Loading...

QSAR analysis of platelet-derived growth inhibitors using GA-ANN and shuffling crossvalidation

Jalali Heravi, M ; Sharif University of Technology | 2008

590 Viewed
  1. Type of Document: Article
  2. DOI: 10.1002/qsar.200710138
  3. Publisher: 2008
  4. Abstract:
  5. Quantitative Structure - Activity Relationship (QSAR) models for the inhibition action of some 1-phenylbenzimidazoles on platelet-derived growth are constructed using Genetic Algorithm and Artificial Neural Network (GA-ANN) method. The statistical parameters of R2 and root-mean-square error are 0.82 and 0.21, respectively using this method. These parameters show a considerable improvement compared to the stepwise multiple linear regression combined with ANN (stepwise MLR-ANN). Ten-fold shuffling crossvalidations are carried out to select the most important descriptors. Five descriptors of index of Balaban (J), average molecular weight (AMW), 3D-Wiener index (W3D), mean atomic van der Waals volume (Sv), and total charge (Qtotal) appear in most of the models. The results of GA-ANN are superior compared with those of GA-MLR and GA-PLS, which indicate that the inhibition behavior has nonlinear characteristics. The ability of GA-ANN model in predicting inhibition behavior of 1-phenylbenzimidazoles [log(1/IC50)] and its robustness is illustrated by validation techniques of leave-one-out and leave-multiple-out crossvalidations and also by Y-randomization technique. © 2008 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim
  6. Keywords:
  7. Benzimidazole derivative ; Platelet derived growth factor ; Artificial neural network ; Controlled study ; Genetic algorithm ; IC 50 ; Inhibition kinetics ; Intermethod comparison ; Molecular weight ; Multiple linear regression analysis ; Nonlinear system ; Partial least squares regression ; Priority journal ; Quantitative structure activity relation ; Validation process
  8. Source: QSAR and Combinatorial Science ; Volume 27, Issue 6 , 2008 , Pages 750-757 ; 1611020X (ISSN)
  9. URL: https://onlinelibrary.wiley.com/doi/10.1002/qsar.200710138