Comparison of physics-based and data-driven modelling techniques for dynamic optimisation of fed-batch bioprocesses

The development of digital bioprocessing technologies is critical to operate modern industrial bioprocesses. This study conducted the first investigation on the efficiency of using physics-based and data-driven models for the dynamic optimisation of long-term bioprocess. More specifically, this study exploits a predictive kinetic model and a cutting-edge data-driven model to compute open-loop optimisation strategies for the production of microalgal lutein during a fed-batch operation. Light intensity and nitrate inflow rate are used as control variables given their key impact on biomass growth and lutein synthesis. By employing different optimisation algorithms, several optimal control sequences were computed. Due to the distinct model construction principles and sophisticated process mechanisms, the physics-based and the data-driven models yielded contradictory optimisation strategies. The experimental verification confirms that the data-driven model predicted a closer result to the experiments than the physics-based model. Both models succeeded in improving lutein intracellular content by over 40% compared to the highest previous record; however, the data-driven model outperformed the kinetic model when optimising total lutein production and achieved an increase of 40–50%. This indicates the possible advantages of using data-driven modelling for optimisation and prediction of complex dynamic bioprocesses, and its potential in industrial bio-manufacturing systems.     

Combining model structure identification and hybrid modelling for photo-production process predictive simulation and optimisation

Integrating physical knowledge and machine learning is a critical aspect of developing industrially focused digital twins for monitoring, optimisation, and design of microalgal and cyanobacterial photo-production processes. However, identifying the correct model structure to quantify the complex biological mechanism poses a severe challenge for the construction of kinetic models, while the lack of data due to the time-consuming experiments greatly impedes applications of most data-driven models. This study proposes the use of an innovative hybrid modelling approach that consists of a simple kinetic model to govern the overall process dynamic trajectory and a data-driven model to estimate mismatch between the kinetic equations and the real process. An advanced automatic model structure identification strategy is adopted to simultaneously identify the most physically probable kinetic model structure and minimum number of data-driven model parameters that can accurately represent multiple data sets over a broad spectrum of process operating conditions. Through this hybrid modelling and automatic structure identification framework, a highly accurate mathematical model was constructed to simulate and optimise an algal lutein production process. Performance of this hybrid model for long-term predictive modelling, optimisation, and online self-calibration is demonstrated and thoroughly discussed, indicating its significant potential for future industrial application.     

A reinforcement learning-based hybrid modeling framework for bioprocess kinetics identification

Constructing predictive models to simulate complex bioprocess dynamics, particularly time-varying (i.e., parameters varying over time) and history-dependent (i.e., current kinetics dependent on historical culture conditions) behavior, has been a longstanding research challenge. Current advances in hybrid modeling offer a solution to this by integrating kinetic models with data-driven techniques. This article proposes a novel two-step framework: first (i) speculate and combine several possible kinetic model structures sourced from process and phenomenological knowledge, then (ii) identify the most likely kinetic model structure and its parameter values using model-free Reinforcement Learning (RL). Specifically, Step 1 collates feasible history-dependent model structures, then Step 2 uses RL to simultaneously identify the correct model structure and the time-varying parameter trajectories. To demonstrate the performance of this framework, a range of in-silico case studies were carried out. The results show that the proposed framework can efficiently construct high-fidelity models to quantify both time-varying and history-dependent kinetic behaviors while minimizing the risks of over-parametrization and over-fitting. Finally, the primary advantages of the proposed framework and its limitation were thoroughly discussed in comparison to other existing hybrid modeling and model structure identification techniques, highlighting the potential of this framework for general bioprocess modeling.     

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.     

Prospective inference of bioprocess cell viability through chemometric modeling of fluorescence multiway data

In this investigation, the fermentation step of a standard mammalian cell-based industrial bioprocess for the production of a therapeutic protein was studied, with particular emphasis on the evolution of cell viability. This parameter constitutes one of the critical variables for bioprocess monitoring since it can affect downstream operations and the quality of the final product. In addition, when the cells experiment an unpredictable drop in viability, the assessment of this variable through classic off-line methods may not provide information sufficiently in advance to take corrective actions. In this context, Process Analytical Technology (PAT) framework aims to develop novel strategies for more efficient monitoring of critical variables, in order to improve the bioprocess performance. Thus, in this work, a set of chemometric tools were integrated to establish a PAT strategy to monitor cell viability, based on fluorescence multiway data obtained from fermentation samples of a particular bioprocess, in two different scales of operation. The spectral information, together with data regarding process variables, was integrated through chemometric exploratory tools to characterize the bioprocess and stablish novel criteria for the monitoring of cell viability. These findings motivated the development of a multivariate classification model, aiming to obtain predictive tools for the monitoring of future lots of the same bioprocess. The model could be satisfactorily fitted, showing the non-error rate of prediction of 100%.     

Review of advanced physical and data-driven models for dynamic bioprocess simulation: Case study of algae–bacteria consortium wastewater treatment

Microorganism production and remediation processes are of critical importance to the next generation of sustainable industries. Undertaking mathematical treatment of dynamic biosystems operating at any spatial or temporal scale is essential to guarantee their performance and safety. However, constructing physical models remains a challenge due to the extreme complexity of process biological mechanisms. Data-driven models also encounter severe limitations because datasets from large-scale bioprocesses are often scarce without complete information and on a restricted operational space. To fill this gap, the current research compares the performance of advanced physical and data-driven models for dynamic bioprocess simulations subject to incomplete and scarce datasets, which to the best of our knowledge has never been addressed before. In specific, kinetic models were constructed by integrating different classic models, and state-of-the-art hyperparameter selection frameworks were developed to design artificial neural networks and Gaussian process regression models. An algae–bacteria consortium wastewater treatment process was selected to test the accuracy of these modeling strategies, as it is one of the most sophisticated biosystems due to the intricate mutualistic and competitive interactions. Based on the current results and available data, a heuristic model selection procedure is provided. This study paves the way to facilitate future bioprocess modeling.     

Biomass soft sensor for a Pichia pastoris fed-batch process based on phase detection and hybrid modeling

A common control strategy for the production of recombinant proteins in Pichia pastoris using the alcohol oxidase 1 (AOX1) promotor is to separate the bioprocess into two main phases: biomass generation on glycerol and protein production via methanol induction. This study reports the establishment of a soft sensor for the prediction of biomass concentration that adapts automatically to these distinct phases. A hybrid approach combining mechanistic (carbon balance) and data-driven modeling (multiple linear regression) is used for this purpose. The model parameters are dynamically adapted according to the current process phase using a multilevel phase detection algorithm. This algorithm is based on the online data of CO₂ in the off-gas (absolute value and first derivative) and cumulative base feed. The evaluation of the model resulted in a mean relative prediction error of 5.52% and R² of .96 for the entire process. The resulting model was implemented as a soft sensor for the online monitoring of the P. pastoris bioprocess. The soft sensor can be used for quality control and as input to process control systems, for example, for methanol control.     

Industrial bioprocess control and optimization in the context of systems biotechnology

The developments of the systems biotechnology and its application in the industrial process open up new horizons to industrial biotechnology. The unprecedented understanding of the relationships between cellular behaviors and the surrounding environments during the bioprocess has been achieved. In this paper, we review new advances in the strain improvement, bioprocess control and optimization. The holistic viewpoints and ideas applied in industrial bioprocesses and their future prospects are discussed by illustrating some successful cases.     

Scale-up of a new bacterial mannitol production process

D-Mannitol is a sugar alcohol with applications in chemistry, food and pharmaceutical industries, and medicine. Commercially, mannitol is produced by catalytic hydrogenation. Although this process is widely used, it is not optimal for mannitol production. New processes, including chemical, enzymatic, and microbial processes, are frequently developed and evaluated against the existing hydrogenation processes. In earlier papers, we have described the identification of a food-grade lactic acid bacterium strain, Leuconostoc mesenteroides ATCC-9135, with efficient mannitol production capabilities and the development and optimization of a new bioprocess in which the strain was applied. The new bioprocess is simple. It requires a reduced bioreactor with the following features: sterilization, pH and T control (at mild conditions), and slow mixing. The contamination risk of the new bioprocess is low, and the downstream processing protocol comprises simple, widely used unit operations: evaporation, crystallization, crystal separation, and drying. On a 2-L laboratory scale, high mannitol yields from fructose (93-97%) and volumetric mannitol productivities (>20 g L(-1) h(-1)) were achieved. In this paper, the scalability of the new bioprocess was tested on a small pilot scale (100 L). In the pilot plant, production levels were achieved similar to those in the laboratory. Also, high-purity mannitol crystals were obtained at similar yield levels. The results presented in this paper indicate that the new bioprocess can easily be scaled-up to an industrial scale and that the production levels achieved with it are comparable to the catalytic hydrogenation processes.     

Framework for online optimization of recombinant protein expression in high-cell-density Escherichia coli cultures using GFP-fusion monitoring

A framework for the online optimization of protein induction using green fluorescent protein (GFP)-monitoring technology was developed for high-cell-density cultivation of Escherichia coli. A simple and unstructured mathematical model was developed that described well the dynamics of cloned chloramphenicol acetyltransferase (CAT) production in E. coli JM105 was developed. A sequential quadratic programming (SQP) optimization algorithm was used to estimate model parameter values and to solve optimal open-loop control problems for piecewise control of inducer feed rates that maximize productivity. The optimal inducer feeding profile for an arabinose induction system was different from that of an isopropyl-beta-D-thiogalactopyranoside (IPTG) induction system. Also, model-based online parameter estimation and online optimization algorithms were developed to determine optimal inducer feeding rates for eventual use of a feedback signal from a GFP fluorescence probe (direct product monitoring with 95-minute time delay). Because the numerical algorithms required minimal processing time, the potential for product-based and model-based online optimal control methodology can be realized.     

Improvement of bioprocess monitoring: development of novel concepts

The advancement of bioprocess monitoring will play a crucial role to meet the future requirements of bioprocess technology. Major issues are the acceleration of process development to reduce the time to the market and to ensure optimal exploitation of the cell factory and further to cope with the requirements of the Process Analytical Technology initiative. Due to the enormous complexity of cellular systems and lack of appropriate sensor systems microbial production processes are still poorly understood. This holds generally true for the most microbial production processes, in particular for the recombinant protein production due to strong interaction between recombinant gene expression and host cell metabolism. Therefore, it is necessary to scrutinise the role of the different cellular compartments in the biosynthesis process in order to develop comprehensive process monitoring concepts by involving the most significant process variables and their interconnections. Although research for the development of novel sensor systems is progressing their applicability in bioprocessing is very limited with respect to on-line and in-situ measurement due to specific requirements of aseptic conditions, high number of analytes, drift, and often rather low physiological relevance. A comprehensive survey of the state of the art of bioprocess monitoring reveals that only a limited number of metabolic variables show a close correlation to the currently explored chemical/physical principles. In order to circumvent this unsatisfying situation mathematical methods are applied to uncover "hidden" information contained in the on-line data and thereby creating correlations to the multitude of highly specific biochemical off-line data. Modelling enables the continuous prediction of otherwise discrete off-line data whereby critical process states can be more easily detected. The challenging issue of this concept is to establish significant on-line and off-line data sets. In this context, online sensor systems are reviewed with respect to commercial availability in combination with the suitability of offline analytical measurement methods. In a case study, the aptitude of the concept to exploit easily available online data for prediction of complex process variables in a recombinant E. coli fed-batch cultivation aiming at the improvement of monitoring capabilities is demonstrated. In addition, the perspectives for model-based process supervision and process control are outlined.     

Intelligent real-time performance monitoring and quality prediction for batch/fed-batch cultivations

Supervision of batch bioprocess operations in real-time during the progress of a batch run offers many advantages over end-of-batch quality control. Multivariate statistical techniques such as multiway partial least squares (MPLS) provide an efficient modeling and supervision framework. A new type of MPLS modeling technique that is especially suitable for online real-time process monitoring and the multivariate monitoring charts are presented. This online process monitoring technique is also extended to include predictions of end-of-batch quality measurements during the progress of a batch run. Process monitoring, quality estimation and fault diagnosis activities are automated and supervised by embedding them into a real-time knowledge-based system (RTKBS). Interpretation of multivariate charts is also automated through a generic rule-base for efficient alarm handling. The integrated RTKBS and the implementation of MPLS-based process monitoring and quality control are illustrated using a fed-batch penicillin production benchmark process simulator.     

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

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.     

A new generation of predictive models: The added value of hybrid models for manufacturing processes of therapeutic proteins

Due to the lack of complete understanding of metabolic networks and reaction pathways, establishing a universal mechanistic model for mammalian cell culture processes remains a challenge. Contrarily, data-driven approaches for modeling these processes lack extrapolation capabilities. Hybrid modeling is a technique that exploits the synergy between the two modeling methods. Although mammalian cell cultures are among the most relevant processes in biotechnology and indeed looks ideal for hybrid modeling, their application has only been proposed but never developed in the literature. This study provides a quantitative assessment of the improvement brought by hybrid models with respect to the state-of-the-art statistical predictive models in the context of therapeutic protein production. This is illustrated using a dataset obtained from a 3.5 L fed-batch experiment. With the goal to robustly define the process design space, hybrid models reveal a superior capability to predict the time evolution of different process variables using only the initial and process conditions in comparison to the statistical models. Hybrid models not only feature more accurate prediction results but also demonstrate better robustness and extrapolation capabilities. For the future application, this study highlights the added value of hybrid modeling for model-based process optimization and design of experiments.     

Integrated framework of nonlinear prediction and process monitoring for complex biological processes

Bioprocesses and biosystems have nonlinear and multiple operation patterns depending on the influent loads, temperatures, the activity of microorganisms, and other factors. In this paper, an integrated framework of nonlinear modeling and process monitoring methods is developed for a complex biological process. The proposed method is based on modeling by fuzzy partial least squares (FPLS) and on process monitoring by a statistical decomposition, which is suitable for predicting and supervising a nonlinear biological process. Case studies in the bio-simulated process and industrial biological plant show that the proposed method can give superior prediction and monitoring performance in complex biological plants compared to other linear and nonlinear methods, since it can effectively capture the nonlinear causal relationship within the biosystem. This gives us the integrated framework that is able to both model and monitor the nonlinear bioprocess simultaneously.     

The potential of random forest and neural networks for biomass and recombinant protein modeling in Escherichia coli fed‐batch fermentations

Product quality assurance strategies in production of biopharmaceuticals currently undergo a transformation from empirical “quality by testing” to rational, knowledge‐based “quality by design” approaches. The major challenges in this context are the fragmentary understanding of bioprocesses and the severely limited real‐time access to process variables related to product quality and quantity. Data driven modeling of process variables in combination with model predictive process control concepts represent a potential solution to these problems. The selection of statistical techniques best qualified for bioprocess data analysis and modeling is a key criterion. In this work a series of recombinant Escherichia coli fed‐batch production processes with varying cultivation conditions employing a comprehensive on‐ and offline process monitoring platform was conducted. The applicability of two machine learning methods, random forest and neural networks, for the prediction of cell dry mass and recombinant protein based on online available process parameters and two‐dimensional multi‐wavelength fluorescence spectroscopy is investigated. Models solely based on routinely measured process variables give a satisfying prediction accuracy of about ± 4% for the cell dry mass, while additional spectroscopic information allows for an estimation of the protein concentration within ± 12%. The results clearly argue for a combined approach: neural networks as modeling technique and random forest as variable selection tool.     

基于比速率及代谢流的黑曲霉突变株和野生株分析

黑曲霉具备优异的外源蛋白表达和分泌能力,从而被广泛应用于工业酶制剂的生产。通过研究黑曲霉突变株和野生株在相同培养条件下生理参数和代谢流的差异,确定了黑曲霉合成糖化酶过程中的限制性因素。宏观动力学分析发现,较之野生株,突变株具有较高的最大比生长速率,并且副产物得率降低了90%,底物利用率提高了近30%,表明突变株与野生株在碳源分配和产物转化率上具有明显的差异。利用流平衡分析（FBA）计算胞内代谢通量分布,发现还原力和核糖的供应水平是限制菌体合成的主要因素,而前体氨基酸是合成糖化酶最主要的限制性因素。这些研究结果为后续发酵工艺优化和菌株基因改造提供了有益的思路。     

Applications of metabolic modeling to drive bioprocess development for the production of value-added chemicals

Increasing numbers of value added chemicals are being produced using microbial fermentation strategies. Computational modeling and simulation of microbial metabolism is rapidly becoming an enabling technology that is driving a new paradigm to accelerate the bioprocess development cycle. In particular, constraint-based modeling and the development of genome-scale models of industrial microbes are finding increasing utility across many phases of the bioprocess development workflow. Herein, we review and discuss the requirements and trends in the industrial application of this technology as we build toward integrated computational/experimental platforms for bioprocess engineering. Specifically we cover the following topics: (1) genome-scale models as genetically and biochemically consistent representations of metabolic networks; (2) the ability of these models to predict, assess, and interpret metabolic physiology and flux states of metabolism; (3) the model-guided integrative analysis of high throughput ‘omics’ data; (4) the reconciliation and analysis of on- and off-line fermentation data as well as flux tracing data; (5) model-aided strain design strategies and the integration of calculated biotransformation routes; and (6) control and optimization of the fermentation processes. Collectively, constraint-based modeling strategies are impacting the iterative characterization of metabolic flux states throughout the bioprocess development cycle, while also driving metabolic engineering strategies and fermentation optimization.     

Theoretical approach to modelling and analysis of the bioprocess with product inhibition and impulse effect

This work presents the first mathematical model of a bioprocess with product inhibition and impulse effect. To begin with, an exemplary mathematical bioprocess model with product inhibition and impulse effect is formulated. Then, according to the model, the analysis of bioprocess stability is presented. The article expresses the product oscillation period, which provides the precise feeding time frame for the regulator bioprocess to achieve an equivalent stable output as that of a bioprocess with impulse effect in the same production environment. Moreover, in this work, the optimization of the production process with respect to the tunable parameters is investigated, and analytical expressions of their optimal values are provided. Numerical simulations using biological data are presented to illustrate the main results.     

Evaluating metabolic stress and plasmid stability in plasmid DNA production by Escherichia coli

In the context of recombinant DNA technology, the development of feasible and high-yielding plasmid DNA production processes has regained attention as more evidence for its efficacy as vectors for gene therapy and DNA vaccination arise. When producing plasmid DNA in Escherichia coli, a number of biological restraints, triggered by plasmid maintenance and replication as well as culture conditions are responsible for limiting final biomass and product yields. This termed "metabolic burden" can also cause detrimental effects on plasmid stability and quality, since the cell machinery is no longer capable of maintaining an active metabolism towards plasmid synthesis and the stress responses elicited by plasmid maintenance can also cause increased plasmid instability. The optimization of plasmid DNA production bioprocesses is still hindered by the lack of information on the host metabolic responses as well as information on plasmid instability. Therefore, systematic and on-line approaches are required not only to characterise this "metabolic burden" and plasmid stability but also for the design of appropriate metabolic engineering and culture strategies. The monitoring tools described to date rapidly evolve from laborious, off-line and at-line monitoring to online monitoring, at a time-scale that enables researchers to solve these bioprocessing problems as they occur. This review highlights major E. coli biological alterations caused by plasmid maintenance and replication, possible causes for plasmid instability and discusses the ability of currently employed bioprocess monitoring techniques to provide information in order to circumvent metabolic burden and plasmid instability, pointing out the possible evolution of these methods towards online bioprocess monitoring.