Naslov
Application of artificial neural networks (ANNs) for development of HPLC gradient separation methods of polyphenolic compounds in medicinal plants

Autori
Belščak-Cvitanović, Ana ; Jurinjak Tušek, Ana ; Valinger, Davor ; Benković, Maja ; Jurina, Tamara ; Komes, Draženka

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 16th Ružička days, "Today science-tomorrow industry" / Jukić, A ; Šubarić, D. - Zagreb : Hrvatsko društvo kemijskih inženjera i tehnologa (HDKI), 2017, 198-208

Skup
16th Ružička days, "Today science-tomorrow industry"

Mjesto i datum
Vukovar, Hrvatska, 21.09.2016. - 23.09.2016

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
artificial neural networks (ANNs) ; HPLC ; medicinal plants ; polyphenols

Sažetak
Extensive research activities have been undertaken recently to systematize the identification, standardization and use of medicinal plants. For that purpose, high performance liquid chromatography (HPLC) methods are imperative for the regular quality control and identification of pharmacologically active compounds. Enormous research efforts have been conducted so far resulting in a vast number of HPLC methods developed for identifying polyphenolic constituents of medicinal plants. In the present study, the approach of using artificial neural networks (ANNs) for prediction of optimal HPLC method for the separation of different groups of polyphenolics was applied. For that purpose, the composition of mobile phase, pH, analysis duration and flow rate as the input parameters were investigated on separation behaviour of gallic, rosmarinic and chlorogenic acids as well as quercetin and rutin as the outputs from five different medicinal plant extracts. The optimal neural network chosen based on the values of the root mean square error (RMSE) and the linear correlation coefficient (R2) was able to accurately predict the experimental responses. The results of the present study confirm the usefulness of ANNs in the development of HPLC gradient separation methods.

Izvorni jezik
Engleski

Znanstvena područja
Biologija, Biotehnologija

POVEZANOST RADA