M. Mulholland et al., TEACHING A COMPUTER ION CHROMATOGRAPHY FROM A DATABASE OF PUBLISHED METHODS, Journal of chromatography, 739(1-2), 1996, pp. 15-24
Citations number
19
Categorie Soggetti
Chemistry Analytical","Biochemical Research Methods
As ion chromatography (IC) has matured as an analytical technique it h
as become more automated, Most instrument control and data handling is
now handled by computers. However, IC has not seen the abundance of a
utomated method optimisation techniques which are provided to conventi
onal chromatography. To a certain extent this was because IC differed
greatly in the approach required to optimise selectivity and sensitivi
ty. There was quite a diverse range of chemistries (or separation mech
anisms) applicable to IC, such as ion exchange, ion interaction, etc.
This paper describes an effort to fill this gap by developing an exper
t system which can give comprehensive advise on suitable method condit
ions for a variety of IC mechanisms. To build this system we applied a
n approach known as induction by machine learning, which was developed
within the field of artificial intelligence (AI). A database of over
4000 published methods using IC, where the sample information and the
chromatographic conditions were recorded, was used to train an expert
system (ES). Both induction and a neural network model were applied to
this task and an expert system which can advise on the following IC m
ethod conditions: mobile phase, column, pH, mechanism, post-column rea
ctors, suppressor use and gradient applicability, was successfully dev
eloped, This paper presents a summary of the most pertinent conclusion
s from this study. A test set of different methods was extracted from
the database and they were not applied in the training of the expert s
ystem. These were used to test the expert system and different amounts
of information were used as inputs. The resulting outputs of the expe
rt system were evaluated by the expert, who decided whether the method
would work or not and if it was a good method or the ideal method for
the application. Over 85% of methods were found to work and almost 62
% of the methods were considered ideal. These were acceptable results
when one considers the limitations of using a database of published me
thods as a learning set and the time saved by the use of machine learn
ing.