Chris Bryant's PhD Project

Duration of the Project: 1993 - 1996

People

• Doctoral Student: Dr Chris Bryant

• Supervisor: Prof A.E. Adam (University of Salford), formerly a member of the department of computation at the University of Manchester Institute of Science and Technology(UMIST)

• Supervisor: Dr D.R. Taylor, formerly a member of the department of chemistry at the University of Manchester Institute of Science and Technology(UMIST)

• Collaborators: Prof R.C. Rowe (School of Pharmacy, University of Bradford), formerly of Zeneca Pharmaceuticals, UK.

Background

The aim of the project was to investigate the application of artificial intelligence techniques to chromatography, a separation technique used by analytical chemists. Three machine learning systems were applied to data from a database of published enantioseparations by High-Performance Liquid Chromatography (HPLC) performed on commercially available chiral stationary phases (CSPs). The aim was to induce generalisations that recommend particular CSP chiral selectors based on the structural features of an enantiomer pair. Two of the tools, Golem and Progol, were from the field of inductive logic programming. The other, DataMariner, was a commercially available tool which generated essentially propositional rules.

Results

Six publications resulted from this research.

This was the first published work to:-

• take a validated step towards an expert system for enantioseparations by HPLC which uses generalisations that may be interpreted and evaluated by chemical analysts;

• investigate whether data mining tools that employ machine induction can be used to develop the generalisations needed for such a system;

• apply the machine learning system DataMariner to a scientific domain;

• apply inductive logic programming to Analytical Chemistry.

This page is maintained by Chris Bryant.
Last updated on 8 May 2007.