Non-linear assessment of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives--chemometric guidelines for further syntheses

Strahinja Z Kovačević; Sanja O Podunavac-Kuzmanović; Lidija R Jevrić; Evgenija A Djurendić; Jovana J Ajduković

doi:10.1016/j.ejps.2014.05.031

Non-linear assessment of anticancer activity of 17-picolyl and 17-picolinylidene androstane derivatives--chemometric guidelines for further syntheses

Eur J Pharm Sci. 2014 Oct 1:62:258-66. doi: 10.1016/j.ejps.2014.05.031. Epub 2014 Jun 11.

Authors

Strahinja Z Kovačević¹, Sanja O Podunavac-Kuzmanović², Lidija R Jevrić², Evgenija A Djurendić³, Jovana J Ajduković³

Affiliations

¹ University of Novi Sad, Faculty of Technology, Department of Applied and Engineering Chemistry, Bulevar cara Lazara 1, 21000 Novi Sad, Serbia. Electronic address: strahko@uns.ac.rs.
² University of Novi Sad, Faculty of Technology, Department of Applied and Engineering Chemistry, Bulevar cara Lazara 1, 21000 Novi Sad, Serbia.
³ University of Novi Sad, Faculty of Sciences, Department of Chemistry, Biochemistry and Environmental Protection, Trg Dositeja Obradovića 3, 21000 Novi Sad, Serbia.

PMID: 24929053
DOI: 10.1016/j.ejps.2014.05.031

Abstract

The present paper deals with prediction of cytotoxic activity of 17-picolyl and 17-picolinylidene androstane derivatives toward androgen receptor negative prostate cancer cell line (PC-3). The prediction was achieved applying artificial neural networks (ANNs) method on the basis of molecular descriptors. The most important descriptors (skin permeability (SP), Madin-Darby canine kidney cell permeability (MDCK) and universal salt solubility factor (S+SF)) were selected by using stepwise selection coupled with partial least squares method. The ANN modelling was carried out in order to obtain reliable models which can facilitate further synthesis of androstane derivatives with high antiproliferative activity toward PC-3 cell line. The modelling procedure resulted in three ANN models with the best statistical performance. The obtained results show that the established ANN models can be applied for required purpose.

Keywords: Androstane derivatives; Artificial neural networks; Chemometrics; Molecular modelling; Prostate cancer.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Androstanes / pharmacology*
Animals
Antineoplastic Agents / pharmacology*
Cell Line, Tumor
Cell Survival / drug effects
Dogs
Humans
Madin Darby Canine Kidney Cells
Models, Biological*
Models, Molecular
Neural Networks, Computer*
Reproducibility of Results

Substances

Androstanes
Antineoplastic Agents