Computational and machine learning tools that accelerate the design of safer, high-performing chemistries by predicting toxicity, guiding safer substitutions, and screening for targeted molecular functionality.
This offering combines advanced machine learning with computational chemistry to enable benign-by-design molecular discovery. The platform helps researchers and industry partners identify new chemistries that deliver targeted functionality while minimizing hazardous impacts, addressing the growing regulatory and market demand for safer alternatives to compounds such as PFAS and other persistent organic chemicals.
Core capabilities:
The platform has been validated through published case studies, including machine learning models that align experimental and theoretical findings on PFAS toxicity. Current work extends these methods to photocatalytic performance prediction and broader molecular functionality screening, positioning the tools for collaborative refinement and application with industrial and academic partners.
University at Buffalo is a comprehensive public research university and a leading campus in the State University of New York system. Industry engagement is anchored by co-located labs on a downtown medical campus, a research and technology park with incubators, shared core facilities, and co-op talent pipelines. Partnerships with regional hospitals enable clinical studies and translation, while proximity to the U.S.–Canada border and the binational Great Lakes corridor facilitates cross‑border collaboration. Research is supported by competitive federal funding from NIH, NSF, DOE, and DoD, alongside New York State innovation programs. A dedicated technology transfer office provides IP management, licensing, and startup support.