Spectroscopic models for real‐time monitoring of cell culture processes using spatiotemporal just‐in‐time Gaussian processes

Tulsyan, Aditya; Khodabandehlou, Hamid; Wang, Tony; Schorner, Gregg; Coufal, Myra; Ündey, Cenk

doi:10.1002/aic.17210

Cited by 20 publications

(23 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The implemented kernel function which is a combination of the linear and the RBF kernel has previously been shown to be a viable combination for chemometric purposes in Chen et al (2007). In other cases, the RBF kernel alone was used for GPR models using near‐infrared and Raman spectroscopy data (Chen et al, 2007; Cui & Fearn, 2017; Tulsyan et al, 2021). In general, the authors consider the usage of covariance kernels beneficial to model the nonlinear observed spectral shift and baseline drift of the absorbance spectra compared with the linear subspace projections the PLSR models are based upon.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, another drawback of the implemented EKF is the steady-state constraints, that is, the experimentally derived cysteine distribution assumed for all batches, which make the EKF rather stiff towards the end of the reaction. This is a known problem of the EKF (Tulsyan et al, 2021) when dealing with only a few states being available for measurement as well as for nonlinear models. In theory, this problem could be circumvented with other more flexible state estimation algorithms, such as particle filters as implemented in Golabgir and Herwig (2016) and Stelzer et al (2017) or unconstrained Kalman filter algorithms as used in Kolås et al (2009) and Simutis and Lübbert (2017) which were beyond the scope of this study.…”

Section: Soft-sensor Developmentmentioning

confidence: 99%

“…In the field of ADCs, monitoring of the conjugation reaction using UV/Vis spectra (Andris et al, 2018) and quantification of aggregation using Raman spectroscopy (Zhang et al, 2019) are recently established PAT tools. Partial least‐squares regression (PLSR) models have commonly been applied in chemometrics (Andersson, 2009; Wold et al, 2001) and, more recently, Gaussian process regression (GPR) models have been identified as a competitive alternative to PLSR (Chen et al, 2007; Cui & Fearn, 2017; Tulsyan et al, 2021). Furthermore, GPR models deliver an uncertainty estimate for each evaluated data point and therefore help perform risk‐based dynamic adjustments during the process (Tulsyan et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…Partial least‐squares regression (PLSR) models have commonly been applied in chemometrics (Andersson, 2009; Wold et al, 2001) and, more recently, Gaussian process regression (GPR) models have been identified as a competitive alternative to PLSR (Chen et al, 2007; Cui & Fearn, 2017; Tulsyan et al, 2021). Furthermore, GPR models deliver an uncertainty estimate for each evaluated data point and therefore help perform risk‐based dynamic adjustments during the process (Tulsyan et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An adaptive soft‐sensor for advanced real‐time monitoring of an antibody‐drug conjugation reaction

Schiemer

Weggen

Schmitt

et al. 2023

Biotech & Bioengineering

View full text Add to dashboard Cite

In the production of antibody‐drug conjugates (ADCs), the conjugation reaction is a central step defining the final product composition and, hence, directly affecting product safety and efficacy. To enable real‐time monitoring, spectroscopic sensors in combination with multivariate regression models have gained popularity in recent years. The extended Kalman filter (EKF) can be used as so‐called soft‐sensor to fuse sensor predictions with long‐horizon forecasts by process models. This enables the dynamic update of the current state and provides increased robustness against experimental noise or model errors. Due to the uncertainty associated with sensor and process models in biopharmaceutical applications, the deployment of such soft‐sensors is challenging. In this study, we demonstrate the combination of an uncertainty‐aware sensor model with a kinetic reaction model using an EKF to monitor a site‐directed ADC conjugation reaction. As the sensor model, a Gaussian process regression model is presented to realize a time‐variant determination of the sensor uncertainty. The EKF fuses the time‐discrete predictions of the amount of conjugated drug from the sensor model with the time‐continuous predictions from the kinetic model. While the ADC species are not distinguishable by on‐line recorded UV/Vis spectra, the developed soft‐sensor is able to dynamically update all relevant reaction species. It could be shown that the use of time‐variant process and sensor noise computation approaches improved the performance of the EKF and achieved a reduction of the prediction error of up to 23% compared with the kinetic model. The developed framework proved to enhance robustness against noisy sensor measurements or wrong model initialization and was successfully transferred from batch to fed‐batch mode. In future, this framework could be implemented for model‐based process control and be adopted for other ADC conjugation reaction types.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Soft-sensor Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An adaptive soft‐sensor for advanced real‐time monitoring of an antibody‐drug conjugation reaction

Schiemer

Weggen

Schmitt

et al. 2023

Biotech & Bioengineering

View full text Add to dashboard Cite

show abstract

“…In the literature, there are many works where data‐driven cell culture process models are employed for monitoring and control purposes (Kiran & Jana, 2009; Tulsyan et al, 2021); however, the choice of model has a considerable impact on the accuracy and reliability of the control policy. Linear models normally have the simplest structure for representing the processes; however, nonlinear models such as neural networks (NN) and Gaussian process (GP) provide more accuracy.…”

Section: Introductionmentioning

confidence: 99%

Machine learning‐based model predictive controller design for cell culture processes

Rashedi

Rafiei

Demers

et al. 2023

Biotech & Bioengineering

Self Cite

View full text Add to dashboard Cite

The biopharmaceutical industry continuously seeks to optimize the critical quality attributes to maintain the reliability and cost‐effectiveness of its products. Such optimization demands a scalable and optimal control strategy to meet the process constraints and objectives. This work uses a model predictive controller (MPC) to compute an optimal feeding strategy leading to maximized cell growth and metabolite production in fed‐batch cell culture processes. The lack of high‐fidelity physics‐based models and the high complexity of cell culture processes motivated us to use machine learning algorithms in the forecast model to aid our development. We took advantage of linear regression, the Gaussian process and neural network models in the MPC design to maximize the daily protein production for each batch. The control scheme of the cell culture process solves an optimization problem while maintaining all metabolites and cell culture process variables within the specification. The linear and nonlinear models are developed based on real cell culture process data, and the performance of the designed controllers is evaluated by running several real‐time experiments.

show abstract

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

Yan,

Dong,

Wan

et al. 2024

Biotechnology Journal

View full text Add to dashboard Cite

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.

show abstract

Spectroscopic models for real‐time monitoring of cell culture processes using spatiotemporal just‐in‐time Gaussian processes

Cited by 20 publications

References 40 publications

An adaptive soft‐sensor for advanced real‐time monitoring of an antibody‐drug conjugation reaction

An adaptive soft‐sensor for advanced real‐time monitoring of an antibody‐drug conjugation reaction

Machine learning‐based model predictive controller design for cell culture processes

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

Contact Info

Product

Resources

About