(322a) Data and Information Management Vision and Strategy Towards Pharma 4.0

Historical perspective of data in pharmaceutical industry has always been the by-product of scientific experiments and business processes required to maintain for regulatory reasons. With the rapid advancements in the field of machine learning (ML) and artificial intelligence (AI), there is a growing view of data as the new oil that could be mined to make quality decisions early and accelerate programs to make life-saving drug reach patients much faster.

To get to ML/AI, we need to build a robust data and information infrastructure which by design allows for these end use cases effortlessly. In this regard, a widely accepted philosophy is FAIRization of data which means data should be Findable, Accessible, Interoperable and Reusable. By making data FAIR, one can pass two litmus tests: a) data can be consumed without the presence of data owner and b) data is machine actionable.

In this talk, we will present vision and strategies that could help in making our laboratory and plant data FAIR and guide efficient process development and robust manufacturing across pipeline projects in pharmaceutical R&D space. We will talk about challenges, pitfalls and learning in this journey. We will also present the case-study of our in-house built platform that makes research data FAIR in the backend while making scientist’s data journey simple in the frontend.

Disclosures: All authors are AbbVie employees and may own AbbVie stock. AbbVie sponsored and funded the study; contributed to the design; participated in the collection, analysis, and interpretation of data, and in writing, reviewing, and approval of the final abstract.