Researchers will gain an integrated synthetic data foundation and an advanced custom search platform to support reaction data discovery and analysis 

CAS, a division of the American Chemical Society, announced a collaboration with Novartis Biomedical Research focused on enhancing reaction data accessibility and supporting AI-enabled research. The initiative will leverage CAS unique scientific data curation expertise and science-smart technology to give Novartis researchers integrated, searchable access to proprietary experimental reaction data alongside more than 160 million+ scientist-curated reactions from the authoritative CAS Content Collection™. 

Scientific research generates valuable reaction data stored across a variety of research systems and repositories, including electronic lab notebooks, reports, shared drives, and partner platforms. Bringing information from these sources together can help researchers more efficiently discover, access, and analyze reaction data across the research enterprise. Foundational to this collaboration is the application of CAS data transformation services, via CAS Intelligence Hub^SM, to organize and standardize Novartis' extensive collection of experimental reaction data, helping make these valuable research data assets more readily accessible for computational research, machine learning, and AI applications.

"This exciting collaboration reflects the critical importance of a strong scientific data infrastructure, alongside domain-specific technology and expertise, to enable today's rapidly evolving drug discovery workflows," said Tim Wahlberg, Interim President, CAS. "We are pleased to extend our long-standing relationship with Novartis to help make this data a more accessible and valuable AI-ready resource." 

As part of this project, CAS will also collaborate with Novartis to develop a customized discovery platform built on the CAS SciFinder® architecture. This platform is designed to enable Novartis researchers to search, analyze, and cross-reference their enriched internal reaction data and CAS data simultaneously. By addressing a long-standing challenge of efficiently and comprehensively searching internal and external data together, this effort also lays the foundation for future CAS platform capabilities, including large language models and agentic AI.