A PSE perspective for the efficient production of monoclonal antibodies: integration of process, cell, and product design aspects

Modeling of cell cultivation for monoclonal antibody production processes considering lactate metabolic shifts

Demand for monoclonal antibodies (mAbs) is rapidly increasing. To achieve higher productivity, there have been improvements to cell lines, operating modes, media, and cultivation conditions. Representative mathematical models are needed to narrow down the growing number of process alternatives. Previous studies have proposed mechanistic models to depict cell metabolic shifts (e.g., lactate production to consumption). However, the impacts of variations of some operating conditions have not yet been fully incorporated in such models. This paper offers a new mechanistic model considering variations in dissolved oxygen and glutamine depletion on cell metabolism applied to a novel Chinese hamster ovary (CHO) cell line. Expressions for the specific rates of lactate production, glutamine consumption, and mAb production were formulated for stirred and shaken-tank reactors. A deeper understanding of lactate metabolic shifts was obtained under different combinations of experimental conditions. Lactate consumption was more pronounced in conditions with higher DO and low glutamine concentrations. The model offers mechanistic insights that are useful for designing advanced operation strategies. It can be used in design space generation and process optimization for better productivity and product quality.

Hybrid deep modeling of a CHO-K1 fed-batch process: combining first-principles with deep neural networks

Introduction: Hybrid modeling combining First-Principles with machine learning is becoming a pivotal methodology for Biopharma 4.0 enactment. Chinese Hamster Ovary (CHO) cells, being the workhorse for industrial glycoproteins production, have been the object of several hybrid modeling studies. Most previous studies pursued a shallow hybrid modeling approach based on three-layered Feedforward Neural Networks (FFNNs) combined with macroscopic material balance equations. Only recently, the hybrid modeling field is incorporating deep learning into its framework with significant gains in descriptive and predictive power. Methods: This study compares, for the first time, deep and shallow hybrid modeling in a CHO process development context. Data of 24 fed-batch cultivations of a CHO-K1 cell line expressing a target glycoprotein, comprising 30 measured state variables over time, were used to compare both methodologies. Hybrid models with varying FFNN depths (3-5 layers) were systematically compared using two training methodologies. The classical training is based on the Levenberg-Marquardt algorithm, indirect sensitivity equations and cross-validation. The deep learning is based on the Adaptive Moment Estimation Method (ADAM), stochastic regularization and semidirect sensitivity equations. Results and conclusion: The results point to a systematic generalization improvement of deep hybrid models over shallow hybrid models. Overall, the training and testing errors decreased by 14.0% and 23.6% respectively when applying the deep methodology. The Central Processing Unit (CPU) time for training the deep hybrid model increased by 31.6% mainly due to the higher FFNN complexity. The final deep hybrid model is shown to predict the dynamics of the 30 state variables within the error bounds in every test experiment. Notably, the deep hybrid model could predict the metabolic shifts in key metabolites (e.g., lactate, ammonium, glutamine and glutamate) in the test experiments. We expect deep hybrid modeling to accelerate the deployment of high-fidelity digital twins in the biopharma sector in the near future.

Deep learning in drug discovery: an integrative review and future challenges

Recently, using artificial intelligence (AI) in drug discovery has received much attention since it significantly shortens the time and cost of developing new drugs. Deep learning (DL)-based approaches are increasingly being used in all stages of drug development as DL technology advances, and drug-related data grows. Therefore, this paper presents a systematic Literature review (SLR) that integrates the recent DL technologies and applications in drug discovery Including, drug-target interactions (DTIs), drug-drug similarity interactions (DDIs), drug sensitivity and responsiveness, and drug-side effect predictions. We present a review of more than 300 articles between 2000 and 2022. The benchmark data sets, the databases, and the evaluation measures are also presented. In addition, this paper provides an overview of how explainable AI (XAI) supports drug discovery problems. The drug dosing optimization and success stories are discussed as well. Finally, digital twining (DT) and open issues are suggested as future research challenges for drug discovery problems. Challenges to be addressed, future research directions are identified, and an extensive bibliography is also included.

Digital Twins in Pharmaceutical and Biopharmaceutical Manufacturing: A Literature Review

The development and application of emerging technologies of Industry 4.0 enable the realization of digital twins (DT), which facilitates the transformation of the manufacturing sector to a more agile and intelligent one. DTs are virtual constructs of physical systems that mirror the behavior and dynamics of such physical systems. A fully developed DT consists of physical components, virtual components, and information communications between the two. Integrated DTs are being applied in various processes and product industries. Although the pharmaceutical industry has evolved recently to adopt Quality-by-Design (QbD) initiatives and is undergoing a paradigm shift of digitalization to embrace Industry 4.0, there has not been a full DT application in pharmaceutical manufacturing. Therefore, there is a critical need to examine the progress of the pharmaceutical industry towards implementing DT solutions. The aim of this narrative literature review is to give an overview of the current status of DT development and its application in pharmaceutical and biopharmaceutical manufacturing. State-of-the-art Process Analytical Technology (PAT) developments, process modeling approaches, and data integration studies are reviewed. Challenges and opportunities for future research in this field are also discussed.

Impact of H2O2 Sorption by Polymers on the Duration of Aeration in Pharmaceutical Decontamination

As part of manufacturing a sterile drug product, we quantified the impact of H₂O₂ sorption by polymers on the duration of aeration in pharmaceutical decontamination. Five polymers, which are typically used as materials/parts in sterile isolators, were investigated: polyethylene, polyvinyl chloride, Silicone, polyoxymethylene (POM), and chlorosulfonated polyethylene. Experiments were performed to estimate the storage capacity and diffusion coefficients of H₂O₂ in the polymer. Considering these key properties of sorption/desorption, mathematical models were developed to simulate the duration of aeration to achieve the target H₂O₂ concentration, which is the indicator to minimize. The models were used to create a map-out of the duration given the properties of the polymers, including the five polymers. In the simulated setup, POM and Silicone were found to require prolonged aeration. Thus, when using these polymers in the isolator, the size/amount should be carefully investigated. Another practical finding was that the superiority of the polymers changed depending on the target H₂O₂ concentration. This result motivates an early incorporation of the product information in the isolator design, to achieve a rapid decontamination/aeration cycle.