NODES 2024 - Ontology-Backed GraphRAG: Injecting Biomedical Logic in LLMs for Drug Discovery

This session will dive into the integration of ontology-backed GraphRAG with LLMs for enhanced drug discovery. The speaker will demonstrate how biomedical and custom ontologies can be leveraged to inject domain-specific logic into language models, improving their performance and precision in complex drug discovery research tasks. You'll learn about the technical challenges of combining graph-based retrieval with LLMs and how ontological constraints can guide more accurate and relevant biological predictions. The session will cover implementation strategies and practical insights into its applications in target identification, drug repurposing, and mechanism-of-action prediction.

Christopher Li, Hamza Farooq



Get certified with GraphAcademy: https://dev.neo4j.com/learngraph
Neo4j AuraDB https://dev.neo4j.com/auradb
Knowledge Graph Builder https://dev.neo4j.com/KGBuilder
Neo4j GenAI https://dev.neo4j.com/graphrag