Application of artificial neural networks for the prediction of antitumor activity of a series of acridinone derivatives

• Published in: Medicinal chemistry (Shp-sariqah, United Arab Emirates) Vol. 8; no. 3; p. 309
• Main Author: Koba, Marcin
• Format: Journal Article
• Language: English
• Published: Netherlands 01-05-2012
• Subjects: Acridones - chemistry; Acridones - pharmacology; Animals; Antineoplastic Agents - chemistry; Antineoplastic Agents - pharmacology; Cell Proliferation - drug effects; Leukemia P388 - drug therapy; Leukemia P388 - pathology; Mice; Models, Molecular; Molecular Structure; Neural Networks (Computer); Quantitative Structure-Activity Relationship; Xenograft Model Antitumor Assays
• ISSN: 1875-6638
• DOI: 10.2174/157340612800786651

Artificial neural networks (ANNs) have been applied for the quantitative structure-activity relationships (QSAR) studies of antitumor activity of acridinone derivatives. Molecular modeling studies were performed with the use of HyperChem and Dragon computer programs and molecular geometry optimization using MM+ molecular mechanics and semi-empirical AM1 method, and several molecular descriptors of agents were obtained. A high correlation resulted between the ANN predicted antitumor activity and that one from biological experiments for the data used in the testing set of acridinones was obtained with correlation coefficient on the level of 0.9484. Moreover, the sensitivity analysis indicated that molecular parameters describing geometrical properties as well as lipophilicity of acridinone derivative molecule are important for acridinones antitumor activity.