Prediction of the Estrogen Receptor Binding Affinity for both hER(alpha) and hER(beta) by QSAR Approaches

• Type: Article in International Scientific Journal
• Date: 2014

Authors

Changliang L Deng (Author) Other; Xuanxuan X Chen (Author) Other; Hongying Y Lu (Author) Other; Xin Yang (Author) Other; Feng Luan (Author) Other; Maria Natalia D S Dias Soeiro Cordeiro (Author) FCUP

Journal

Title: Letters in Drug Design & Discovery

Vol. 11

Pages: 265-278

ISSN: 1570-1808

Publisher: Bentham Science

Indexing

ISI Web of Knowledge - 3 Citations

Scopus - 2 Citations

Scientific classification

FOS: Medical and Health sciences > Basic medicine

Other information

Authenticus ID: P-009-782

DOI: 10.2174/15701808113109990067

Abstract (EN): A QSAR study is reported to predict the binding affinity of a set of 81 modulators for both of human estrogen receptor alpha and beta (ER alpha and ER beta). In this study, the derived QSAR models were built by forward stepwise multilinear regression (MLR) and nonlinear radial basis function neural networks (RBFNN), respectively. The statistical characteristics of the external test set provided by multiple linear model (R-2=0.814, F=61.277, RMS=0.5461 for ER alpha; R-2=0.600, F=21.039, RMS=0.6707 for ER beta) indicated satisfactory stability and predictive ability of the model built. The predictive ability for ER beta of RBFNN model is somewhat superior: R2=0.7691, F=32.012, RMS=0.5764, and the similar result was obtained for ERa of the test set: R2=0.7950, F=54.131 RMS=0.3120. Overall, the appropriate results proved the models to be meaningful and useful to predict and virtual screen of the derivatives with high binding activity.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 14