In the transformative landscape of drug discovery, the integration of Artificial Intelligence (AI) with FAIR (Findable, Accessible, Interoperable, and Reusable) data principles is critical.

It emphasizes the importance of overcoming the limitations of siloed data systems and isolated AI models by adopting knowledge graphs and R&D data ontologies. These tools integrate diverse data types, enabling advanced reasoning and inferential capabilities essential for answering critical questions in drug discovery.

With a case study on creating a knowledge graph for robot scientist, illustrating the need for a fully automated laboratory environment that synergizes high-throughput experimental data with intelligent data processing.

The construction of knowledge graphs, particularly when implemented as ontologies, is highlighted as a dynamic framework for knowledge synthesis and hypothesis generation, paving the way for personalized and autonomous drug discovery. The experience in building this infrastructure underscores the importance of starting with granular, team-specific knowledge graphs to establish a robust foundation for advanced R&D AI capabilities.