Naslov
Quantitative Structure Retention Relationship in Ion Chromatography

Autori
Bolanča, Tomislav ; Ukić, Šime ; Novak Stankov, Mirjana ; Rogošić, Marko

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
21st International Symposium on Separation Sciences, Book of Abstracts / Vovk, Irena ; Glavnik, Vesna ; Albreht, Alen - Ljubljana : National Institute of Chemistry Ljubljana, 2015, 50-50

ISBN
978-961-6104-28-9

Skup
21st International Symposium on Separation Sciences

Mjesto i datum
Ljubljana, Slovenija, 30.06.2015. - 03.07.2015

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Nije recenziran

Ključne riječi
Quantitative Structure Retention Relationship; Ion Chromatography

Sažetak
A priori knowledge of the retention time of a given analyte simplifies the determination of separation conditions therefore quantitative structure retention relationship (QSRR) modelling might be considered a reasonable selection. The first problem in QSRR modelling is to select the most informative descriptors from among a large number of mutually correlated descriptors, while the second one is to build the core model of isocratic and/or gradient elution retention. A lot of conventional methods have been elaborated that are mainly based on different types of regression and simple variable selection methodology (i.e. principal component analysis), showing rather questionable prediction ability. This work reveals recent results on development of artificial intelligence (AI) hybrid methodology implementing all three AI paradigms: artificial neural networks, genetic algorithms and fuzzy logic. The developed models were fully optimized and validated with external set of compounds showing significant improvement of generalization ability. Furthermore, recent demands for increasing the productivity using the gradients, in combination with ever growing complexity of analyzed samples, are introducing an additional request on the analytical system – beside being fairly separated, the peaks are required be as “smoothly” shaped as possible to ensure their precise quantification. In other words, the analysts are becoming interested in peak shapes and peak shape modelling as well. This work also discusses recent developments is peak shape modelling based on QSRR modelling. The developed models are based on generalized logistic distribution and hybrid AI systems. The external validation results show promising predictive ability, but still indicate that there is much to be done before QSRR based optimization strategy could be efficiently built into a useful commercial software.

Izvorni jezik
Engleski

Znanstvena područja
Kemija, Kemijsko inženjerstvo

POVEZANOST RADA