As the life sciences industry moves toward greater flexibility, scalability, and efficiency, the Module Type Package (MTP) standard is emerging as a key enabler of modular automation, Plug & Produce integration, and advanced data orchestration. This presentation will introduce the ISPE MTP Implementation Guide, a resource designed to bridge the gap between standards and real-world application. By showcasing diverse use cases, this guide provides practical insights into how MTP can reduce deployment time, improve interoperability, simplify process change agility, democratize data, and streamline compliance in regulated manufacturing environments.

Analytical and formulation data is foundational to CMC Development. Recording CMC development data in a user-friendly manner and having a standardized way to capture analytical results, register formulations, process parameters, batches, and samples unlocks efficiency gains and ensures data is easily accessible in the future. In this presentation we discuss AbbVie’s CMC data digital journey towards connecting analytical and formulation results to their respective study and sample ID, to empower storytelling visualizations that enable comparison across projects. 

This presentation explores the integration of digital modeling and simulations as a starting point for downstream bioprocessing, focusing on a proof of concept for cation exchange chromatography. This represents a shift toward Quality by Digital Design (QbDD), leading to enhanced process efficiency and increase productivity through computational models and real-time data, demonstrating the future state of our in silico first approach.

Bioprocess Development groups face challenges with complex modalities, faster development cycles, and more experimental data from HT and PAT technologies. Historically, lab experimental data is dispersed in many different instrument software and unstructured files formats requiring substantial manual data-manipulation efforts for experimental insights, decision making, process modeling, and tech transfer. Here, we will share our journey to build and deploy a fit-for-science digital ecosystem within our bioprocess development labs.

Understanding metabolic shifts in CHO cells is critical for enhancing productivity and process control in mAb manufacturing. This presentation introduces a hybrid modeling framework designed to identify the occurrence of metabolic shifts and their associated conditions. Clustering is used to segment concentration and process data into distinct metabolic phases, and phase-specific hybrid models are then trained to learn biological rate terms using a sparse, interpretable approach. The resulting models reveal key variables linked to metabolic transitions and provide a basis for optimizing their timing in future processes.

Digital twin calibration and optimal control in biomanufacturing involve creating and refining virtual models that replicate real-world bioprocesses. Calibration ensures the digital twin accurately reflects experimental data, while optimal control leverages this model to enhance process efficiency, stability, and product quality. This approach enables real-time monitoring, predictive adjustments, and improved decision-making in biomanufacturing.

Digital twins streamline bioprocessing by creating virtual models that simulate monoclonal antibody (mAb) and viral vector production, reducing the need for extensive lab experiments. These models enable real-time optimization, predictive insights, and process control, improving efficiency and scalability. By minimizing experimental effort, digital twins accelerate development timelines and enhance biomanufacturing precision.

Navigating the digital future in bioprocessing involves integrating advanced analytics, automation, and AI to optimize production, enhance quality control, and accelerate decision-making. As digital tools become central to biomanufacturing, companies must adapt by upskilling their workforce and modernizing infrastructure to remain competitive and compliant.

• Cross-Sector Collaboration: Foster partnerships between academia, industry, and government to align skills development with bioprocessing needs.
• Targeted Training Programs: Develop specialized education and upskilling initiatives to equip workers with the latest digital and AI-driven biomanufacturing skills.
• Global Talent Mobility: Streamline policies and initiatives to attract and retain skilled professionals worldwide, ensuring a diverse and adaptable workforce.

Real Time Release of the final product is encouraged by the regulatory bodies and a clear business case. Although this QbD concept is proposed since more than 15 years, there are hardly any solutions in place so far. This contribution shows how end-to-end digital twins can be embedded in real time environment concurrently with the actual batch. Digital Twin predictions can be directly fed into the electronic batch record and the OOS probability is therewith minimized. This solution can also be used to target CPV and continuous optimization.

The development of robust models for process optimization is a critical aspect of enhancing efficiency, reducing costs, and ensuring consistency in manufacturing processes. This presentation will address how Hybrid Model approaches used to extract the missing relationships that cannot be captured by the mechanistic model in downstream and upstream process.

Ever had a great AI/ML solution that was technically feasible but didn’t make it to implementation? You are not alone, let’s talk. We will discuss hurdles that are often overlooked until it is too late, and approaches to overcome them. We will recommend under-valued areas for AI/ML solutions. Brought to you as confessions from someone who has been on the AI/ML development side and on the manufacturing receiving side.

Selecting optimal data-driven modeling methods and integrating batch and time-series data are key challenges in biopharmaceutical manufacturing. Accurate modeling requires capturing both inter-batch variability and intra-batch dynamics. This presentation describes the application of smart process data analytics software and tensorial methods to industrial end-to-end biomanufacturing datasets for monoclonal antibody production, demonstrating how automated DA/ML tool selection and multiway modeling improve predictive accuracy and process understanding.

The biopharmaceutical industry is increasingly turning to data science to optimize manufacturing processes and enhance product quality. This presentation explores two innovative case studies that leverage data science to improve efficiency in biologics manufacturing. The first case study focuses on a cloud-based predictive modeling application designed to enhance the predictability of mammalian cell culture processes by forecasting bioreactor potency from at-line process parameters over a multiple-day horizon. The second case study presents a novel application for assessing the out-of-specification risk associated with drug product potency. The cloud-based statistical software application streamlines the evaluation of alternate potency targets.

While the in vitro reaction for RNA synthesis is traditionally performed in a batch mode, fed-batch in vitro transcription holds promise to more efficiently use expensive catalysts and agents for co-transcriptional capping. We develop and mathematically optimize a mechanistic model for IVT to find feeding policies that maximize RNA production while maintaining substrate ratios essential minimizing formation of uncapped RNA impurities. Experimental validation demonstrates how these model-based strategies can be used to accelerate process development and optimize costly resources.