Multivariate data analysis of growth medium trends affecting antibody glycosylation

Powers, David N.; Trunfio, Nicholas; Velugula‐Yellela, Sai Rashmika; Angart, Phillip; Faustino, Anneliese; Agarabi, Cyrus

doi:10.1002/btpr.2903

Cited by 16 publications

(12 citation statements)

References 29 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this method, the original dataset is first projected onto an orthogonal low-dimensional space and linear regression is performed to establish the relations and interactions among different variables. PLSR is extensively used to identify CQAs-CPPs correlation/relationship in biomanufacturing QbD: several studies have particularly used PLSR to explore the effect of individual components in the cell culture medium (e.g., glucose, glutamine, glutamate, other amino acids) on various process outcomes such as viable cell density (VCD)/cell growth, 23 , 31–33 titer, 17 , 19 , 22 , 23 , 25 , 32–35 toxic by-product (lactate and ammonia) accumulation, 23 , 31 , 34 and CQAs such as N-glycosylation, 17 , 18 , 21 , 22 , 25 , 35 , 36 aggregation, 17 , 18 and charge variants. 17 , 18 Other studies have also associated the impact of cell culture pH 19 , 34 , 37–39 and dO2 34 , 39 with process outcomes using this method.…”

Section: Biomanufacturing Qbd Tour De Force By Multivariate Analysismentioning

confidence: 99%

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Walsh

Myint

Nguyen-Khuong

et al. 2022

mAbs

View full text Add to dashboard Cite

Ensuring consistent high yields and product quality are key challenges in biomanufacturing. Even minor deviations in critical process parameters (CPPs) such as media and feed compositions can significantly affect product critical quality attributes (CQAs). To identify CPPs and their interdependencies with product yield and CQAs, design of experiments, and multivariate statistical approaches are typically used in industry. Although these models can predict the effect of CPPs on product yield, there is room to improve CQA prediction performance by capturing the complex relationships in high-dimensional data. In this regard, machine learning (ML) approaches offer immense potential in handling non-linear datasets and thus are able to identify new CPPs that could effectively predict the CQAs. ML techniques can also be synergized with mechanistic models as a ‘hybrid ML’ or ‘white box ML’ to identify how CPPs affect the product yield and quality mechanistically, thus enabling rational design and control of the bioprocess. In this review, we describe the role of statistical modeling in Quality by Design (QbD) for biomanufacturing, and provide a generic outline on how relevant ML can be used to meaningfully analyze bioprocessing datasets. We then offer our perspectives on how relevant use of ML can accelerate the implementation of systematic QbD within the biopharma 4.0 paradigm.

show abstract

Section: Biomanufacturing Qbd Tour De Force By Multivariate Analysismentioning

confidence: 99%

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Walsh

Myint

Nguyen-Khuong

et al. 2022

mAbs

View full text Add to dashboard Cite

show abstract

“…Since the VIP is a squared sum always resulting in a positive magnitude, the VIP was used as a ranking system for all the variables in terms of importance to the predictability of the model. Moreover, Powers et al described that the average VIP value compared across all variables is typically around 1 (Powers et al, 2020). Accordingly, VIP values >1 were selected to be variables that significantly contributed toward the predictability of the response variable whereas those with a VIP <0.5…”

Section: Identifying Variable Importance With Sbsmentioning

confidence: 99%

Using MVDA with stoichiometric balances to optimize amino acid concentrations in chemically defined CHO cell culture medium for improved culture performance

Salim

Chauhan

Templeton

et al. 2021

Biotech & Bioengineering

View full text Add to dashboard Cite

Chemically defined (CD) media are routinely used in the production of biologics in Chinese hamster ovary (CHO) cell culture and provide enhanced raw material control. Nutrient optimized CD media is an important path to increase cell growth and monoclonal antibody (mAb) productivity in recombinant CHO cell lines. However, nutrient optimization efforts for CD media typically rely on multifactorial and experimental design of experiment approaches or complex mathematical models of cellular metabolism or gene expression systems. Moreover, the majority of these efforts are aimed at amino acids since they constitute essential nutrients in CD media as they directly contribute to biomass and protein production. In this study, we demonstrate the utilization of multivariate data analytics (MVDA) coupled with amino acid stoichiometric balances (SBs) to increased cell growth and mAb productivity in efforts to support CD media development efforts. SBs measure the difference between theoretical demand of amino acids and the empirically measured fluxes to identify various catabolic or anabolic states of the cell. When coupled with MVDA, the statistical models were not only able to highlight key amino acids toward cell growth or productivity, but also provided direction on metabolic favorability of the amino acid. Experimental validation of our approach resulted in a 55% increase in total cell growth and about an 80% increase in total mAb productivity. Increased specific consumption of stoichiometrically balanced amino acids and decreased specific consumption of glucose was also observed in optimized CD media suggesting favorable consumption of desired nutrients and a potential for energy redistribution toward increased cellular growth and mAb productivity.

show abstract

“…Since the VIP is a squared sum always resulting in a positive magnitude, the VIP was used as a ranking system for all the variables in terms of importance to the predictability of the model. Moreover, Powers et al described that the average VIP value compared across all variables is typically around 1 (Powers et al, 2020). Accordingly, VIP values greater than 1 were selected to be variables that significantly contributed towards the predictability of the response variable whereas those with a VIP less than 0.5 were presumed to have nominal contributions to the overall model.…”

Section: Identifying Variable Importance With Stoichiometric Balancesmentioning

confidence: 99%

Using MVDA with Stoichiometric Balances to Optimize Amino Acid Concentrations in Chemically Defined CHO Cell Culture Medium for Improved Culture Performance

Salim

Chauhan

Templeton

et al. 2021

Preprint

View full text Add to dashboard Cite

Chemically defined (CD) media are routinely used in the production of biologics in Chinese Hamster Ovary (CHO) cell culture and provide enhanced raw material control. Nutrient optimized CD media is an important path to increase cell growth and monoclonal antibody (mAb) productivity in recombinant CHO cell lines. However, nutrient optimization efforts for CD media typically rely on multi-factorial and experimental design of experiment (DoE) approaches or complex mathematical models of cellular metabolism or gene expression systems. Moreover, the majority of these efforts are aimed at amino acids since they constitute essential nutrients in CD media as they directly contribute to biomass and protein production. In this study, we demonstrate the utilization of multi-variate data analytics (MVDA) coupled with amino acid stoichiometric balances (SBs) to increased cell growth and mAb productivity in efforts to reduce CD media development efforts. SBs measure the difference between theoretical demand of amino acids and the empirically measured fluxes to identify metabolic states of the cell. When coupled with MVDA, the statistical models were not only able to highlight key amino acids towards cell growth or productivity, but also provided direction on metabolic favorability of the amino acid. Experimental validation of our approach resulted in a 55% increase in total cell growth and about an 80% increase in total mAb productivity. Increased specific consumption of stoichiometrically balanced amino acids and decreased specific consumption of glucose was also observed in optimized CD media suggesting favorable consumption of desired nutrients and a potential for energy redistribution towards increased cellular growth or mAb productivity.

show abstract

Multivariate data analysis of growth medium trends affecting antibody glycosylation

Cited by 16 publications

References 29 publications

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Using MVDA with stoichiometric balances to optimize amino acid concentrations in chemically defined CHO cell culture medium for improved culture performance

Using MVDA with Stoichiometric Balances to Optimize Amino Acid Concentrations in Chemically Defined CHO Cell Culture Medium for Improved Culture Performance

Contact Info

Product

Resources

About