Miss Kim Hallam
PhD Student

Research area(s)

Research Title: Quantitative Structure-Retention Relationship Models to Predict Gradient High-Performance Liquid Chromatography Retention Time

This research focuses on developing quantitative structure-retention relationship (QSRR) models to predict compound retention in high-performance liquid chromatography (HPLC). Molecular descriptors and machine learning techniques are used to investigate how chemical structure and physicochemical properties influence retention. The research also incorporates experimental parameters to improve model transferability across chromatographic systems. The overall aim is to develop robust predictive models that can support more efficient chromatographic method development and improve understanding of retention behaviour across chemically diverse compounds.

Primary supervisor - Thomas Miller

Secondary supervisor - Leon Barron (Imperial)

Industry supervisor - Azzedine Dabo (GSK)

Research Interests

Analytical chemistry; chemometrics; machine learning; predictive modelling; chemical data science.

Previous research experience includes classification modelling of near-infrared spectra using principal component analysis (PCA), partial least squares (PLS), linear discriminant analysis (LDA), and soft independent modelling of class analogy (SIMCA).