Topology indices as predictors of retention behavior of newly synthesized androstane 3-oximes in RP-UHPLC artificial intelligence approach /
The present study describes the application of artificial neural networks (ANNs), as artificial intelligence approach, as a tool in prediction of retention behavior of a series of newly synthesized series of androstane 3-oximes by using several molecular topology descriptors. The retention behavior...
Elmentve itt :
| Szerzők: | |
|---|---|
| Testületi szerző: | |
| Dokumentumtípus: | Könyv része |
| Megjelent: |
University of Szeged
Szeged
2024
|
| Sorozat: | Proceedings of the International Symposium on Analytical and Environmental Problems
30 |
| Kulcsszavak: | Mesterséges intelligencia, Analitikai kémia, Gyógyszerkémia |
| Tárgyszavak: | |
| Online Access: | http://acta.bibl.u-szeged.hu/85748 |
| Tartalmi kivonat: | The present study describes the application of artificial neural networks (ANNs), as artificial intelligence approach, as a tool in prediction of retention behavior of a series of newly synthesized series of androstane 3-oximes by using several molecular topology descriptors. The retention behavior of the studied androstane derivatives was determined by using reversedphase ultra high performance liquid chromatography (RP-UHPLC) with C18 column, as stationary phase, and methanol/water mobile phase. The retention behavior was determined in the form of logarithm of capacity factor (logk). The ANN modeling was performed applying Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm and multi-layer perceptron (MLP) feedforward networks. The obtained model successfully correlates hyper Wiener index (HWI), Szeged index (SZG) and Wiener index (WI) with logk values. The model was validated by internal validation and based on various statistical parameters. The model can be used for the prediction of retention behavior of the compounds structurally similar to those used in the modeling. |
|---|---|
| Terjedelem/Fizikai jellemzők: | 318-322 |
| ISBN: | 978-963-688-009-5 |