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

Montano-Herrera, Liliana; Eilert, Tobias; Ho, I-Ting; Matysik, Milena; Laussegger, Michael; Guderlei, Ralph Joachim; Schrantz, Bernhard; Jung, Alexander; Bluhmki, Erich; Smiatek, Jens

doi:10.3390/pr10040662

Cited by 3 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random sampling from this distribution is used for the transfer to subsequent UOs. One advantage here is the combination of multiple models per UO, which may be useful in creating more robust predictive outcomes, especially in data-poor environments [ 21 ]. One consideration to add to this framework is the prediction of extreme model outputs.…”

Section: Introductionmentioning

confidence: 99%

Architectural and Technological Improvements to Integrated Bioprocess Models towards Real-Time Applications

Taylor

Pretzner

Zahel³

et al. 2022

Bioengineering

View full text Add to dashboard Cite

Integrated or holistic process models may serve as the engine of a digital asset in a multistep-process digital twin. Concatenated individual-unit operation models are effective at propagating errors over an entire process, but are nonetheless limited in certain aspects of recent applications that prevent their deployment as a plausible digital asset, particularly regarding bioprocess development requirements. Sequential critical quality attribute tests along the process chain that form output–input (i.e., pool-to-load) relationships, are impacted by nonaligned design spaces at different scales and by simulation distribution challenges. Limited development experiments also inhibit the exploration of the overall design space, particularly regarding the propagation of extreme noncontrolled parameter values. In this contribution, bioprocess requirements are used as the framework to improve integrated process models by introducing a simplified data model for multiunit operation processes, increasing statistical robustness, adding a new simulation flow for scale-dependent variables, and describing a novel algorithm for extrapolation in a data-driven environment. Lastly, architectural and procedural requirements for a deployed digital twin are described, and a real-time workflow is proposed, thus providing a final framework for a digital asset in bioprocessing along the full product life cycle.

show abstract

Section: Introductionmentioning

confidence: 99%

Architectural and Technological Improvements to Integrated Bioprocess Models towards Real-Time Applications

Taylor

Pretzner

Zahel³

et al. 2022

Bioengineering

View full text Add to dashboard Cite

show abstract

Process intensification in biopharmaceutical process development and production – an industrial perspective

Schaub,

Ankenbauer,

Habicher

et al. 2023

Physical Sciences Reviews

View full text Add to dashboard Cite

Process intensification aims to increase productivity in biologics manufacturing. Significant progress has been made in academia, the biopharmaceutical industry, and by the regulatory guidance since the 2000s. Process intensification can include all unit operations of a drug substance manufacturing process. The applied upstream concepts have consequences on the downstream process (DSP). The DSP process must manage larger product amounts while ensuring the required quality and impurity profiles, and cope with the available time frame as per scheduling requirements in a facility. Further, intensification in DSP is not based on a single technology only but rather on various technologies. This contribution provides an industry perspective on process intensification, describing basic concepts, technical and engineering aspects as well as the impact on the manufacturing process given existing facilities and a product portfolio to be manufactured. It also covers scientific approaches that support understanding and design of intensified bioprocesses. From an implementation perspective, the technologies used for intensification must be robust, scalable, and suitable for commercial manufacturing. Specific examples for a high seeding density fed batch (using N-1 perfusion) and a continuous process are provided for Chinese hamster ovary (CHO) cells producing therapeutic antibodies. Economic and sustainability aspects are addressed as well. Process intensification in an industrial environment is complex and many factors need to be considered, ranging from characteristics of a specific molecule to its commercial manufacturing at internal or external sites for global or regional markets.

show abstract

Solubilization of inclusion bodies: insights from explainable machine learning approaches

Walther,

Martinetz,

Friedrich

et al. 2023

Front. Chem. Eng.

View full text Add to dashboard Cite

We present explainable machine learning approaches for gaining deeper insights into the solubilization processes of inclusion bodies. The machine learning model with the highest prediction accuracy for the protein yield is further evaluated with regard to Shapley additive explanation (SHAP) values in terms of feature importance studies. Our results highlight an inverse fractional relationship between the protein yield and total protein concentration. Further correlations can also be observed for the dominant influences of the urea concentration and the underlying pH values. All findings are used to develop an analytical expression that is in reasonable agreement with experimental data. The resulting master curve highlights the benefits of explainable machine learning approaches for the detailed understanding of certain biopharmaceutical manufacturing steps.

show abstract

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

Cited by 3 publications

References 55 publications

Architectural and Technological Improvements to Integrated Bioprocess Models towards Real-Time Applications

Architectural and Technological Improvements to Integrated Bioprocess Models towards Real-Time Applications

Process intensification in biopharmaceutical process development and production – an industrial perspective

Solubilization of inclusion bodies: insights from explainable machine learning approaches

Contact Info

Product

Resources

About