AI-assisted molecular and reaction design: integrating molecular properties and synthesizability.
Project ID: 2228cd1282 (You will need this ID for your application)
Research Theme: Advanced Materials
UCL Lead department: Chemical Engineering
Lead Supervisor: Lauren Ye Seol Lee
Project Summary:
Can we create a solvent that effectively captures carbon dioxide to combat climate change, or a drug to fight human disease? With growing challenges of our society, designing novel chemical products is of great importance in achieving positive environmental outcomes and technological advances. In this context, computer-aided molecular design (CAMD) has emerged as a powerful tool that can accelerate identification of optimal molecular candidates from a vast chemical space. However, current approaches focus on the candidates’ properties or performance in an isolated campaign and therefore they are limited by bottlenecks in the prediction uncertainty, synthesis of candidates and the pace of validation within the system of interest. Consequently, there is a pressing need for an integrated framework that simultaneously optimises the molecular structures and evaluates synthesizability, to truly catalyse innovation in chemical product design in a closed loop.
This project is devoted to the development of AI-enabled CAMD approaches for pharmaceutical applications that offer an innovative way of identifying high-performing and synthesizable molecules. You will focus on 1) improving molecular property prediction models by developing a scientific machine learning framework that can account for uncertainty in data-poor environments, 2) developing an AI-based reaction prediction models and synthesizability scoring method that is suited to ensuring synthetic accessibility of molecules being designed, and 3) integrating it within the CAMD framework.
The project is primarily supervised by Dr Lauren Lee in collaboration with Dr Federico Galvanin. The successful candidate will be part of the Sargent Centre for Process Systems Engineering at the UCL Chemical Engineering Department.
We are seeking an enthusiastic and self-motivated person who is interested in advancing CAMD technologies. Candidates should hold a minimum 2:1 MEng/MSc, or equivalent degree in Chemical Engineering, Chemistry, or a related field. A solid background in mathematical modelling, optimisation, data science and/or computational chemistry is desirable.