The identification of suitable cell lines for monoclonal antibody (mAb) manufacturing is a complex and resource-intensive process. We have developed an AI-driven approach using machine learning to accelerate clone selection. The model uses early-stage multi-omics data to predict late-stage cell line productivity, enabling early detection of high-producer cell lines. This shift to a model-centric process significantly reduces project timelines, accelerates mAb delivery, and fosters a data-driven culture in bioprocessing.

Digital twins have become a cornerstone in modern bioprocess development, enabling accelerated timelines, deeper process understanding, and potentially robust real-time control. This presentation will showcase industrial examples across monoclonal antibodies, viral vectors, and advanced therapies, highlighting applications from batch to continuous manufacturing. Case studies will demonstrate how tailored modelling, smart experimental design, and real-time deployment can drive end-to-end integration, seamless scale-up, and efficient technology transfer. By addressing both established and emerging modalities, the talk will illustrate how digital twins are moving beyond proof-of-concept to deliver industrial impact, fostering flexibility, resilience, and cost efficiency in next-generation biomanufacturing.

Efficient experimentation is critical in bioprocess development, where time, cost, and complexity constrain traditional Design of Experiments. We introduce a model-based algorithm that leverages Pareto fronts and Bayesian optimisation to balance exploitation of high-performing regions with exploration of uncertain areas. This approach accelerates learning, reduces experimental burden, and scales effectively to high-dimensional design spaces, providing a robust and resource-efficient strategy for modern bioprocess optimisation, while effectively exploring trade-offs among performance and quality objectives.

This presentation describes the development and optimisation of an intensified upstream process for a high-value commercial biologic. By leveraging advanced at-line metabolic data, our team identified key drivers of cell growth and productivity, enabling rapid process adjustments and improved consistency. We will share the analytical approach, decision-making framework, and performance outcomes that demonstrate how real-time metabolic insights can accelerate scale-up and ensure robust, cost-effective manufacturing.

Hybrid modelling that combines first-principles with machine learning is emerging as a cornerstone of Biopharma 4.0. In this work, we explore deep hybrid model architectures that seamlessly integrate deep neural networks with mechanistic equations. Our results demonstrate a consistent generalisation advantage of deep hybrid models across multiple CHO platforms. This study highlights the transformative potential of deep hybrid modelling for accelerating process development in modern biomanufacturing.

The KIWI-biolab at TU Berlin exemplifies a cognitive self-driving laboratory integrating automated fermentation, analytics, and model-based optimisation within a reproducible workflow. The presentation outlines the essential components required to realise such laboratories—covering automation, modelling, and workflow orchestration—and illustrates their functionality through examples of adaptive process control and model-based optimisation for antibody Fab fragment production in Escherichia coli.

Accurate quantification of glycogen in biological samples is critical for studying metabolism, disease mechanisms, and therapeutic impact. This presentation describes the development of a novel automated workflow for measuring glycogen in tissue lysates with improved sensitivity and reproducibility. Leveraging optimised sample preparation, advanced detection methods, and automation, the approach minimises variability and enables high-throughput analysis. The enhanced performance supports deeper insights into glycogen biology and reliable evaluation of metabolic interventions.

Glycans attached to antibodies mediate inflammatory pathways in disease and aging but the mechanisms that regulate antibody glycosylation are still largely unknown. To decipher the molecular determinants of antibody glycosylation, specifically immunoglobulin G (IgG), we developed a series of robust CRISPR/dCas9 cell line platforms based on our flexible and extendible EpiToolbox scaffold. We discovered that the control of IgG glycosylation extends far beyond the known glycosylation-related genes.

Leveraging CHO cells’ established role in producing human-like glycosylated therapeutics, we developed a panel of 30 glycoengineered CHO (geCHO) cells. This platform enables tailored glycosylation for protein production. Screening with geCHO we have identified therapeutic candidates exhibiting enhanced activity, optimised immunogenicity, and improved stability, thereby demonstrating the panel’s potential to optimise next generation biotherapeutics.