This workshop explores the growing role of quantum technologies in the pharmaceutical industry, focusing on real-world applications of quantum computing and sensing in drug discovery and development. Key topics include strategies to address the "harvest now, decrypt later" threat through post-quantum cryptography, the implications of quantum and AI integration for pharma data and intellectual property, and methods to build a quantum-ready workforce within pharmaceutical organizations. Join us to uncover how quantum technologies can revolutionize pharma innovation and reshape the future of healthcare.

The Pistoia Alliance collaborative portfolio is advancing AI-data readiness through its ontology projects, AI, and FAIR initiatives. A key resource in this endeavor is the FAIR Maturity Matrix, a framework designed to help organizations assess and enhance their FAIR capabilities which are instrumental to generate a solid foundation of AI-ready data. The Alliance’s IDMP Ontology enhances the ISO IDMP standard, enabling semantic interoperability. Additionally, the Pharma General Ontology project provides a core framework to enhance interoperability between FAIR data sets across the pharmaceutical industry. The Artificial Intelligence & Machine Learning Community focuses on defining best practices for AI and machine learning in life-sciences research. This includes developing a Best Practices Toolkit for Good Machine Learning Practices and educating members through webinars and conference presentations. By leveraging these resources and initiatives, organizations can systematically evaluate their current data practices, identify areas for improvement, and implement strategies to achieve higher levels of AI data maturity. This progression enhances data quality and accessibility, ensuring that AI applications are built on a robust and reliable data foundation which is a must in a highly regulated environment.

In vivo preclinical animal studies are crucial for discovering new therapeutics. However, their complexity often leads to the creation of multiple localized solutions for data capture, hindering data exchange and reuse. This poses significant challenges for data scientists aiming to gain disease insights and advance discoveries. FISH (FAIR* in vivo data SHaring) platform is a "FAIR by design" system that consolidates previously siloed solutions into a unified platform, providing standardized and context-rich metadata and results for animal studies. Utilizing globally unique persistent resolvable identifiers (GUPRIs), FISH enables seamless data access, identification, and exchange. The platform employs semantic models and standardized terminologies to ensure structured, consistent, and machine-actionable data capture across teams. Each component integrates smoothly with existing registration or Laboratory Information Management Systems (LIMS), ensuring clear ownership, entity validation, and minimizing data duplication. By providing FAIRified data, FISH unlocks the full potential of animal studies, facilitating data reuse and efficient use of ML/AI algorithms or automation of lab workflows. This approach enhances reproducibility of in vivo studies and enables the repurposing of animal data. Ultimately, it increases the probability of successful Entry into Human (EiH) trials and significantly reduces the need for additional animal testing. (FAIR: Findable, Accessible, Interoperable, Reusable)

Preparing data for AI workloads is to put it mildly, awful. Health data poses an even greater difficulty from access to formats to regulatory restrictions. This talk will explore the complexities of data preparation for AI with examples coming from several people surveyed and interviewed. We will discuss a few examples from medical imaging to text, and cover common tools and methods used today in the broader context that could be leveraged by health data science practitioners.

Across the pharma industry, companies sit on massive amounts of data but can't leverage it for meaningful AI application as the data is processed and stored in a historically grown, siloed system landscape. We'll discuss approaches to overcome that systemic challenge through a combination of technology, culture, and mindset.

At AbbVie, the PageRank algorithm has emerged as a powerful method for drawing high-quality associations between genes and diseases. By leveraging our diverse and expertly curated R&D knowledge graph, ARCH, the relatively simple PageRank algorithm provides association rankings that surpass those of other world-class, purpose-built knowledge bases. This talk will focus on the knowledge structure, curation, and our next-generation analytical strategies. Some main points are: The importance of normalized and curated propositional knowledge; Weighting for clinical and novel relevance; The next generation of analytics beyond PageRank.

Building on the foundational concepts introduced in the morning workshop, this advanced workshop explores real-world case studies from industry leaders in hardware innovation, pharma quantum teams, and virtual drug discovery. Attendees will delve deeper into breakthrough applications and learn how to overcome current challenges in adopting quantum technologies. The session concludes with an interactive roundtable discussion on the future roadmap, offering participants an opportunity to collaborate on shaping the next generation of quantum-driven drug development.