Hybrid modeling as a QbD/PAT tool in process development: an industrial E. coli case study

Physics-informed neural networks for biopharmaceutical cultivation processes: Consideration of varying process parameter settings

We present a new modeling approach for the study and prediction of important process outcomes of biotechnological cultivation processes under the influence of process parameter variations. Our model is based on physics-informed neural networks (PINNs) in combination with kinetic growth equations. Using Taylor series, multivariate external process parameter variations for important variables such as temperature, seeding cell density and feeding rates can be integrated into the corresponding kinetic rates and the governing growth equations. In addition to previous approaches, PINNs also allow continuous and differentiable functions as predictions for the process outcomes. Accordingly, our results show that PINNs in combination with Taylor-series expansions for kinetic growth equations provide a very high prediction accuracy for important process variables such as cell densities and concentrations as well as a detailed study of individual and combined parameter influences. Furthermore, the proposed approach can also be used to evaluate the outcomes of new parameter variations and combinations, which enables a saving of experiments in combination with a model-driven optimization study of the design space.

An innovative hybrid modeling approach for simultaneous prediction of cell culture process dynamics and product quality

The use of hybrid models is extensively described in the literature to predict the process evolution in cell cultures. These models combine mechanistic and machine learning methods, allowing the prediction of complex process behavior, in the presence of many process variables, without the need to collect a large amount of data. Hybrid models cannot be directly used to predict final product critical quality attributes, or CQAs, because they are usually measured only at the end of the process, and more mechanistic knowledge is needed for many classes of CQAs. The historical models can instead predict the CQAs better; however, they cannot directly relate manipulated process parameters to final CQAs, as they require knowledge of the process evolution. In this work, we propose an innovative modeling approach based on combining a hybrid propagation model with a historical data-driven model, that is, the combined hybrid model, for simultaneous prediction of full process dynamics and CQAs. The performance of the combined hybrid model was evaluated on an industrial dataset and compared to classical black-box models, which directly relate manipulated process parameters to CQAs. The proposed combined hybrid model outperforms the black-box model by 33% on average in predicting the CQAs while requiring only around half of the data for model training to match performance. Thus, in terms of model accuracy and experimental costs, the combined hybrid model in this study provides a promising platform for process optimization applications.

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

Hybrid modeling, with an appropriate blend of the mechanistic and data-driven framework, is increasingly being adopted in bioprocess modeling, model-based experimental design (digital-twin), identification of critical process parameters, and optimization. However, the development of a hybrid model from experimental data is an inherently complex workflow, involving designed experiments, selection of the data-driven process, identification of model parameters, assessment fitness, and generalization capability. Depending on the complexity of the process system and purpose, each piece of these modules can flexibly be incorporated into the puzzle. However, this extra flexibility can be a cause of concern to trace an "optimal" model structure. In this paper, the development of hybrid models in a common bioprocess system, selection of data-driven components and their mapping to states, choice of parameter identification techniques, and model quality assurance are revisited. The challenges associated with hybrid-model development, and corrective actions have also been reviewed. The review also suggests the lack of data, and code sharing in communal repositories can be a hurdle in the exploration, and expansion of those tools in a bioprocess system.

Artificial intelligence and machine learning applications in biopharmaceutical manufacturing

Artificial intelligence and machine learning (AI-ML) offer vast potential in optimal design, monitoring, and control of biopharmaceutical manufacturing. The driving forces for adoption of AI-ML techniques include the growing global demand for biotherapeutics and the shift toward Industry 4.0, spurring the rise of integrated process platforms and continuous processes that require intelligent, automated supervision. This review summarizes AI-ML applications in biopharmaceutical manufacturing, with a focus on the most used AI-ML algorithms, including multivariate data analysis, artificial neural networks, and reinforcement learning. Perspectives on the future growth of AI-ML applications in the area and the challenges of implementing these techniques at manufacturing scale are also presented.

A General Hybrid Modeling Framework for Systems Biology Applications: Combining Mechanistic Knowledge with Deep Neural Networks under the SBML Standard

In this paper, a computational framework is proposed that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models that are currently stored in public databases in SBML. With the proposed framework, existing SBML models may be redesigned into hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and uploaded in model databases, where they may be further analyzed as regular SBML models. This approach is illustrated with three well-known case studies: the Escherichia coli threonine synthesis model, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications.

Advances in bioreactor control for production of biotherapeutic products

Advanced control strategies are well established in chemical, pharmaceutical, and food processing industries. Over the past decade, the application of these strategies is being explored for control of bioreactors for manufacturing of biotherapeutics. Most of the industrial bioreactor control strategies apply classical control techniques, with the control system designed for the facility at hand. However, with the recent progress in sensors, machinery, and industrial internet of things, and advancements in deeper understanding of the biological processes, coupled with the requirement of flexible production, the need to develop a robust and advanced process control system that can ease process intensification has emerged. This has further fuelled the development of advanced monitoring approaches, modeling techniques, process analytical technologies, and soft sensors. It is seen that proper application of these concepts can significantly improve bioreactor process performance, productivity, and reproducibility. This review is on the recent advancements in bioreactor control and its related aspects along with the associated challenges. This study also offers an insight into the future prospects for development of control strategies that can be designed for industrial-scale production of biotherapeutic products.

Development and Validation of an Artificial Neural-Network-Based Optical Density Soft Sensor for a High-Throughput Fermentation System

Optical density (OD) is a critical process parameter during fermentation, this being directly related to cell density, which provides valuable information regarding the state of the process. However, to measure OD, sampling of the fermentation broth is required. This is particularly challenging for high-throughput-microbioreactor (HT-MBR) systems, which require robotic liquid-handling (LiHa) systems for process control tasks, such as pH regulation or carbon feed additions. Bioreactor volume is limited and automated at-line sampling occupies the resources of LiHa systems; this affects their ability to carry out the aforementioned pipetting operations. Minimizing the number of physical OD measurements is therefore of significant interest. However, fewer measurements also result in less process information. This resource conflict has previously represented a challenge. We present an artificial neural-network-based soft sensor developed for the real-time estimation of the OD in an MBR system. This sensor was able to estimate the OD to a high degree of accuracy (>95%), even without informative process variables stemming from, e.g., off-gas analysis only available at larger scales. Furthermore, we investigated and demonstrated scaling of the soft sensor’s generalization capabilities with the data from different antibody fragments expressing Escherichia coli strains. This study contributes to accelerated biopharmaceutical process development.

Bioprocessing of recombinant proteins from Escherichia coli inclusion bodies: insights from structure-function relationship for novel applications

The formation of inclusion bodies (IBs) during expression of recombinant therapeutic proteins using E. coli is a significant hurdle in producing high-quality, safe, and efficacious medicines. The improved understanding of the structure-function relationship of the IBs has resulted in the development of novel biotechnologies that have streamlined the isolation, solubilization, refolding, and purification of the active functional proteins from the bacterial IBs. Together, this overall effort promises to radically improve the scope of experimental biology of therapeutic protein production and expand new prospects in IBs usage. Notably, the IBs are increasingly used for applications in more pristine areas such as drug delivery and material sciences. In this review, we intend to provide a comprehensive picture of the bio-processing of bacterial IBs, including assessing critical gaps that still need to be addressed and potential solutions to overcome them. We expect this review to be a useful resource for those working in the area of protein refolding and therapeutic protein production.

The use of predictive models to develop chromatography-based purification processes

Chromatography is the workhorse of biopharmaceutical downstream processing because it can selectively enrich a target product while removing impurities from complex feed streams. This is achieved by exploiting differences in molecular properties, such as size, charge and hydrophobicity (alone or in different combinations). Accordingly, many parameters must be tested during process development in order to maximize product purity and recovery, including resin and ligand types, conductivity, pH, gradient profiles, and the sequence of separation operations. The number of possible experimental conditions quickly becomes unmanageable. Although the range of suitable conditions can be narrowed based on experience, the time and cost of the work remain high even when using high-throughput laboratory automation. In contrast, chromatography modeling using inexpensive, parallelized computer hardware can provide expert knowledge, predicting conditions that achieve high purity and efficient recovery. The prediction of suitable conditions in silico reduces the number of empirical tests required and provides in-depth process understanding, which is recommended by regulatory authorities. In this article, we discuss the benefits and specific challenges of chromatography modeling. We describe the experimental characterization of chromatography devices and settings prior to modeling, such as the determination of column porosity. We also consider the challenges that must be overcome when models are set up and calibrated, including the cross-validation and verification of data-driven and hybrid (combined data-driven and mechanistic) models. This review will therefore support researchers intending to establish a chromatography modeling workflow in their laboratory.

Promoting Sustainability through Next-Generation Biologics Drug Development

The fourth industrial revolution in 2011 aimed to transform the traditional manufacturing processes. As part of this revolution, disruptive innovations in drug development and data science approaches have the potential to optimize CMC (chemistry, manufacture, and control). The real-time simulation of processes using “digital twins” can maximize efficiency while improving sustainability. As part of this review, we investigate how the World Health Organization’s 17 sustainability goals can apply toward next-generation drug development. We analyze the state-of-the-art laboratory leadership, inclusive personnel recruiting, the latest therapy approaches, and intelligent process automation. We also outline how modern data science techniques and machine tools for CMC help to shorten drug development time, reduce failure rates, and minimize resource usage. Finally, we systematically analyze and compare existing approaches to our experiences with the high-throughput laboratory KIWI-biolab at the TU Berlin. We describe a sustainable business model that accelerates scientific innovations and supports global action toward a sustainable future.

Generic and specific recurrent neural network models: Applications for large and small scale biopharmaceutical upstream processes

The calculation of temporally varying upstream process outcomes is a challenging task. Over the last years, several parametric, semi-parametric as well as non-parametric approaches were developed to provide reliable estimates for key process parameters. We present generic and product-specific recurrent neural network (RNN) models for the computation and study of growth and metabolite-related upstream process parameters as well as their temporal evolution. Our approach can be used for the control and study of single product-specific large-scale manufacturing runs as well as generic small-scale evaluations for combined processes and products at development stage. The computational results for the product titer as well as various major upstream outcomes in addition to relevant process parameters show a high degree of accuracy when compared to experimental data and, accordingly, a reasonable predictive capability of the RNN models. The calculated values for the root-mean squared errors of prediction are significantly smaller than the experimental standard deviation for the considered process run ensembles, which highlights the broad applicability of our approach. As a specific benefit for platform processes, the generic RNN model is also used to simulate process outcomes for different temperatures in good agreement with experimental results. The high level of accuracy and the straightforward usage of the approach without sophisticated parameterization and recalibration procedures highlight the benefits of the RNN models, which can be regarded as promising alternatives to existing parametric and semi-parametric methods.

Industry 4.0 for pharmaceutical manufacturing: Preparing for the smart factories of the future

Over the last two centuries, medicines have evolved from crude herbal and botanical preparations into more complex manufacturing of sophisticated drug products and dosage forms. Along with the evolution of medicines, the manufacturing practices for their production have advanced from small-scale manual processing with simple tools to large-scale production as part of a trillion-dollar pharmaceutical industry. Today's pharmaceutical manufacturing technologies continue to evolve as the internet of things, artificial intelligence, robotics, and advanced computing begin to challenge the traditional approaches, practices, and business models for the manufacture of pharmaceuticals. The application of these technologies has the potential to dramatically increase the agility, efficiency, flexibility, and quality of the industrial production of medicines. How these technologies are deployed on the journey from data collection to the hallmark digital maturity of Industry 4.0 will define the next generation of pharmaceutical manufacturing. Acheiving the benefits of this future requires a vision for it and an understanding of the extant regulatory, technical, and logistical barriers to realizing it.

Model-assisted DoE software: optimization of growth and biocatalysis in Saccharomyces cerevisiae bioprocesses

Bioprocess development and optimization are still cost- and time-intensive due to the enormous number of experiments involved. In this study, the recently introduced model-assisted Design of Experiments (mDoE) concept (Möller et al. in Bioproc Biosyst Eng 42(5):867, https://doi.org/10.1007/s00449-019-02089-7 , 2019) was extended and implemented into a software ("mDoE-toolbox") to significantly reduce the number of required cultivations. The application of the toolbox is exemplary shown in two case studies with Saccharomyces cerevisiae. In the first case study, a fed-batch process was optimized with respect to the pH value and linearly rising feeding rates of glucose and nitrogen source. Using the mDoE-toolbox, the biomass concentration was increased by 30% compared to previously performed experiments. The second case study was the whole-cell biocatalysis of ethyl acetoacetate (EAA) to (S)-ethyl-3-hydroxybutyrate (E3HB), for which the feeding rates of glucose, nitrogen source, and EAA were optimized. An increase of 80% compared to a previously performed experiment with similar initial conditions was achieved for the E3HB concentration.

Review of machine learning algorithms' application in pharmaceutical technology

Machine learning algorithms, and artificial intelligence in general, have a wide range of applications in the field of pharmaceutical technology. Starting from the formulation development, through a great potential for integration within the Quality by design framework, these data science tools provide a better understanding of the pharmaceutical formulations and respective processing. Machine learning algorithms can be especially helpful with the analysis of the large volume of data generated by the Process analytical technologies. This paper provides a brief explanation of the artificial neural networks, as one of the most frequently used machine learning algorithms. The process of the network training and testing is described and accompanied with illustrative examples of machine learning tools applied in the context of pharmaceutical formulation development and related technologies, as well as an overview of the future trends. Recently published studies on more sophisticated methods, such as deep neural networks and light gradient boosting machine algorithm, have been described. The interested reader is also referred to several official documents (guidelines) that pave the way for a more structured representation of the machine learning models in their prospective submissions to the regulatory bodies.

Decision Making and Risk Management in Biopharmaceutical Engineering-Opportunities in the Age of Covid-19 and Digitalization

In 2020, the Covid-19 pandemic resulted in a worldwide challenge without an evident solution. Many persons and authorities involved befriended the value of available data and established expertise to make decisions under time pressure. This omnipresent example is used to illustrate the decision-making procedure in biopharmaceutical manufacturing. This commentary addresses important challenges and opportunities to support risk management in biomanufacturing through a process-centered digitalization approach combining two vital worlds-formalized engineering fundamentals and data empowerment through customized machine learning. With many enabling technologies already available and first success stories reported, it will depend on the interaction of different groups of stakeholders how and when the huge potential of the discussed technologies will be broadly and systematically realized.

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.

Working within the Design Space: Do Our Static Process Characterization Methods Suffice?

The Process Analytical Technology initiative and Quality by Design paradigm have led to changes in the guidelines and views of how to develop drug manufacturing processes. On this occasion the concept of the design space, which describes the impact of process parameters and material attributes on the attributes of the product, was introduced in the ICH Q8 guideline. The way the design space is defined and can be presented for regulatory approval seems to be left to the applicants, among who at least a consensus on how to characterize the design space seems to have evolved. The large majority of design spaces described in publications seem to follow a "static" statistical experimentation and modeling approach. Given that temporal deviations in the process parameters (i.e., moving within the design space) are of a dynamic nature, static approaches might not suffice for the consideration of the implications of variations in the values of the process parameters. In this paper, different forms of design space representations are discussed and the current consensus is challenged, which in turn, establishes the need for a dynamic representation and characterization of the design space. Subsequently, selected approaches for a dynamic representation, characterization and validation which are proposed in the literature are discussed, also showcasing the opportunity to integrate the activities of process characterization, process monitoring and process control strategy development.

Monitoring Parallel Robotic Cultivations with Online Multivariate Analysis

In conditional microbial screening, a limited number of candidate strains are tested at different conditions searching for the optimal operation strategy in production (e.g., temperature and pH shifts, media composition as well as feeding and induction strategies). To achieve this, cultivation volumes of >10 mL and advanced control schemes are required to allow appropriate sampling and analyses. Operations become even more complex when the analytical methods are integrated into the robot facility. Among other multivariate data analysis methods, principal component analysis (PCA) techniques have especially gained popularity in high throughput screening. However, an important issue specific to high throughput bioprocess development is the lack of so-called golden batches that could be used as a basis for multivariate analysis. In this study, we establish and present a program to monitor dynamic parallel cultivations in a high throughput facility. PCA was used for process monitoring and automated fault detection of 24 parallel running experiments using recombinant E. coli cells expressing three different fluorescence proteins as the model organism. This approach allowed for capturing events like stirrer failures and blockage of the aeration system and provided a good signal to noise ratio. The developed application can be easily integrated in existing data- and device-infrastructures, allowing automated and remote monitoring of parallel bioreactor systems.

When Is an In Silico Representation a Digital Twin? A Biopharmaceutical Industry Approach to the Digital Twin Concept

Digital twins (DTs) are expected to render process development and life-cycle management much more cost-effective and time-efficient. A DT definition, a brief retrospect on their history and expectations for their deployment in today's business environment, and a detailed financial assessment of their attractive economic benefits are provided in this chapter. The argument that restrictive guidelines set forth by regulatory agencies would hinder the adoption of DTs in the (bio)pharmaceutical industry is revisited, concluding that those companies who collaborate with the agencies to further their technical capabilities will gain significant competitive advantage. The analyzed process development examples show high methodological readiness levels but low systematic adoption of technology. Given the technical feasibilities, financial opportunities, and regulatory encouragement, concerns regarding intellectual property and data sharing, though required to be taken into account, will at best delay an industry-wide adoption of DTs. In conclusion, it is expected that a strategic investment in DTs now will gain an advantage over competition that will be difficult to overcome by late adopters.

Digital Twins and Their Role in Model-Assisted Design of Experiments

Rising demands for biopharmaceuticals and the need to reduce manufacturing costs increase the pressure to develop productive and efficient bioprocesses. Among others, a major hurdle during process development and optimization studies is the huge experimental effort in conventional design of experiments (DoE) methods. As being an explorative approach, DoE requires extensive expert knowledge about the investigated factors and their boundary values and often leads to multiple rounds of time-consuming and costly experiments. The combination of DoE with a virtual representation of the bioprocess, called digital twin, in model-assisted DoE (mDoE) can be used as an alternative to decrease the number of experiments significantly. mDoE enables a knowledge-driven bioprocess development including the definition of a mathematical process model in the early development stages. In this chapter, digital twins and their role in mDoE are discussed. First, statistical DoE methods are introduced as the basis of mDoE. Second, the combination of a mathematical process model and DoE into mDoE is examined. This includes mathematical model structures and a selection scheme for the choice of DoE designs. Finally, the application of mDoE is discussed in a case study for the medium optimization in an antibody-producing Chinese hamster ovary cell culture process.

Real-time monitoring and model-based prediction of purity and quantity during a chromatographic capture of fibroblast growth factor 2

Process analytical technology combines understanding and control of the process with real‐time monitoring of critical quality and performance attributes. The goal is to ensure the quality of the final product. Currently, chromatographic processes in biopharmaceutical production are predominantly monitored with UV/Vis absorbance and a direct correlation with purity and quantity is limited. In this study, a chromatographic workstation was equipped with additional online sensors, such as multi‐angle light scattering, refractive index, attenuated total reflection Fourier‐transform infrared, and fluorescence spectroscopy. Models to predict quantity, host cell proteins (HCP), and double‐stranded DNA (dsDNA) content simultaneously were developed and exemplified by a cation exchange capture step for fibroblast growth factor 2 expressed in Escherichia coliOnline data and corresponding offline data for product quantity and co‐eluting impurities, such as dsDNA and HCP, were analyzed using boosted structured additive regression. Different sensor combinations were used to achieve the best prediction performance for each quality attribute. Quantity can be adequately predicted by applying a small predictor set of the typical chromatographic workstation sensor signals with a test error of 0.85 mg/ml (range in training data: 0.1–28 mg/ml). For HCP and dsDNA additional fluorescence and/or attenuated total reflection Fourier‐transform infrared spectral information was important to achieve prediction errors of 200 (2–6579 ppm) and 340 ppm (8–3773 ppm), respectively.

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.

From Physics to Bioengineering: Microbial Cultivation Process Design and Feeding Rate Control Based on Relative Entropy Using Nuisance Time

For historic reasons, industrial knowledge of reproducibility and restrictions imposed by regulations, open-loop feeding control approaches dominate in industrial fed-batch cultivation processes. In this study, a generic gray box biomass modeling procedure uses relative entropy as a key to approach the posterior similarly to how prior distribution approaches the posterior distribution by the multivariate path of Lagrange multipliers, for which a description of a nuisance time is introduced. The ultimate purpose of this study was to develop a numerical semi-global convex optimization procedure that is dedicated to the calculation of feeding rate time profiles during the fed-batch cultivation processes. The proposed numerical semi-global convex optimization of relative entropy is neither restricted to the gray box model nor to the bioengineering application. From the bioengineering application perspective, the proposed bioprocess design technique has benefits for both the regular feed-forward control and the advanced adaptive control systems, in which the model for biomass growth prediction is compulsory. After identification of the gray box model parameters, the options and alternatives in controllable industrial biotechnological processes are described. The main aim of this work is to achieve high reproducibility, controllability, and desired process performance. Glucose concentration measurements, which were used for the development of the model, become unnecessary for the development of the desired microbial cultivation process.