Quantitative Structure-activity Relationships of Imidazole-containing Farnesyltransferase Inhibitors Using Different Chemometric Methods

Abstract

Farnesyltranseferase inhibitors (FTIs) are one of the most promising classes of anticancer agents, but though some compounds in this category are in clinical trials there are no marketed drugs in this class yet. Quantitative structure activity relationship (QSAR) models can be used for predicting the activity of FTI candidates in early stages of drug discovery. In this study 192 imidazole-containing FTIs were obtained from the literature, structures of the molecules were optimized using Hyperchem software, and molecular descriptors were calculated using Dragon software. The most suitable descriptors were selected using genetic algorithms-partial least squares (GA-PLS) and stepwise regression, and indicated that the volume, shape and polarity of the FTIs are important for their activities. 2D-QSAR models were prepared using both linear methods, i.e., multiple linear regression (MLR), and non-linear methods, i.e., artificial neural networks (ANN) and support vector machines (SVM). The proposed QSAR models were validated using internal and external validation methods. The results show that the proposed 2D-QSAR models are valid and that they can be applied to predict the activities of imidazole-containing FTIs. The prediction capability of the 2D-QSAR (linear and non-linear) models is comparable to and somewhat better than that of previous 3D-QSAR models and the non-linear models are more accurate than the linear models.

Image‐Based Analysis to Predict the Activity of Tariquidar Analogs as P‐Glycoprotein Inhibitors: The Importance of External Validation

“…SVM, which have been employed in QSAR studies , is another approach utilized to model the relation between descriptors and activity in this study. SVM constructs a hyperplane in a multidimensional space to map the PCs related to the activity onto a higher dimensional feature space by kernel function .…”

2D-QSAR study of some 2,5-diaminobenzophenone farnesyltransferase inhibitors by different chemometric methods

“…It has been showed that farnesyltranaferase inhibitors (FTIs) can inhibit the growth of Plasmodium falciparum in human red blood cells (Ohkanda et al, 2001[ 25 ]). Therefore, these compounds can be used as antimalarial agents against Plasmodium falciparum (Shayanfar et al, 2013[ 29 ]).…”

“…The drug development contributes to high cost and long time. Quantitative structure-activity relationship (QSAR) approach as a computational methods can be used to predict drug biological activity by finding a correlation between the structures and the activities of drugs, and therefore decreases the cost and time of the drug development (Shayanfar et al, 2013[ 29 ]; Yee and Wei, 2012[ 36 ]). This methods are based on correlation between molecular properties and differences in the features of the molecules (Jain et al, 2012[ 19 ]).…”

“…2D-QSAR models investigate correlation between the activities of active molecules and structures without regarding the three-dimensional conformations of the molecules. However, 3D-QSAR models consider the 3D conformations of the molecules (Shayanfar et al, 2013[ 29 ]).…”

“…Modeling studies were performed for some thiol and non-thiolpeptidomimetic inhibitors using artificial neural networks (ANN) and radial distribution function (RDF) approaches by Gonzalez et al (2006[ 16 ]). Recently Gaurav et al (2011[ 12 ]) and Shayanfar et al (2013[ 29 ]) also studied QSAR of imidazole containing FTIs.…”