Fingerprint detection and process prediction by multivariate analysis of fed-batch monoclonal antibody cell culture data

Holistic Process Models: A Bayesian Predictive Ensemble Method for Single and Coupled Unit Operation Models

The coupling of individual models in terms of end-to-end calculations for unit operations in manufacturing processes is a challenging task. We present a probability distribution-based approach for the combined outcomes of parametric and non-parametric models. With this so-called Bayesian predictive ensemble, the statistical moments such as mean value and standard deviation can be accurately computed without any further approximation. It is shown that the ensemble of different model predictions leads to an uninformed prior distribution, which can be transformed into a predictive posterior distribution using Bayesian inference and numerical Markov Chain Monte Carlo calculations. We demonstrate the advantages of our method using several numerical examples. Our approach is not restricted to certain unit operations, and can also be used for the more robust interpretation and assessment of model predictions in general.

Model Transferability and Reduced Experimental Burden in Cell Culture Process Development Facilitated by Hybrid Modeling and Intensified Design of Experiments

Reliable process development is accompanied by intense experimental effort. The utilization of an intensified design of experiments (iDoE) (intra-experimental critical process parameter (CPP) shifts combined) with hybrid modeling potentially reduces process development burden. The iDoE can provide more process response information in less overall process time, whereas hybrid modeling serves as a commodity to describe this behavior the best way. Therefore, a combination of both approaches appears beneficial for faster design screening and is especially of interest at larger scales where the costs per experiment rise significantly. Ideally, profound process knowledge is gathered at a small scale and only complemented with few validation experiments on a larger scale, saving valuable resources. In this work, the transferability of hybrid modeling for Chinese hamster ovary cell bioprocess development along process scales was investigated. A two-dimensional DoE was fully characterized in shake flask duplicates (300 ml), containing three different levels for the cultivation temperature and the glucose concentration in the feed. Based on these data, a hybrid model was developed, and its performance was assessed by estimating the viable cell concentration and product titer in 15 L bioprocesses with the same DoE settings. To challenge the modeling approach, 15 L bioprocesses also comprised iDoE runs with intra-experimental CPP shifts, impacting specific cell rates such as growth, consumption, and formation. Subsequently, the applicability of the iDoE cultivations to estimate static cultivations was also investigated. The shaker-scale hybrid model proved suitable for application to a 15 L scale (1:50), estimating the viable cell concentration and the product titer with an NRMSE of 10.92% and 17.79%, respectively. Additionally, the iDoE hybrid model performed comparably, displaying NRMSE values of 13.75% and 21.13%. The low errors when transferring the models from shaker to reactor and between the DoE and the iDoE approach highlight the suitability of hybrid modeling for mammalian cell culture bioprocess development and the potential of iDoE to accelerate process characterization and to improve process understanding.

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

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.

Challenges in the Development of Soft Sensors for Bioprocesses: A Critical Review

Among the greatest challenges in soft sensor development for bioprocesses are variable process lengths, multiple process phases, and erroneous model inputs due to sensor faults. This review article describes these three challenges and critically discusses the corresponding solution approaches from a data scientist’s perspective. This main part of the article is preceded by an overview of the status quo in the development and application of soft sensors. The scope of this article is mainly the upstream part of bioprocesses, although the solution approaches are in most cases also applicable to the downstream part. Variable process lengths are accounted for by data synchronization techniques such as indicator variables, curve registration, and dynamic time warping. Multiple process phases are partitioned by trajectory or correlation-based phase detection, enabling phase-adaptive modeling. Sensor faults are detected by symptom signals, pattern recognition, or by changing contributions of the corresponding sensor to a process model. According to the current state of the literature, tolerance to sensor faults remains the greatest challenge in soft sensor development, especially in the presence of variable process lengths and multiple process phases.

Digital Twins in Biomanufacturing

In recent years process modelling has become an established method which generates digital twins of manufacturing plant operation with the aid of numerically solved process models. This article discusses the benefits of establishing process modelling, in-house or by cooperation, in order to support the workflow from process development, piloting and engineering up to manufacturing. The examples are chosen from the variety of botanicals and biologics manufacturing thus proving the broad applicability from variable feedstock of natural plant extracts of secondary metabolites to fermentation of complex molecules like mAbs, fragments, proteins and peptides.Consistent models and methods to simulate whole processes are available. To determine the physical properties used as model parameters, efficient laboratory-scale experiments are implemented. These parameters are case specific since there is no database for complex molecules of biologics and botanicals in pharmaceutical industry, yet.Moreover, Quality-by-Design approaches, demanded by regulatory authorities, are integrated within those predictive modelling procedures. The models could be proven to be valid and predictive under regulatory aspects. Process modelling does earn its money from the first day of application. Process modelling is a key-enabling tool towards cost-efficient digitalization in chemical-pharmaceutical industries.

Artificial neural networks for the prediction of solvation energies based on experimental and computational data

The knowledge of thermodynamic properties for novel electrolyte formulations is of fundamental interest for industrial applications as well as academic research. Herewith, we present an artificial neural networks (ANN) approach for the prediction of solvation energies and entropies for distinct ion pairs in various protic and aprotic solvents. The considered feed-forward ANN is trained either by experimental data or computational results from conceptual density functional theory calculations. The proposed concept of mapping computed values to experimental data lowers the amount of time-consuming and costly experiments and helps to overcome certain limitations. Our findings reveal high correlation coefficients between predicted and experimental values which demonstrate the validity of our approach.

Forecasting and control of lactate bifurcation in Chinese hamster ovary cell culture processes

Biomanufacturing exhibits inherent variability that can lead to variation in performance attributes and batch failure. To help ensure process consistency and product quality the development of predictive models and integrated control strategies is a promising approach. In this study, a feedback controller was developed to limit excessive lactate production, a widespread metabolic phenomenon that is negatively associated with culture performance and product quality. The controller was developed by applying machine learning strategies to historical process development data, resulting in a forecast model that could identify whether a run would result in lactate consumption or accumulation. In addition, this exercise identified a correlation between increased amino acid consumption and low observed lactate production leading to the mechanistic hypothesis that there is a deficiency in the link between glycolysis and the tricarboxylic acid cycle. Using the correlative process parameters to build mechanistic insight and applying this to predictive models of lactate concentration, a dynamic model predictive controller (MPC) for lactate was designed. This MPC was implemented experimentally on a process known to exhibit high lactate accumulation and successfully drove the cell cultures towards a lactate consuming state. In addition, an increase in specific titer productivity was observed when compared with non-MPC controlled reactors.

Decision Tree-PLS (DT-PLS) algorithm for the development of process: Specific local prediction models

This work presents a novel multivariate statistical algorithm, Decision Tree-PLS (DT-PLS), to improve the prediction and understanding of dynamic processes based on local partial least square regression (PLSR) models for characteristic process groups defined based on Decision Tree (DT) analysis. The DT-PLS algorithm is successfully applied to two different cell culture data sets, one obtained from bioreactors of 3.5 L lab scale and the other obtained from the 15 ml ambr microbioreactor system. Substantial improvement in the predictive capabilities of the model can be achieved based on the localization compared to the classical PLSR approach, which is implemented in the commercially available packages. Additionally, the differences in the model parameters of the local models suggest that the governing process variables vary for the different process regimes indicating the different states of the cell under different process conditions.

Scale-Down Model Development in ambr systems: An Industrial Perspective

High-Throughput (HT) technologies such as miniature bioreactors (MBRs) are increasingly employed within the biopharmaceutical manufacturing industry. Traditionally, these technologies have been utilized for discrete screening approaches during pre-clinical development (e.g., cell line selection and process optimization). However, increasing interest is focused towards their use during late clinical phase process characterization studies as a scale-down model (SDM) of the cGMP manufacturing process. In this review, the authors describe a systematic approach toward SDM development in one of the most widely adopted MBRs, the ambr 15 and 250 mL (Sartorius Stedim Biotech) systems. Recent efforts have shown promise in qualifying ambr systems as SDMs to support more efficient, robust and safe biomanufacturing processes. The authors suggest that combinatorial improvements in process understanding (matching of mass transfer and cellular stress between scales through computational fluid dynamics and in vitro analysis), experimental design (advanced risk assessment and statistical design of experiments), and data analysis (combining uni- and multi-variate techniques) will ultimately yield ambr SDMs applicable for future regulatory submissions.

Accelerated Bioprocess Development of Endopolygalacturonase-Production with Saccharomyces cerevisiae Using Multivariate Prediction in a 48 Mini-Bioreactor Automated Platform

Mini-bioreactor systems enabling automatized operation of numerous parallel cultivations are a promising alternative to accelerate and optimize bioprocess development allowing for sophisticated cultivation experiments in high throughput. These include fed-batch and continuous cultivations with multiple options of process control and sample analysis which deliver valuable screening tools for industrial production. However, the model-based methods needed to operate these robotic facilities efficiently considering the complexity of biological processes are missing. We present an automated experiment facility that integrates online data handling, visualization and treatment using multivariate analysis approaches to design and operate dynamical experimental campaigns in up to 48 mini-bioreactors (8⁻12 mL) in parallel. In this study, the characterization of Saccharomyces cerevisiae AH22 secreting recombinant endopolygalacturonase is performed, running and comparing 16 experimental conditions in triplicate. Data-driven multivariate methods were developed to allow for fast, automated decision making as well as online predictive data analysis regarding endopolygalacturonase production. Using dynamic process information, a cultivation with abnormal behavior could be detected by principal component analysis as well as two clusters of similarly behaving cultivations, later classified according to the feeding rate. By decision tree analysis, cultivation conditions leading to an optimal recombinant product formation could be identified automatically. The developed method is easily adaptable to different strains and cultivation strategies, and suitable for automatized process development reducing the experimental times and costs.

Enhanced process understanding and multivariate prediction of the relationship between cell culture process and monoclonal antibody quality

This work investigates the insights and understanding which can be deduced from predictive process models for the product quality of a monoclonal antibody based on designed high-throughput cell culture experiments performed at milliliter (ambr-15^® ) scale. The investigated process conditions include various media supplements as well as pH and temperature shifts applied during the process. First, principal component analysis (PCA) is used to show the strong correlation characteristics among the product quality attributes including aggregates, fragments, charge variants, and glycans. Then, partial least square regression (PLS1 and PLS2) is applied to predict the product quality variables based on process information (one by one or simultaneously). The comparison of those two modeling techniques shows that a single (PLS2) model is capable of revealing the interrelationship of the process characteristics to the large set product quality variables. In order to show the dynamic evolution of the process predictability separate models are defined at different time points showing that several product quality attributes are mainly driven by the media composition and, hence, can be decently predicted from early on in the process, while others are strongly affected by process parameter changes during the process. Finally, by coupling the PLS2 models with a genetic algorithm first the model performance can be further improved and, most importantly, the interpretation of the large-dimensioned process-product-interrelationship can be significantly simplified. The generally applicable toolset presented in this case study provides a solid basis for decision making and process optimization throughout process development. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 33:1368-1380, 2017.