Smart process development: Application of machine-learning and integrated process modeling for inclusion body purification processes.

The development of a biopharmaceutical production process usually occurs sequentially, and tedious optimization of each individual unit operation is very time-consuming. Here, the conditions established as optimal for one-step serve as input for the following step. Yet, this strategy does not consider potential interactions between a priori distant process steps and therefore cannot guarantee for optimal overall process performance. To overcome these limitations, we established a smart approach to develop and utilize integrated process models using machine learning techniques and genetic algorithms. We evaluated the application of the data-driven models to explore potential efficiency increases and compared them to a conventional development approach for one of our development products. First, we developed a data-driven integrated process model using gradient boosting machines and Gaussian processes as machine learning techniques and a genetic algorithm as recommendation engine for two downstream unit operations, namely solubilization and refolding. Through projection of the results into our large-scale facility, we predicted a twofold increase in productivity. Second, we extended the model to a three-step model by including the capture chromatography. Here, depending on the selected baseline-process chosen for comparison, we obtained between 50% and 100% increase in productivity. These data show the successful application of machine learning techniques and optimization algorithms for downstream process development. Finally, our results highlight the importance of considering integrated process models for the whole process chain, including all unit operations.

Implementation of a Fully Automated Microbial Cultivation Platform for Strain and Process Screening.

Advances in molecular biotechnology have resulted in the generation of numerous potential production strains. Because every strain can be screened under various process conditions, the number of potential cultivations is multiplied. Exploiting this potential without increasing the associated timelines requires a cultivation platform that offers increased throughput and flexibility to perform various bioprocess screening protocols. Currently, there is no commercially available fully automated cultivation platform that can operate multiple microbial fed-batch processes, including at-line sampling, deep freezer off-line sample storage, and complete data handling. To enable scalable high-throughput early-stage microbial bioprocess development, a commercially available microbioreactor system and a laboratory robot are combined to develop a fully automated cultivation platform. By making numerous modifications, as well as supplementation with custom-built hardware and software, fully automated milliliter-scale microbial fed-batch cultivation, sample handling, and data storage are realized. The initial results of cultivations with two different expression systems and three different process conditions are compared using 5 L scale benchmark cultivations, which provide identical rankings of expression systems and process conditions. Thus, fully automated high-throughput cultivation, including automated centralized data storage to significantly accelerate the identification of the optimal expression systems and process conditions, offers the potential for automated early-stage bioprocess development.