BO for increasing noise levels and parallel batch sizes on two in silico bioprocesses, and compare it to the industry state-of-the-art. As an in vitro showcase, we apply the method to the optimization of a monocyte purification unit operation. The in silico results show that BO significantly outperforms the state-of-the-art, requiring approximately 50% fewer experiments on average. This study highlights the potential of noisy, parallel BO as valuable tool for cell therapy process development and optimization.