The AI in Drug Discovery Xchange – San Francisco brings together senior-level scientists and executives from the pharmaceutical and biotech sectors to tackle key challenges in Data Quality, Target Identification, Lead Generation & Optimization, Drug Response Prediction and Drug Design & Modeling. Digital Science are looking forward to joining the event once again in 2026, with Robert McGrath, Chief AI Officer at Digital Science, presenting the opening keynote and a roundtable session.
Keynote
The Data Behind the Agent: Why AI Workflows Fail Without the Right Foundation
Wednesday 9 September, 08:30 – 09:00
As pharmaceutical R&D embraces multi-agent AI systems, the bottleneck is shifting. The challenge is no longer whether AI can reason over scientific literature — it’s whether the data feeding these systems is fit for purpose. Agentic workflows that span internal datasets, external knowledge bases, and third-party sources introduce compounding risks: lost provenance, conflicting ontologies, and results that can’t be reproduced. As these systems grow in complexity and tool access, their performance becomes harder to predict and harder to trust. This talk will explore what a reliable data foundation for agentic research workflows looks like, and how the relationship between data infrastructure and AI capability is evolving.
Roundtable
Assembling the Data Stack: What Pharma Needs from External Knowledge in the Age of AI Agents
Wednesday 9 September, time TBC
- How are research teams combining internal R&D data with external knowledge bases, and where does it break down?
- What are organizations looking for from external data providers — and what’s on the horizon?
- How do you manage and harmonize data across multiple external providers with different formats, standards, and levels of enrichment?
- What role do ontologies, knowledge graphs, data lakes, and modern retrieval techniques play in making data AI-ready?
- As AI workflows become more autonomous, how do organizations maintain provenance and traceability back to source data?
