Building Better AI for Chemistry
Building Better AI for Chemistry
IPST Professor Pratyush Tiwary organized a National Science Foundation-funded workshop at the University of Maryland that brought together more than 50 experts to develop a roadmap for chemistry-specific artificial intelligence tools, data infrastructure and standards.
The University of Maryland recently hosted a U.S. National Science Foundation-funded workshop focused on building artificial intelligence tools specifically designed for chemistry.
Organized by Pratyush Tiwary, professor in the Department of Chemistry and Biochemistry and the Institute for Physical Science and Technology, the two-day workshop brought together more than 50 experts from academia, government and industry. Participants explored ways to make chemical data, models and research tools more accessible, reliable, interoperable and reusable across the scientific community.
The discussion addressed practical challenges in chemistry-focused AI, including organizing data from experiments, simulations, publications and repositories; evaluating the trustworthiness of AI systems; and balancing open-science goals with the value of data, models and workflows.
“Building AI specifically for chemistry takes a shared vision across a range of stakeholders,” Tiwary said. “Together, our long-term objective is to make experimental and computational chemical data, models and tools more accessible, searchable, interoperable and shareable.”
The workshop was supported by the National Science Foundation, the Department of Chemistry and Biochemistry, IPST and the University of Maryland Institute for Health Computing. Participants are now preparing a community-facing report that will outline priorities and potential pilot projects for the field.
Read the full CMNS story: Building Better AI for Chemistry
