Conference: Artificial Intelligence in Laboratories
25/26 November 2025
Background & Objectives
This conference aims to address the impact of Artificial Intelligence (AI) on pharmaceutical laboratories and explore AI applications in analytical processes, regulatory compliance, and quality control.
Artificial Intelligence is transforming pharmaceutical laboratories by enhancing automation, data interpretation, and compliance monitoring. With the rise of machine learning, deep learning, and big data analytics, AI enables predictive analytics, anomaly detection, and process optimization, reducing human error and increasing efficiency. Regulatory authorities are increasingly focusing on these innovations to ensure AI implementation aligns with Good Laboratory Practice (GLP) and Good Manufacturing Practice (GMP) guidelines. This track will present case studies and discuss current trends, challenges, and opportunities for AI-driven laboratory operations.
This conference therefore deals with the following topics:
- AI and GxPs
- Case Studies
Target Audience
This conference will be of significant value to Laboratory managers, supervisors and analysts, Quality control managers, Heads of quality control, Qualified Persons (QPs), Analytical scientists, Senior laboratory staff and responsible authorities
This conference is also intended for employees in Quality Assurance and from contract laboratories. Furthermore, it is useful for service providers, such as contract research organisations and contract manufacturers.
Moderation
Dr Karl-Heinz Bauer (Day 1)
Isabella Küfner (Day 2)
Programme
Tuesday, 25 November 2025
KEYNOTE on 25 November 2025: Artificial
Intelligence in Pharmaceutical Industries
Dr Marcel Franke, Senior Scientist Predictive Formulation,
Process Solutions/Upstream & Process Materials R&D
Merck Life Science
- Milestones & History AI
- Terms, Definition & Abbreviations
- Commonly used AI-Tools & Plugins
- AI-Hitlist and Press Review (2020–2025)
- Opportunities and limitations of AI
- Summary & Conclusion
- Data Management / Data Science as foundation for a successful AI implementation
- The sad reality of Data within the lab: paper, proprietary data format, lack of system integration
- How can digital system like LIMS/LES and standards in the lab (SiLA, AniML, Allotrope) set the right foundation for FAIR Data?
- First use cases for AI within the Lab
- Accelerating data analysis
- Predictive modeling
- Automation of routine tasks
- Enhancing method development
- Accelerated drug discovery
- Critical data for investigation and root cause analysis using AI
- How AI can be used for Investigation and Root Cause analysis
- Insight into the level of validation required for use of AI technology
- AI interaction with contamination control data
- How AI is changing the way we interact with our data
- AI governance model for the APAS Independence and the path to demonstrating robust performance
- The ISPE AI Maturity model
- How automated systems should be considered in terms of risk
- Testing and regulatory considerations and methodology
- What performance metrics would be considered important for validation
- Regulations for AI developers (The EU AI-Act)
- Regulations for the AI-Users (e.g. GAMP 5, 21 CFR Part 11, EU GMP Annex 11)
- Use Cases or QC & QA in Pharmaceutical Industry
- (I) Annual Compilation of PQRs
- (II) Handling of customer complaints regarding packaging materials
- Live-Demo: Using AI-Power Prompts
Wednesday, 26 November 2025
KEYNOTE on 26 November 2025: From Bog to
Bedside: Lessons from the First Dedicated Phage
Therapy Center in North America
Prof Dr Steffanie Strathdee, University of California San
Diego School of Medicine/Co-Director at the Center for
Innovative Phage Applications and Therapeutics
>> Find out more
- How trained AI model can recognize microbial type (training on labeled datasets of bacterial and mold images, learning patterns, adapt algorithm to adjust to image variability, materials and methods, results)
- Examples on 3P®STATION
- Findings from a two-phase suitability assessment of an automated system that combines incubation, continuous plate reading, and AI-powered colony counting
- Applications in environmental monitoring (EM) and Bioburden testing
- Key performance indicators to benchmark the AI system’s results against those obtained from traditional methods
- Cross-functional collaboration (QC, QIT, QEx) to develop and refine use case-specific prompts
- Embraced the principle “standardize before you digitize” by leveraging chatGPT to streamline and simplify validation lifecycle deliverables
- Integrated ChatGPT into a structured and iterative standardization framework
- Consolidated validation requirements and test cases from over 10 sites across 7 languages
- Connecting a large language model to quality management system data
- Quantitative evaluation of chat functionality
- Utilizing the setup to determine the documentation quality for laboratory-specific events
- Real-world use cases and reference projects from SIEMENS
- Understand how AI accelerates drug development, from discovery to operations, by enhancing decision-making, speeding up processes, and improving data accuracy
- Siemens’ AI-powered tools, including FAIR data frameworks, digital twins, and generative AI copilots