Monitoring of Amino Acids and Antibody N-Glycosylation in High Cell Density Perfusion Culture based on Raman Spectroscopy

Predictive modeling for cell culture in commercial manufacturing of biotherapeutics

The biopharmaceutical industry continually seeks advancements in the commercial manufacturing of therapeutic proteins, where mammalian cell culture plays a pivotal role. The current work presents a novel data-driven predictive modeling application designed to enhance the efficiency and predictability of cell culture processes in biotherapeutic production. The capability of the cloud-based digital data science application, developed using open-source tools, is demonstrated with respect to predicting bioreactor potency from at-line process parameters over a 5-day horizon. The uncertainty in model's prediction is quantified, providing valuable insights for process control and decision-making. Model validation on unseen data confirms the model's robust generalizability. An interactive dashboard, tailored to process scientist's requirements is also developed to streamline biopharmaceutical manufacturing processes, ultimately leading to enhanced productivity and product quality.

Integration of just-in-time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy

Protein production in the biopharmaceutical industry necessitates the utilization of multiple analytical techniques and control methodologies to ensure both safety and consistency. To facilitate real-time monitoring and control of cell culture processes, Raman spectroscopy has emerged as a versatile analytical technology. This technique, categorized as a Process Analytical Technology, employs chemometric models to establish correlations between Raman signals and key variables of interest. One notable approach for achieving real-time monitoring is through the application of just-in-time learning (JITL), an industrial soft sensor modeling technique that utilizes Raman signals to estimate process variables promptly. The conventional Raman-based JITL method relies on the K-nearest neighbor (KNN) algorithm with Euclidean distance as the similarity measure. However, it falls short of addressing the impact of data uncertainties. To rectify this limitation, this study endeavors to integrate JITL with a variational autoencoder (VAE). This integration aims to extract dominant Raman features in a nonlinear fashion, which are expressed as multivariate Gaussian distributions. Three experimental runs using different cell lines were chosen to compare the performance of the proposed algorithm with commonly utilized methods in the literature. The findings indicate that the VAE-JITL approach consistently outperforms partial least squares, convolutional neural network, and JITL with KNN similarity measure in accurately predicting key process variables.

Development of generic metabolic Raman calibration models using solution titration in aqueous phase and data augmentation for in-line cell culture analysis

This study presents a novel approach for developing generic metabolic Raman calibration models for in-line cell culture analysis using glucose and lactate stock solution titration in an aqueous phase and data augmentation techniques. First, a successful set-up of the titration method was achieved by adding glucose or lactate solution at several different constant rates into the aqueous phase of a bench-top bioreactor. Subsequently, the in-line glucose and lactate concentration were calculated and interpolated based on the rate of glucose and lactate addition, enabling data augmentation and enhancing the robustness of the metabolic calibration model. Nine different combinations of spectra pretreatment, wavenumber range selection, and number of latent variables were evaluated and optimized using aqueous titration data as training set and a historical cell culture data set as validation and prediction set. Finally, Raman spectroscopy data collected from 11 historical cell culture batches (spanning four culture modes and scales ranging from 3 to 200 L) were utilized to predict the corresponding glucose and lactate values. The results demonstrated a high prediction accuracy, with an average root mean square errors of prediction of 0.65 g/L for glucose, and 0.48 g/L for lactate. This innovative method establishes a generic metabolic calibration model, and its applicability can be extended to other metabolites, reducing the cost of deploying real-time cell culture monitoring using Raman spectroscopy in bioprocesses.

NIR spectroscopy-CNN-enabled chemometrics for multianalyte monitoring in microbial fermentation

As the biopharmaceutical industry looks to implement Industry 4.0, the need for rapid and robust analytical characterization of analytes has become a pressing priority. Spectroscopic tools, like near-infrared (NIR) spectroscopy, are finding increasing use for real-time quantitative analysis. Yet detection of multiple low-concentration analytes in microbial and mammalian cell cultures remains an ongoing challenge, requiring the selection of carefully calibrated, resilient chemometrics for each analyte. The convolutional neural network (CNN) is a puissant tool for processing complex data and making it a potential approach for automatic multivariate spectral processing. This work proposes an inception module-based two-dimensional (2D) CNN approach (I-CNN) for calibrating multiple analytes using NIR spectral data. The I-CNN model, coupled with orthogonal partial least squares (PLS) preprocessing, converts the NIR spectral data into a 2D data matrix, after which the critical features are extracted, leading to model development for multiple analytes. Escherichia coli fermentation broth was taken as a case study, where calibration models were developed for 23 analytes, including 20 amino acids, glucose, lactose, and acetate. The I-CNN model result statistics depicted an average R2 values of prediction 0.90, external validation data set 0.86 and significantly lower root mean square error of prediction values ∼0.52 compared to conventional regression models like PLS. Preprocessing steps were applied to I-CNN models to evaluate any augmentation in prediction performance. Finally, the model reliability was assessed via real-time process monitoring and comparison with offline analytics. The proposed I-CNN method is systematic and novel in extracting distinctive spectral features from a multianalyte bioprocess data set and could be adapted to other complex cell culture systems requiring rapid quantification using spectroscopy.

Building blocks needed for mechanistic modeling of bioprocesses: A critical review based on protein production by CHO cells

This paper reviews the key building blocks needed to develop a mechanistic model for use as an operational production tool. The Chinese Hamster Ovary (CHO) cell, one of the most widely used hosts for antibody production in the pharmaceutical industry, is considered as a case study. CHO cell metabolism is characterized by two main phases, exponential growth followed by a stationary phase with strong protein production. This process presents an appropriate degree of complexity to outline the modeling strategy. The paper is organized into four main steps: (1) CHO systems and data collection; (2) metabolic analysis; (3) formulation of the mathematical model; and finally, (4) numerical solution, calibration, and validation. The overall approach can build a predictive model of target variables. According to the literature, one of the main current modeling challenges lies in understanding and predicting the spontaneous metabolic shift. Possible candidates for the trigger of the metabolic shift include the concentration of lactate and carbon dioxide. In our opinion, ammonium, which is also an inhibiting product, should be further investigated. Finally, the expected progress in the emerging field of hybrid modeling, which combines the best of mechanistic modeling and machine learning, is presented as a fascinating breakthrough. Note that the modeling strategy discussed here is a general framework that can be applied to any bioprocess.

Genetic algorithm-based semisupervised convolutional neural network for real-time monitoring of Escherichia coli fermentation of recombinant protein production using a Raman sensor

As a non-destructive sensing technique, Raman spectroscopy is often combined with regression models for real-time detection of key components in microbial cultivation processes. However, achieving accurate model predictions often requires a large amount of offline measurement data for training, which is both time-consuming and labor-intensive. In order to overcome the limitations of traditional models that rely on large datasets and complex spectral preprocessing, in addition to the difficulty of training models with limited samples, we have explored a genetic algorithm-based semi-supervised convolutional neural network (GA-SCNN). GA-SCNN integrates unsupervised process spectral labeling, feature extraction, regression prediction, and transfer learning. Using only an extremely small number of offline samples of the target protein, this framework can accurately predict protein concentration, which represents a significant challenge for other models. The effectiveness of the framework has been validated in a system of Escherichia coli expressing recombinant ProA5M protein. By utilizing the labeling technique of this framework, the available dataset for glucose, lactate, ammonium ions, and optical density at 600 nm (OD600) has been expanded from 52 samples to 1302 samples. Furthermore, by introducing a small component of offline detection data for recombinant proteins into the OD600 model through transfer learning, a model for target protein detection has been retrained, providing a new direction for the development of associated models. Comparative analysis with traditional algorithms demonstrates that the GA-SCNN framework exhibits good adaptability when there is no complex spectral preprocessing. Cross-validation results confirm the robustness and high accuracy of the framework, with the predicted values of the model highly consistent with the offline measurement results.

Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy

Advanced process control in the biopharmaceutical industry often lacks real-time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real-time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two-dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed-batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real-time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs.

Model-based control system design to manage process parameters in mammalian cell culture for biopharmaceutical manufacturing

To enhance the robustness and flexibility of biopharmaceutical manufacturing, a paradigm shift toward methods of continuous processing, such as perfusion, and fundamental technologies for high-throughput process development are being actively investigated. The continuous upstream process must establish an advanced control strategy to ensure a "State of Control" before operation. Specifically, feedforward and feedback control must address the complex fluctuations that occur during the culture process and maintain critical process parameters in appropriate states. However, control system design for industry-standard mammalian cell culture processes is still often performed in a laborious trial-and-error manner. This paper provides a novel control approach in which controller specifications to obtain desired control characteristics can be determined systematically by combining a culture model with control theory. In the proposed scheme, control conditions, such as PID parameters, can be specified mechanistically based on process understanding and control requirements without qualitative decision making or specific preliminary experiments. The effectiveness of the model-based control algorithm was verified by control simulations assuming perfusion Chinese hamster ovary culture. As a tool to assist in the development of control strategies, this study will reduce the high operational workload that is a serious problem in continuous culture and facilitate the digitalization of bioprocesses.

Development of an in-line Raman analytical method for commercial-scale CHO cell culture process monitoring: Influence of measurement channels and batch number on model performance

The mammalian cell culture process is a key step in commercial therapeutic protein production and needs to be monitored and controlled due to its complexity. Raman spectroscopy has been reported for cell culture process monitoring by analysis of many important parameters. However, studies on in-line Raman monitoring of the cell culture process were mainly conducted on small or pilot scale. Developing in-line Raman analytical methods for commercial-scale cell culture process monitoring is more challenging. In this study, an in-line Raman analytical method was developed for monitoring glucose, lactate, and viable cell density (VCD) in the Chinese hamster ovary (CHO) cell culture process during commercial production of biosimilar adalimumab (1500 L). The influence of different Raman measurement channels was considered to determine whether to merge data from different channels for model development. Raman calibration models were developed and optimized, with minimum root mean square error of prediction of 0.22 g L-1 for glucose in the range of 1.66-3.53 g L-1 , 0.08 g L-1 for lactate in the range of 0.15-1.19 g L-1 , 0.31 E6 cells mL-1 for VCD in the range of 0.96-5.68 E6 cells mL-1 on test sets. The developed analytical method can be used for cell culture process monitoring during manufacturing and meets the analytical purpose of this study. Further, the influence of the number of batches used for model calibration on model performance was also studied to determine how many batches are needed basically for method development. The proposed Raman analytical method development strategy and considerations will be useful for monitoring of similar bioprocesses.

Feasibility and performance of cross-clone Raman calibration models in CHO cultivation

Raman spectroscopy is widely used in monitoring and controlling cell cultivations for biopharmaceutical drug manufacturing. However, its implementation for culture monitoring in the cell line development stage has received little attention. Therefore, the impact of clonal differences, such as productivity and growth, on the prediction accuracy and transferability of Raman calibration models is not yet well described. Raman OPLS models were developed for predicting titer, glucose and lactate using eleven CHO clones from a single cell line. These clones exhibited diverse productivity and growth rates. The calibration models were evaluated for clone-related biases using clone-wise linear regression analysis on cross validated predictions. The results revealed that clonal differences did not affect the prediction of glucose and lactate, but titer models showed a significant clone-related bias, which remained even after applying variable selection methods. The bias was associated with clonal productivity and lead to increased prediction errors when titer models were transferred to cultivations with productivity levels outside the range of their training data. The findings demonstrate the feasibility of Raman-based monitoring of glucose and lactate in cell line development with high accuracy. However, accurate titer prediction requires careful consideration of clonal characteristics during model development.

Raman-controlled pyruvate feeding to control metabolic activity and product quality in continuous biomanufacturing

BACKGROUND

Despite technological advances ensuring stable cell culture perfusion operation over prolonged time, reaching a cellular steady-state metabolism remains a challenge for certain manufacturing cell lines. This study investigated the stabilization of a steady-state perfusion process producing a bispecific antibody with drifting product quality attributes, caused by shifting metabolic activity in the cell culture.

MAIN METHODS

A novel on-demand pyruvate feeding strategy was developed, leveraging lactate as an indicator for tricarboxylic acid (TCA) cycle saturation. Real-time lactate monitoring was achieved through in-line Raman spectroscopy, enabling accurate control at predefined target setpoints.

MAJOR RESULTS

The implemented feedback control strategy resulted in a three-fold reduction of ammonium accumulation and stabilized product quality profiles. Stable and flat glycosylation profiles were achieved with standard deviations below 0.2% for high mannose and fucosylation. Whereas galactosylation and sialylation were stabilized in a similar manner, varying lactate setpoints might allow for fine-tuning of these glycan forms.

IMPLICATION

The Raman-controlled pyruvate feeding strategy represents a valuable tool for continuous manufacturing, stabilizing metabolic activity, and preventing product quality drifting in perfusion cell cultures. Additionally, this approach effectively reduced high mannose, helping to mitigate increases associated with process intensification, such as extended culture durations or elevated culture densities.

Current challenges and recent advances on the path towards continuous biomanufacturing

Continuous biopharmaceutical manufacturing is currently a field of intense research due to its potential to make the entire production process more optimal for the modern, ever-evolving biopharmaceutical market. Compared to traditional batch manufacturing, continuous bioprocessing is more efficient, adjustable, and sustainable and has reduced capital costs. However, despite its clear advantages, continuous bioprocessing is yet to be widely adopted in commercial manufacturing. This article provides an overview of the technological roadblocks for extensive adoptions and points out the recent advances that could help overcome them. In total, three key areas for improvement are identified: Quality by Design (QbD) implementation, integration of upstream and downstream technologies, and data and knowledge management. First, the challenges to QbD implementation are explored. Specifically, process control, process analytical technology (PAT), critical process parameter (CPP) identification, and mathematical models for bioprocess control and design are recognized as crucial for successful QbD realizations. Next, the difficulties of end-to-end process integration are examined, with a particular emphasis on downstream processing. Finally, the problem of data and knowledge management and its potential solutions are outlined where ontologies and data standards are pointed out as key drivers of progress.

Optimization of medium with perfusion microbioreactors for high density CHO cell cultures at very low renewal rate aided by design of experiments

A novel approach of design of experiment (DoE) is developed for the optimization of key substrates of the culture medium, amino acids, and sugars, by utilizing perfusion microbioreactors with 2 mL working volume, operated in high cell density continuous mode, to explore the design space. A mixture DoE based on a simplex-centroid is proposed to test multiple medium blends in parallel perfusion runs, where the amino acids concentrations are selected based on the culture behavior in presence of different amino acid mixtures, and using targeted specific consumption rates. An optimized medium is identified with models predicting the culture parameters and product quality attributes (G0 and G1 level N-glycans) as a function of the medium composition. It is then validated in runs performed in perfusion microbioreactor in comparison with stirred-tank bioreactors equipped with alternating tangential flow filtration (ATF) or with tangential flow filtration (TFF) for cell separation, showing overall a similar process performance and N-glycosylation profile of the produced antibody. These results demonstrate that the present development strategy generates a perfusion medium with optimized performance for stable Chinese hamster ovary (CHO) cell cultures operated with very high cell densities of 60 × 106 and 120 × 106  cells/mL and a low cell-specific perfusion rate of 17 pL/cell/day, which is among the lowest reported and is in line with the framework recently published by the industry.

Raman spectroscopy provides valuable process insights for cell-derived and cellular products

Two of the big challenges in modern bioprocesses are process economics and in-depth process understanding. Getting access to online process data helps to understand process dynamics and monitor critical process parameters (CPPs). This is an important part of the quality-by- design concept that was introduced to the pharmaceutical industry in the last decade. Raman spectroscopy has proven to be a versatile tool to allow noninvasive measurements and access to a broad spectrum of analytes. This information can then be used for enhanced process control strategies. This review article will focus on the latest applications of Raman spectroscopy in established protein production bioprocesses as well as show its potential for virus, cell therapy, and mRNA processes.

Near-infrared spectroscopy based monitoring of all 20 amino acids in mammalian cell culture broth

The biopharmaceutical industry extensively employs Chinese hamster ovary (CHO) cell culture for monoclonal antibody production. Amino acids represent an essential source of nutrients in all CHO cell culture media, and their concentration is known to significantly impact cell viability, titre, and monoclonal antibody critical quality attributes. In this study, a robust Fourier transform near-infrared spectroscopy (FT-NIR) based quantification method has been developed for of all 20 amino acids (0-24 mM), as well as concentrations of glucose (0-6.7 mg mL^-1), lactate (0-2.7 mg mL^-1), and trastuzumab (0-2.5 mg mL^-1) in the CHO cell culture. Near infra-red absorbance spectrum in the range of 4000-11,000 cm^-1 were acquired, and spectra pre-processing through smoothening and derivatives were employed to enhance key characteristic signals. High-performance liquid chromatography with pre-column derivatization was used as the orthogonal analytical tool for quantification. Principal component analysis and partial least squares regression were employed for region selection and calibration model development, respectively. The results demonstrate that a good calibration statistic with the acceptable coefficient of determinations for both calibration (R_c² = 0.94-0.99) and prediction (R_p² = 0.83-0.98) could be achieved, along with high RPD values (>3) for all components except alanine (2.4). The external validation study also exhibited a satisfactory outcome (R_EV² = 0.89-0.99, RMSE = 0.04-1.04), validating the model's ability to predict the concentrations of the respective species. The calibration models were successfully applied for at-line monitoring of two perfusion runs on a 10 L scale. To our knowledge, this is the first application where NIR spectroscopy-based measurement of all 20 amino acids in mammalian cell culture samples has been demonstrated. The proposed tool can play a critical role as biopharma manufacturers implement continuous processing as well as for facilitating process analytical technology-based control of mammalian cell culture processes.

Model-based intensification of CHO cell cultures: One-step strategy from fed-batch to perfusion

There is a growing interest in continuous processing of the biopharmaceutical industry. However, the technology transfer from traditional batch-based processes is considered a challenge as protocol and tools still remain to be established for their usage at the manufacturing scale. Here, we present a model-based approach to design optimized perfusion cultures of Chinese Hamster Ovary cells using only the knowledge captured during small-scale fed-batch experiments. The novelty of the proposed model lies in the simplicity of its structure. Thanks to the introduction of a new catch-all variable representing a bulk of by-products secreted by the cells during their cultivation, the model was able to successfully predict cellular behavior under different operating modes without changes in its formalism. To our knowledge, this is the first experimentally validated model capable, with a single set of parameters, to capture culture dynamic under different operating modes and at different scales.