AC Seminar: Material Discovery in The World Avatar

Register here to attend Markus Kraft 's AC seminar taking place in person at 700 University Avenue in the 10th Floor Seminar Room or online via Zoom.

Abstract: The World Avatar (TWA) is a dynamic digital ecosystem designed to represent complex systems and processes using knowledge graphs and AI, seamlessly integrating data, computational models, and reasoning across multiple domains. Within chemistry and laboratory automation, TWA employs structured semantic representations of chemical knowledge, experimental data, and laboratory protocols. By leveraging detailed ontologies and advanced semantic web technologies, TWA facilitates precise reasoning, interoperability among automated laboratory instruments, computational chemistry simulations, and comprehensive databases. This integration significantly enhances automated decision-making, reproducibility of experiments, and accelerates intelligent discovery workflows.

Reticular chemistry focuses on designing porous crystalline frameworks through the deliberate linking of molecular building blocks, enabling the systematic engineering of materials with precise structures and tailored properties. A particularly compelling class of materials in this field is Metal-Organic Polyhedra (MOPs), which feature discrete, cage-like architectures with finely adjustable porosity, shape, and chemical functionality. Due to their modular synthesis, MOPs are uniquely suited for diverse applications, including gas storage and separation, catalysis, drug delivery, and chemical sensing. Their well-defined structural characteristics provide a powerful platform for investigating structure-property relationships, fostering innovative solutions to significant environmental and industrial challenges.

This seminar will showcase how The World Avatar enables intelligent agents to autonomously navigate chemical space, discovering new MOP structures, evaluating their properties, and proposing viable synthesis pathways for both known and novel architectures. This integration of reticular chemistry and digital innovation exemplifies the potential for transforming materials research through automation, semantic reasoning, and artificial intelligence.

Bio: Professor Kraft FREng researches data-driven modelling, machine learning, and semantic web technologies and has pioneered The World Avatar – an all-encompassing knowledge graph approach to developing a dynamic world model. He co-edited the book "Intelligent Decarbonisation" which comprehensively assesses the current and future impact of digital technologies and artificial intelligence on the decarbonisation of key economic sectors. He is a Fellow of Churchill College and a Professor in the Department of Chemical Engineering and Biotechnology at the University of Cambridge. Until the beginning of 2025 he has been the founding Director of the Cambridge Centre for Advanced Research and Education in Singapore (CARES), the University of Cambridge's first overseas research centre, based at CREATE. In 2025 Prof Kraft is a visiting Professor in the Department of Chemical Engineering at MIT. He is an elected Fellow of the Royal Academy of Engineering.

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.