Abstract
The growing application of cell and gene therapies in humans leads to a need for cell type-optimized culture media. Design of Experiments (DoE) is a successful and well known tool for the development and optimization of cell culture media for bioprocessing. When optimizing culture media for primary cells used in cell and gene therapy, traditional DoE approaches that depend on interpretable models will not always provide reliable predictions due to high donor variability. Here we present the implementation of a machine learning pipeline into the DoE-based design of cell culture media to optimize T cell cultures in one experimental step (one-time optimization). We applied a definitive screening design from the DoE toolbox to screen 12 major media components, resulting in 25 (2k + 1) media formulations. T cells purified from a set of four human donors were cultured for 6 days and cell viability on day 3 and cell expansion on day 6 were recorded as response variables. These data were used as a training set in the machine learning pipeline. In the first step, individual models were created for each donor, evaluated and selected for each response variable, resulting in eight final statistical models (R2 > 0.92, RMSE < 1.5). These statistical models were used to predict T cell viability and expansion for 105 random in silico-generated media formulations for each donor in a grid search approach. With the aim of identifying similar formulations in all donors, the 40 best performing media formulations of each response variable were pooled from all donors (n = 320) and subjected to unsupervised clustering using the k-means algorithm. The median of each media component in each cluster was defined as the cluster media formulation. When these formulations were tested in a new set of donor cells, they not only showed a higher T cell expansion than the reference medium, but also precisely matched the average expansion predicted from the donor models of the training set. In summary, we have shown that the introduction of a machine learning pipeline resulted in a one-time optimized T cell culture medium and is advantageous when working with heterogeneous biological material.
Highlights
In autologous cell therapy approaches, cells from a given patient are isolated, may be genetically modified to fulfill a therapeutic purpose and expanded in order to provide a sufficient dose of the cell product (Kazmi et al, 2009; June et al, 2018)
Media Optimization Using Machine Learning cells are purified by their common surface marker CD3, they differ in each donor in expression of other surface markers as well as in their metabolic and functional capacity (Mahnke et al, 2013; Klein Geltink et al, 2018)
In contrast to a traditional optimization strategy based on sequential screening, characterization and optimization steps (Anderson, 2019) (Figure 1A), we carried out a one-time media optimization using a machine learning pipeline
Summary
In autologous cell therapy approaches, cells from a given patient are isolated, may be genetically modified to fulfill a therapeutic purpose and expanded in order to provide a sufficient dose of the cell product (Kazmi et al, 2009; June et al, 2018). These cells are typically activated by ligation of the T cell coreceptors CD3 and CD28 to trigger expansion of T cells and are cultured for several days in culture media supplemented with appropriate cytokines (Trickett and Kwan, 2003; Xu et al, 2014) In this process, an efficient and robust expansion of T cells from any donor regardless of the heterogeneity of cell populations is essential to meet the specifications of good manufacturing practice and because timely manufacturing of the cell product can be critical to patient treatment (Gee, 2018). This can be achieved with an optimized cell culture medium formulation that supports the expansion of each donor’s T cells
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
