Development of Linear, Ensemble, and Nonlinear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors
- 14 September 2004
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Computer Sciences
- Vol. 44 (6) , 2179-2189
- https://doi.org/10.1021/ci049849f
Abstract
A QSAR modeling study has been done with a set of 79 piperazyinylquinazoline analogues which exhibit PDGFR inhibition. Linear regression and nonlinear computational neural network models were developed. The regression model was developed with a focus on interpretative ability using a PLS technique. However, it also exhibits a good predictive ability after outlier removal. The nonlinear CNN model had superior predictive ability compared to the linear model with a training set error of 0.22 log(IC50) units (R2 = 0.93) and a prediction set error of 0.32 log(IC50) units (R2 = 0.61). A random forest model was also developed to provide an alternate measure of descriptor importance. This approach ranks descriptors, and its results confirm the importance of specific descriptors as characterized by the PLS technique. In addition the neural network model contains the two most important descriptors indicated by the random forest model.Keywords
This publication has 24 references indexed in Scilit:
- On the Physical Interpretation of QSAR ModelsJournal of Chemical Information and Computer Sciences, 2003
- Prediction of Physicochemical Parameters by Atomic ContributionsJournal of Chemical Information and Computer Sciences, 1999
- Structure−Activity Relationships for 5-Substituted 1-Phenylbenzimidazoles as Selective Inhibitors of the Platelet-Derived Growth Factor ReceptorJournal of Medicinal Chemistry, 1999
- Synthesis and Tyrosine Kinase Inhibitory Activity of a Series of 2-Amino-8H-pyrido[2,3-d]pyrimidines: Identification of Potent, Selective Platelet-Derived Growth Factor Receptor Tyrosine Kinase InhibitorsJournal of Medicinal Chemistry, 1998
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Automated Descriptor Selection for Quantitative Structure-Activity Relationships Using Generalized Simulated AnnealingJournal of Chemical Information and Computer Sciences, 1995
- Prediction of Reduced Ion Mobility Constants from Structural Information Using Multiple Linear Regression Analysis and Computational Neural NetworksAnalytical Chemistry, 1994
- Growth factor signaling by receptor tyrosine kinasesNeuron, 1992
- Atom pairs as molecular features in structure-activity studies: definition and applicationsJournal of Chemical Information and Computer Sciences, 1985
- On molecular identification numbersJournal of Chemical Information and Computer Sciences, 1984