Search

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.

Efficient development for multistep downstream processing of biopharmaceuticals depends on fast and robust transfer from bench to manufacturing-scale. Equivalence tests are used to assess the impact of changes in product quality and quantity during process development, optimization and production. This article presents the results of a simulation study comparing the impact of sample sizes, data distributions, variances and equivalence acceptance criteria (EAC) on the performance of equivalence tests. Our results show that a sample size of at least four in the reference group was the minimum recommended size to obtain an acceptable overall performance. Reference data should be evaluated for outliers prior to the equivalence tests and reliable test decisions are only taken with a low variance in the data of the reference group using the EAC proposed by Limentani. Considering these recommendations we obtained a reliable product yield comparability after chromatographic purification of a biopharmaceutical in bench and manufacturing-scale.