doi:10.1016/j.bmc.2006.03.019
Copyright © 2006 Elsevier Ltd All rights reserved.
QSAR study of 1,4-dihydropyridine calcium channel antagonists based on gene expression programming
aDepartment of Chemistry, Lanzhou University, 730000 Lanzhou, PR China
bCenter for Disease Control of Gansu Province, 730020 Lanzhou, PR China
cClinical Laboratory, The First Hospital of Lanzhou University, 73000 Lanzhou, PR China
dSchool of Mechanical and Electrical Engineering, JUST, 341000 Ganzhou, PR China
eUniversité Paris 7-Denis Diderot, ITODYS 1, rue Guy de la Brosse, 75005 Paris, France
Received 26 January 2006;
revised 13 March 2006;
accepted 13 March 2006.
Available online 31 March 2006.
References and further reading may be available for this article. To view references and further reading you must
purchase this article.
Abstract
The gene expression programming, a novel machine learning algorithm, is used to develop quantitative model as a potential screening mechanism for a series of 1,4-dihydropyridine calcium channel antagonists for the first time. The heuristic method was used to search the descriptor space and select the descriptors responsible for activity. A nonlinear, six-descriptor model based on gene expression programming with mean-square errors 0.19 was set up with a predicted correlation coefficient (R2) 0.92. This paper provides a new and effective method for drug design and screening.
Graphical abstract
The log (1/IC50) for 45 1,4-dihydropyridines was modeled using the descriptors calculated from the molecular structure along with a quantitative structure–activity relationship (QSAR) technique. The heuristic method (HM) and gene expression programming (GEP) were utilized to construct the linear and nonlinear prediction models, leading to a good prediction.
Keywords: QSAR; Calcium channel antagonists; Gene expression programming
Figure 1. GEP expression tree.
Figure 2. The flowchart of gene expression algorithm.
Figure 3. Plot of predicted log (1/IC50) versus experimental values for the training and testing sets by HM.
Figure 4. Influence of the number of descriptors on the correlation coefficient (R2) and the cross-validation correlation coefficient
of the regression model.
Figure 5. Fitting curve of training set.
Figure 6. Fitting curve of test set.
Table 1.
Experimental and predicted activities (−log (IC50)) of 1,4-dihydropyridine calcium channel antagonists
a Test set.
Table 2.
Correlation matrix of the 6 descriptorsa
a HOMOE, HOMO energy; MIC, Moment of inertia C; XYSR, XY Shadow/XY Rectangle; YZSR, YZ Shadow/YZ Rectangle; MSA, Molecular surface area; THCMD, Tot hybridization component of the molecular dipole.
Table 3.
Result of correlation coefficient (R2) and mean-square errors (S2) with GEP and HM
