Pregled bibliografske jedinice broj: 645448
Development of gradient retention model in ion chromatography. Part II: Artificial intelligence QSRR approach
Development of gradient retention model in ion chromatography. Part II: Artificial intelligence QSRR approach // 19th International Symposium on Separation Sciences, New Achievement in Chromatography, Book of Abstracts / Ukić, Šime ; Bolanča, Tomislav (ur.).
Zagreb: Hrvatsko društvo kemijskih inženjera i tehnologa (HDKI), 2013. str. 162-162 (poster, međunarodna recenzija, sažetak, ostalo)
CROSBI ID: 645448 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Development of gradient retention model in ion chromatography. Part II: Artificial intelligence QSRR approach
Autori
Vlahović, Ana ; Novak, Mirjana ; Ukić, Šime ; Bolanča, Tomislav
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, ostalo
Izvornik
19th International Symposium on Separation Sciences, New Achievement in Chromatography, Book of Abstracts
/ Ukić, Šime ; Bolanča, Tomislav - Zagreb : Hrvatsko društvo kemijskih inženjera i tehnologa (HDKI), 2013, 162-162
ISBN
978-953-6470-64-8
Skup
19th International Symposium on Separation Sciences, New Achievements in Chromatography
Mjesto i datum
Poreč, Hrvatska, 25.09.2013. - 28.09.2013
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
QSRR; ion chromatography; sugar analysis; retention prediction; articial intelligence
Sažetak
Quantitative Structure-Retention Relationships, QSRR, is a common name for methodology that is predicting chromatographic retention time explicitly on basis of analytes’ molecular- structure. Application of these models can generally short the selection-time for propriate method when dealing with other similar analytes, or can replace the time-consuming “trial and error” approach in method optimization. In this work, artificial intelligence was applied in order to develop good QSRR model. The genetic algorithm was used for selection of the most appropriate molecular descriptors, i.e. descriptors with the highest content of useful information. Artificial neural networks, which are generally known as universal approximators, were taken as QSRR models. The QSRR models were developed for several isocratic elutions, all indicating good prediction ability. The results of QSRR prediction were used for development of isocratic retention model, providing prediction over whole domain of isocratic elutions. In order to enable prediction for gradient elutions, a gradient model based on isocratic data was applied. Although the results indicated slight systematic error, the prediction remained satisfactory good.
Izvorni jezik
Engleski
Znanstvena područja
Kemija, Kemijsko inženjerstvo
POVEZANOST RADA
Projekti:
125-1253092-3004 - Procesi ionske izmjene u sustavu kvalitete industrijskih voda (Bolanča, Tomislav, MZOS ) ( CroRIS)
Ustanove:
Fakultet kemijskog inženjerstva i tehnologije, Zagreb
