Day Two

• Applying machine learning to LNP formulation design to systematically identify optimal ionisable lipids, compositions, and formulation technologies beyond traditional empirical screening
• Integrating formulation, microfluidics, and biological readouts into data-driven workflows, enabling faster iteration and more informed decision-making during early LNP development
• Reducing formulation development timelines while improving robustness, outlining how ML-guided approaches can support scalable, adaptable LNP strategies as mRNA modalities diversify

• Identifying the key principles for advancing LNP drug products through clinical phases while maintaining flexibility for evolving modalities and indications
• Evaluating when and why to introduce novel excipients and ionisable lipids into LNP formulations to balance innovation with CMC and regulatory risk
• Managing drug product CMC across development stages to ensure manufacturability, comparability, and clinical progression of LNP-based mRNA therapies
• Aligning formulation strategy, excipient selection, and control approaches to support robust CMC packages without over-engineering early programs

• Examining how LNP internal structure and lipid composition govern stability, biodistribution, and immune interaction, and why these relationships become increasingly critical as payloads extend beyond conventional mRNA
• Adapting LNP architectures to accommodate new and mixed cargoes, including selfamplifying RNA and non-RNA payloads, while preserving functional performance in biologically relevant systems
• Investigating how small formulation choices influence biological behaviour, including immune response and in vivo performance, even when core components remain unchanged

As mRNA programmes scale in complexity and regulatory scrutiny, teams are under pressure to deliver faster and more robust development. While AI and automation are widely discussed, many organisations still struggle to translate these capabilities into practical, connected workflows that materially improve how work gets done across development and CMC.

Led by Pfizer and BioNTech, this workshop will explore how augmented intelligence and automation can be operationalised, enabling more efficient process development, stronger CMC alignment, and improved regulatory readiness. Attendees will gain insight into where AI and automation deliver immediate value, and how digitally enabled workflows can reduce friction while preserving quality and compliance.

Key Questions to be Addressed:

• Where can AI and automation deliver the greatest operational impact across mRNA analytical development, QC, and CMC workflows?
• How can digital intelligence be connected with laboratory systems such as LIMS, sample workflows, and robotics to create more integrated development environments?
• What practical steps can mRNA teams take today to redesign workflows and prepare their organisations for the next generation of mRNA therapies?

BRAND NEW: Build, Train & Test Your Own mRNA AI System

Work through real mRNA development scenarios to design and build your own AI agenda capable of supporting scientific workflows, analysing information, and completing operational tasks.

*Laptops required to participate

• Introducing silicon-stabilised hybrid lipid nanoparticles (sshLNP) as a next-generation RNA delivery platform, combining organic lipid systems with bioabsorbable inorganic silicon to overcome stability and safety limitations of conventional LNPs
• Demonstrating how sshLNP architecture improves RNA stability, transfection efficiency, and tolerability, enabling more reliable delivery across challenging genetic targets and rare disease applications
• Translating delivery innovation into scalable therapeutic development, outlining how integrated bio-analytical capabilities and platform scalability, support rapid progression to clinic