Abstract: While we have a strong understanding of the physico-chemical properties of molecules in solution, we cannot readily predict solubility, surface tension, viscosity, phase separation, or related properties for mixtures due to the emergent non-linear interactions between molecular components. In December 2023, the Dutch BigChemistry Consortium was awarded a €97 million grant from the Dutch National Growth fund for research on complex molecular systems, with an emphasis on developing high throughput methods and training AI models to . Our consortium focuses on applications around aqueous formulations used in personal care, food and beverages, and coatings. The long-term goal is to build chemistry-aware models that can predict the physicochemical properties of (for example) emulsions, polymer solutions, or coatings. This presentation will show first prototypes of self-driving modules for high throughput measurements of physical properties of molecular systems, and discuss results on training AI models on experimental data sets.
Bio: Prof. Dr. Wilhelm T. S. Huck received his PhD in 1997 from the University of Twente. After postdoctoral research with George Whitesides at Harvard University, he took up a position in the Department of Chemistry at the University of Cambridge, where he was promoted to Reader (2003) and Full Professor of Macromolecular Chemistry (2007). In 2010 he moved to the Radboud University in Nijmegen, the Netherlands, to take up a position as Professor of Physical Organic Chemistry. His research interests center around understanding life as a set of complex chemical reactions and the application of AI and ML in chemistry. He is Co-PI on a SUMMIT grant ‘Evolving life from non-life’ (EVOLF) and lead PI on a 97M Euro Dutch National Growth Fund initiative on AI and chemistry (BigChemistry). He received the Spinoza Prize (2016), a VICI award (2011) and two ERC Advanced Grants (2010 & 2019). Prof. Huck is a member of the Royal Netherlands Academy of Arts and Sciences. His group uses microfluidics, and, increasingly, AI and robotics, to study chemical reaction networks, to construct minimal synthetic cells, and to develop self-driving modules for formulating functional complex mixtures.
About the AC Seminar Series
The Acceleration Consortium (AC) seminar series explores perspectives on the future of AI for science, presents cutting-edge research findings, enables collaborations, and offers training and upskilling opportunities. Presented both in-person and online, these seminars will host a diverse set of speakers on topics related to accelerated discovery across three tracks:
- AC Distinguished Seminars: Leaders in the autonomous discovery community will share their findings and perspectives that are helping to shape future directions and address key challenges. These will be delivered in a hybrid format at the University of Toronto.
- AC Early Career Seminars: Early career researchers will present results from their latest publications, taking a technical dive into findings, methods, and tools. These will be delivered in a hybrid format at the University of Toronto.
- AC Virtual Training Seminars: Instructors will provide standalone introduction lectures and hands-on tutorials on topics related to self-driving labs with an emphasis on principles, literacy, and skills. These will be delivered virtually.
Do you have a suggestion for a talk? We welcome your ideas for potential speakers from diverse career stages and backgrounds.
