UNIVERSITÉ DE MONTRÉAL

Published purpose

Designing molecules with desired properties in drug, vaccine, and materials discovery is a challenge. Accurately identifying lead candidate molecules early on can significantly reduce the time and cost involved. Artificial Intelligence (AI) has the potential to revolutionize drug and material discovery by analyzing evidence from a large amount of previously accumulated data, thereby significantly accelerating the process. This Project will examine searching for molecules with optimized properties in the presence of different types of oracles, corresponding to estimators of the desired properties at varying degrees of computational cost and fidelity. The Project aims to build an efficient and effective machine learning framework for searching molecules with designed properties, and showcase its applications on antibiotic and materials discovery, thereby enabling AIempowered candidate discovery. This presents a solution for reducing a resource intensive and time consuming design bottleneck, which is a core design challenge across many industrial domains.