Event description

The goal of this workshop is to share best practices and tools for the FAIRification and the FAIR data management of internal preclinical and clinical datasets in Pharma IT.

The advent of ML / AI for pharma is very promising, however without a basic amount of metadata and smart annotation of existing data assets, the algorithms cannot make much headway.

Several years of IMI knowledge management projects, experiments with data warehouses, data lakes etc. have made it clear that proper semantic annotation of data assets is hard and is resource intensive but a very important hurdle to overcome.

In this workshop, we will evaluate key topics around the Findability, Accessibility and Interoperability of data sets, and discuss the role in this of recent developments such as Bioschemas. We will focus on concrete practical approaches and tools that exist today to bring existing pharma data assets in line with the FAIR Guiding Principles. In the last breakout session, we will flesh out the business case for the proposed FAIR principles project selected at the Boston conference “FAIR principles and metrics tools for life science industry”

DRAFT Agenda

09:00   Welcome / logistics/ purpose (Host: Chris Waller, Vice President and Chief Scientist at EPAM Systems & Pistoia Alliance: Roger Frechette)

09:10  Short talk #1.1: FAIR for Pharma Introduction, Data Catalogues to Knowledge Graphs (Tom Plasterer, US Cross-Science Director, R&D Information, AstraZeneca)

09:25  Short talk #1.2: Pistoia Alliance US breakout summary (TBD)

09:45  Short talk #1.3: FAIR Metrics (Avi Ma’ayan, Professor, Department of Pharmacological Sciences; Director, Mount Sinai Center for Bioinformatics)

10:00¬†¬†Introduction to the ‚ÄúWorld Caf√©‚ÄĚ breakout session methodology (Andreas Matern, Head of APIs and Data Cataloging, Sanofi)

10:15¬† ¬†Breakout #1: (World Caf√© – 1 topic, 4 groups)¬†‚ÄúFAIR Metrics for Pharma‚ÄĒWhat is relevant?‚ÄĚ

11:15  Coffee Break

11:30   Session 2: FAIR Metrics Gap Analysis 

11:30   Short talk #2.1: FAIR, Master Data and Reference Data (TBC РColin Wood, Head of Information Architecture, AstraZeneca)

11:45¬†¬†Breakout #2: (World Caf√© – 4 topics, 4 groups) ‚ÄúFAIR Metrics for Pharma‚ÄĒWhat is missing‚ÄĚ (including¬†Findability,¬†Accessibility, Interoperability and Reusability)

12:45  Lunch

13:30    Session 3: Future state 

13:30   Short talk #3.1: FAIR Ecosystem (TBC РRafael Jimenez Chief Data Architect at ELIXIR)

13:45¬† ¬†Breakout #3: (World Caf√© – 1 topic, 4 groups) ‚ÄúAssessing your current data estate for FAIRness, estimating cost-of-change and return-on-investment‚ÄĚ

What about other data profiling needs? Data Quality? Data Utility (data can be FAIR but not useful)

14:45  Coffee break

15:15  Session 4: Operationalization

15:15¬† ¬†Short talk #4.1: “The challenges & Opportunities of Implementing¬†FAIR in life Science R&D”¬†(Eric Little, Chief Data Officer, Osthus)

15:30  Breakout #4 (World Café Р4 topics, 4 groups) РFAIR project Business Case: Situational Analysis, Cost-benefit analysis, Challenges and Risks, Communications & Sustainability

16:30  Review proposal outline and identify project leads

16:40   What’s next? Brainstorm (workshops, webinars, publications, related topics РAI, etc.)

17:00  Workshop Close & Networking Reception



Signup Here