Developing Quantum and Machine Learning-Enhanced Descriptors for Catalyst Design

This internship focuses on introducing students to computational chemistry by integrating quantum chemistry (QM) and machine learning (ML) to develop molecular descriptors that enhance predictive models for catalyst design. Catalysis is fundamental to modern chemistry, but traditional trial-and-error approaches to catalyst discovery can be slow and inefficient. This project aims to bridge that gap by using computational tools to extract meaningful chemical insights, making catalyst screening more systematic and data-driven. The student will learn to design and apply descriptors that capture key catalytic features such as non-covalent interactions (NCIs), conformational flexibility, and stereoelectronic effects—factors crucial for understanding and predicting enantioselectivity. The project will involve exploring graph-based and 3D molecular models to incorporate key chemical properties like chirality, aromaticity, and geometric arrangements. By streamlining input data for ML models, this work will contribute to reducing reliance on extensive experimental screening, accelerating catalyst discovery in asymmetric organocatalysis. A core objective of the internship is to introduce the student to practical computational chemistry techniques, from molecular data preparation to model interpretation. The student will gain hands-on experience with quantum chemical calculations, data processing, and machine learning applications in chemistry, providing them with valuable interdisciplinary skills. This internship is ideal for students with a chemistry background who are curious about how computational methods can support and enhance experimental chemistry. The skills developed will be broadly applicable, offering insights into modern research approaches in catalysis, materials science, and beyond.

Part of the prestigious Russell Group of universities, The University of Manchester is the largest single-site university in the UK, with the biggest student community.