Explainable AI for CHO cell culture media optimization and prediction of critical quality attribute.

Cell culture media play a critical role in cell growth and propagation by providing a substrate; media components can also modulate the critical quality attributes (CQAs). However, the inherent complexity of the cell culture media makes unraveling the impact of the various media components on cell growth and CQAs non-trivial. In this study, we demonstrate an end-to-end machine learning framework for media component selection and prediction of CQAs. The preliminary dataset for feature selection was generated by performing CHO-GS (-/-) cell culture in media formulations with varying metal ion concentrations. Acidic and basic charge variant composition of the innovator product (24.97 ± 0.54% acidic and 11.41 ± 1.44% basic) was chosen as the target variable to evaluate the media formulations. Pearson's correlation coefficient and random forest-based techniques were used for feature ranking and feature selection for the prediction of acidic and basic charge variants. Furthermore, a global interpretation analysis using SHapley Additive exPlanations was utilized to select optimal features by evaluating the contributions of each feature in the extracted vectors. Finally, the medium combinations were predicted by employing fifteen different regression models and utilizing a grid search and random search cross-validation for hyperparameter optimization. Experimental results demonstrate that Fe and Zn significantly impact the charge variant profile. This study aims to offer insights that are pertinent to both innovators seeking to establish a complete pipeline for media development and optimization and biosimilar-based manufacturers who strive to demonstrate the analytical and functional biosimilarity of their products to the innovator. KEY POINTS: • Developed a framework for optimizing media components and prediction of CQA. • SHAP enhances global interpretability, aiding informed decision-making. • Fifteen regression models were employed to predict medium combinations.

Enablers of continuous processing of biotherapeutic products.

The benefits of continuous processing over batch manufacturing are widely acknowledged across the biopharmaceutical industry, primary of which are higher productivity and greater consistency in product quality. Furthermore, the reduced equipment and facility footprint lead to significantly lower capital costs. Technology enablers have a major role in this migration from batch to continuous processing. In this review, we highlight the various enablers that are facilitating adoption of continuous upstream and downstream bioprocessing. This includes new bioreactors and cell retention devices for upstream operations, and on-column and continuous flow refolding, novel continuous chromatography, and single-pass filtration systems for downstream processes. We also elucidate the significant roles of process integration and control as well as of data analytics in these processes.

Effect of vitamins and metal ions on productivity and charge heterogeneity of IgG1 expressed in CHO cells.

Recombinant monoclonal antibodies have emerged as the most successful modality of biotherapeutics. They are primarily expressed in Chinese Hamster Ovary (CHO) cells. It is well known that post-translational modifications (PTM) contribute significantly to heterogeneity with respect to charge, glycosylation, and size. These attributes in turn impact stability, pharmacokinetics, and pharmacodynamics of the biotherapeutic product. Cell culture media components are known to significantly contribute to both cellular productivity as well as post-translational modifications. Thus, it is highly desirable to understand how media components affect product quality. This study aims to explore the impact of vitamins and metal ions on protein expression and post-translational modifications specifically charge heterogeneity. Biotin, choline chloride, D-calcium pantothenate, folic acid, pyridoxine hydrochloride, thiamine hydrochloride vitamins and Fe, Cu, Mg, Co, Zn, Mn, Ni metal ions were examined in this study. The results indicate that pyridoxine enhances productivity while Zn, Cu, Fe, Mn, and biotin impact charge heterogeneity. While, Fe, Mn and Ni enhance production of the acidic variants, Cu and biotin inhibit it. Zn reduces formation of basic variants while biotin enhances it. The results from this investigation could be used for process control so as to get consistent charge variant profile, in particular for biosimilars.