Process characterization is necessary in the biopharmaceutical industry, leading to concepts such as design of experiments (DoE) in combination with process modeling. However, these methods still have shortcomings, including large numbers of required experiments. The concept of intensified design of experiments (iDoE) is proposed, that is, intra‐experimental shifts of critical process parameters (CPP) that combine with hybrid modeling to more rapidly screen a particular design space. To demonstrate these advantages, a comprehensive experimental design of Escherichia coli (E. coli) fed‐batch cultivations (20 L) producing recombinant human superoxide dismutase is presented. The accuracy of hybrid models trained on iDoE and on a fractional‐factorial design is evaluated, without intra‐experimental shifts, to simultaneously predict the biomass concentration and product titer of the full‐factorial design. The hybrid model trained on data from the iDoE describes the biomass and product at each time point for the full‐factorial design with high and adequate accuracy. The fractional‐factorial hybrid model demonstrates inferior accuracy and precision compared to the intensified approach. Moreover, the intensified hybrid model only required one‐third of the data for model training compared to the full‐factorial description, resulting in a reduced experimental effort of >66%. Thus, this combinatorial approach has the potential to accelerate bioprocess characterization.

The fast exploration of a design space and identification of the best process conditions facilitating the highest space-time yield are of great interest for manufacturers. To obtain this information, depending on the design space, a large number of practical experiments must be performed, analyzed, and evaluated. To reduce this experimental effort and increase the process understanding, we evaluated a model-based design of experiments to rapidly identify the optimum process conditions in a design space maximizing space-time yield. From a small initial dataset, hybrid models were implemented and used as digital bioprocess twins, thus obtaining the recommended optimal experiment. In cases where these optimum conditions were not covered by existing data, the experiment was carried out and added to the initial data set, re-training the hybrid model. The procedure was repeated until the model gained certainty about the best process conditions, i.e., no new recommendations. To evaluate this workflow, we utilized different initial data sets and assessed their respective performances. The fastest approach for optimizing the space-time yield in a three-dimensional design space was found with five initial experiments. The digital twin gained certainty after four recommendations, leading to a significantly reduced experimental effort compared to other state-of-the-art approaches. This highlights the benefits of in silico design space exploration for accelerating knowledge-based bioprocess development, and reducing the number of hands-on experiments, time, energy, and raw materials.

Despite the advantages of mathematical bioprocess modeling, successful model implementation already starts with experimental planning and accordingly can fail at this early stage. For this study, two different modeling approaches (mechanistic and hybrid) based on a four‐dimensional antibody‐producing CHO fed‐batch process are compared. Overall, 33 experiments are performed in the fractional factorial four‐dimensional design space and separated into four different complex data partitions subsequently used for model comparison and evaluation. The mechanistic model demonstrates the advantage of prior knowledge (i.e., known equations) to get informative value relatively independently of the utilized data partition. The hybrid approach displayes a higher data dependency but simultaneously yielded a higher accuracy on all data partitions. Furthermore, our results demonstrate that independent of the chosen modeling framework, a smart selection of only four initial experiments can already yield a very good representation of a full design space independent of the chosen modeling structure. Academic and industry researchers are recommended to pay more attention to experimental planning to maximize the process understanding obtained from mathematical modeling.

Upstream bioprocess characterization and optimization are time and resource-intensive tasks. Regularly in the biopharmaceutical industry, statistical design of experiments (DoE) in combination with response surface models (RSMs) are used, neglecting the process trajectories and dynamics. Generating process understanding with time-resolved, dynamic process models allows to understand the impact of temporal deviations, production dynamics, and provides a better understanding of the process variations that stem from the biological subsystem. The authors propose to use DoE studies in combination with hybrid modeling for process characterization. This approach is showcased on Escherichia coli fed-batch cultivations at the 20L scale, evaluating the impact of three critical process parameters. The performance of a hybrid model is compared to a pure data-driven model and the widely adopted RSM of the process endpoints. Further, the performance of the time-resolved models to simultaneously predict biomass and titer is evaluated. The superior behavior of the hybrid model compared to the pure black-box approaches for process characterization is presented. The evaluation considers important criteria, such as the prediction accuracy of the biomass and titer endpoints as well as the time-resolved trajectories. This showcases the high potential of hybrid models for soft-sensing and model predictive control. The evaluation of a three-dimensional Escherichia coli design space, utilizing different modeling techniques, provides a comprehensive data basis to compare the advantages and limitations of different modeling approaches. Hybrid modeling has been proven to be superior compared to solely endpoint evaluation using design of experiments or black-box modeling, highlighting the potential of hybrid models for soft-sensing and model predictive control.

Reliable process development is accompanied by intense experimental effort. The utilization of an intensified design of experiments (iDoE) (intra-experimental critical process parameter (CPP) shifts combined) with hybrid modeling potentially reduces process development burden. The iDoE can provide more process response information in less overall process time, whereas hybrid modeling serves as a commodity to describe this behavior the best way. Therefore, a combination of both approaches appears beneficial for faster design screening and is especially of interest at larger scales where the costs per experiment rise significantly. Ideally, profound process knowledge is gathered at a small scale and only complemented with few validation experiments on a larger scale, saving valuable resources. In this work, the transferability of hybrid modeling for Chinese hamster ovary cell bioprocess development along process scales was investigated. A two-dimensional DoE was fully characterized in shake flask duplicates (300 ml), containing three different levels for the cultivation temperature and the glucose concentration in the feed. Based on these data, a hybrid model was developed, and its performance was assessed by estimating the viable cell concentration and product titer in 15 L bioprocesses with the same DoE settings. To challenge the modeling approach, 15 L bioprocesses also comprised iDoE runs with intra-experimental CPP shifts, impacting specific cell rates such as growth, consumption, and formation. Subsequently, the applicability of the iDoE cultivations to estimate static cultivations was also investigated. The shaker-scale hybrid model proved suitable for application to a 15 L scale (1:50), estimating the viable cell concentration and the product titer with an NRMSE of 10.92% and 17.79%, respectively. Additionally, the iDoE hybrid model performed comparably, displaying NRMSE values of 13.75% and 21.13%. The low errors when transferring the models from shaker to reactor and between the DoE and the iDoE approach highlight the suitability of hybrid modeling for mammalian cell culture bioprocess development and the potential of iDoE to accelerate process characterization and to improve process understanding.

The accurate estimation of cell growth or the substrate consumption rate is crucial for the understanding of the current state of a bioprocess. Rates unveil the actual cell status, making them valuable for quality-by-design concepts. However, in bioprocesses, the real rates are commonly not accessible due to analytical errors. We simulated Escherichia coli fed-batch fermentations, sampled at four different intervals and added five levels of noise to mimic analytical inaccuracy. We computed stepwise integral estimations with and without using moving average estimations, and smoothing spline interpolations to compare the accuracy and precision of each method to calculate the rates. We demonstrate that stepwise integration results in low accuracy and precision, especially at higher sampling frequencies. Contrary, a simple smoothing spline function displayed both the highest accuracy and precision regardless of the chosen sampling interval. Based on this, we tested three different options for substrate uptake rate estimations.