Deep learning is a promising approach for building sequence-to-expression models for strain optimisation. But these need large and costly data that create steep entry barriers for many laboratories. In this talk I will discuss data requirements and how they impact predictive accuracy, alongside training strategies for improved prediction of protein expression in new regions of the sequence space. These results provide guidelines for balancing data cost/quality in predictive strain design.

This presentation will delve into strategies for developing accurate predictive models from limited and yet complex data, the necessary data inputs, and the potential challenges faced during implementation. Based on many industrial use cases attendees will gain insights into how these models can forecast performance, reduce variability, and streamline manufacturing, improving both efficiency and product quality in biologic drug development.

Complex self-driving intelligent experiments for bioprocess development are only possible by integrating all aspects of cell cultivation, analytics and modeling into a comprehensive framework and steered by an effective Workflow Management System. This is realised in the KIWI-biolab and its opportunities for process optimisation and collaboration are demonstrated by a number of developmental projects. The strict implementation of such full automated approaches promotes the application of Findable, Accessible, Interoperable and Reusable (FAIR) principles, allowing researchers to readily share protocols, models, methods and data.

The application of modelling tools in bioprocess development and manufacturing has garnered considerable interest. But what does it really take to develop digital bioprocess twins? This talk dives into key topics such as the business impact of process modelling, experimental design strategies, tailored modelling approaches, accelerated process development, seamless scale-up, and the real-time use of models for monitoring and control. These principles will be demonstrated through several diverse industrial case studies, showcasing the Toolbox capabilities, from accelerated upstream development to gene and cell therapy (G&GT).

While AI's transformative power is well recognized across industries, its potential in pharmaceutical bioprocessing remains underexploited due to limited data. In 2019, Raissi et al. introduced Physics-Informed Neural Networks (PINNs), creating a new paradigm by integrating deep learning with first-principles laws. This method enables the use of AI even with scarce data, presenting a groundbreaking chance to revolutionise biopharmaceutical processes by cutting costs and accelerating the time-to-market for new therapies.

Increasing demand and the approval of biosimilars are forcing biopharmaceutical manufacturers to make their processes more efficient. Perfusion processes play an important role in this so-called process intensification. In this presentation, an overview of possible applications of the perfusion mode in the upstream process of antibody productions will be given and case studies from the cell culture lab of the ZHAW will be presented.

Bioproduction at manufacturing scale can be limited by cellular variation (heterogeneity). Using synthetic biology, it is possible to addict cells to product formation. Such technology efficiently selects for production in the bioreactor, lifting titres and rates >30 % by coupling cell growth to high-level production using essential genes linked to product biosensors. We will present cases and ways of diagnosis in diverse microorganisms, including E. coli, Bacillus, and yeast.

Single-use equipment offers various strategies of power input and gas mass transfer. This variety is often not used as, for a long time, geometrical similarity was one of the most important criteria for applicants. This parameter is, however, not relevant for achieving an optimal cell viability and additionally the maximum sustainability and cost efficiency. This talk aims to present strategies for suitable hybrid bioreactor application under consideration of these parameters.

This research work is focused on intensified processes with high seeding density inoculated from seed bioreactor in fed-batch mode using Chinese Hamster Ovary cells. The impact of the feeding strategy and specific power input (P/V) in the seed bioreactor and on the production step with two different cell lines (CL1 and CL2) producing two different monoclonal antibodies was investigated and the "organized stress" concept is introduced.

With the UKNHS setting ambitious targets to be net zero by 2045, there is an increasing impetus for manufacturers to prioritise sustainability. This presentation describes the challenges to be addressed and the innovations being adopted, including energy efficiency improvements, waste reduction strategies, and resource optimisation. Solutions discussed will provide pathways to greener processes, demonstrating how sustainability and productivity can coexist in the biologics manufacturing landscape, shaping a more responsible future.

The increased complexity of bi and multispecific formats makes these molecules difficult to express compared to standard mAbs. This session explores a holistic approach to overcoming these challenges, featuring techniques such as signal peptide optimisation, vector design, and cell line selection. Attendees will learn how these strategies have successfully increased expression levels and titres of BEAT and TREAT antibodies by up to 10-fold, reaching titres as high as 11 g/L.

Emerging therapeutic modalities present unique challenges in cell engineering and cell line development. I will present innovative strategies to address these complexities, focused on genetic optimisation of expression systems and overcoming hurdles specific to novel biologics. Attendees will gain insights into the advanced techniques designed to improve productivity, stability, and quality when working with cutting-edge modalities in biologic drug development.

Process development focusses on quality-by-design principles and is often focused on CQA to CPP relationships. However, in many bioprocesses, such as bioeconomy or CGT processes, the effect of raw material attributes is the main source for variation. This contribution proposes digital tools to make the process more robust despite raw material variability using PAT, random effect modelling using linear mixed models, and MIMO feedback control tools.