We encourage you to join us early to collect your name badge, and network over a light lunch. The program starts at 12:00 pm.

Dr. Jim Webber, Chief Scientist, Neo4j

AI agents in life sciences start every session from scratch, missing the "tribal knowledge" that tells researchers not just what worked, but why other approaches didn't. Neo4j Chief Scientist Dr. Jim Webber introduces the Context Graph: a memory architecture that combines an Enterprise Knowledge Graph, a Conversational Graph, and a Decision Graph so agents can reason about both success and failure. See how Merck uses this approach to power autonomous agents that collaborate on drug discovery, with every decision transparent, traceable, and grounded in clinical evidence.

Dr. Alexander Jarasch, Head of Pharmaceutical, Healthcare & Life Sciences, Neo4j

Sergiusz Wesolowski, Lead Data Scientist, EMD Serono / Ardigen

Knowledge graphs connect biomedical evidence across diseases, targets, drugs, pathways and mechanisms, but having a graph does not automatically make that knowledge useful to scientists. This talk shares lessons from operationalizing knowledge graphs for drug discovery at EMD Serono, covering use cases in graph exploration, interpretable prioritization, biological context analysis and GraphML workflows. We focus on a practical question: how do we turn access to a knowledge graph into scientific workflows researchers can actually use?

Jonathan W. Lowe, Founder, Amalgo LLC

Sook Hopkins, Principal Data Scientist, Nestle

As organizations advance their digital transformation journeys, connecting fragmented data is essential to creating a more complete understanding of stakeholder experiences. This session explores how data, AI, and knowledge graph technologies can help create a more connected view of patient and healthcare professional journeys, generating actionable insights that improve decision-making and deliver measurable business value. Drawing from real-world applications, the discussion will focus on how connecting data across the value chain can uncover meaningful opportunities and translate digital innovation into actionable impact.

Hamza Farooq, CTO, BioBox Analytics

Most teams have plenty of data. But when it lives in disconnected systems, decisions end up made from flattened summaries and spreadsheets. The evidence is out of reach, and the reasoning is lost the moment the meeting ends. This talk shows what becomes possible when that changes. BioBox is a decision layer that encodes scientific frameworks and institutional knowledge directly against a team's own data, making every prioritization transparent, repeatable, and explainable. Making this work requires data that is truly connected, which is why it runs on a Neo4J knowledge graph of entities, evidence, and provenance. We'll walk through how it's modelled, how it's queried, and how to track the way decisions evolve as new evidence arrives. The goal of: "What should we do next, and why has that changed?" becomes a question you can actually answer.