Support Vector Machine‐Based Quantitative Structure–Activity Relationship Study of Cholesteryl Ester Transfer Protein Inhibitors

Abstract

To explore inhibition of cholesteryl ester transfer protein, a support vector machine in quantitative structure-activity relationship was developed for modeling cytotoxicity data for a series of cholesteryl ester transfer protein inhibitors. A large number of descriptors were calculated and genetic algorithm was used to select variables that resulted in the best-fitted models. The data set was randomly divided into 68 molecules of training and 17 molecules of test set. The selected molecular descriptors were used as inputs for support vector machine. The obtained results using support vector machine were compared with those of multiple linear regression which revealed superiority of the support vector machine model over the multiple linear regression. The root mean square errors of the training set and the test set for support vector machine model were calculated to be 3.707, 5.273 and the correlation coefficients (r(2)) were obtained to be 0.947, 0.899, respectively. The obtained statistical parameter of leave-one-out cross-validation test correlation coefficients (q(2)) on support vector machine model was 0.852, which indicates the reliability of the proposed model.

Simultaneously Optimized Support Vector Regression Combined With Genetic Algorithm for QSAR Analysis of KDR/VEGFR‐2 Inhibitors

“…Generally, GA‐SVR is not computationally more expensive in searching the best combination of descriptors using GA, except that the algorithm of SVR is much more sophisticated and more time may be needed. However, it is very sorry to point out that although SVM has been successfully introduced into many research fields including QSAR (23–25), a few of the researches were devoted to the simultaneous optimization of the parameters of kernel function and cost (C) involved in the established model, cutting down the probability of achieving the global optimum.…”

“…Because of its remarkable generalization performance, SVM has attracted deep attention and gained extensive applications in a large number of researches, such as pattern recognition problems, drug design and also QSAR analysis (22). However, it is very sorry to point out that parameters of SVR have not been properly optimized in the foregoing QSAR studies (23–25), where C, γ and ε were optimized step by step rather than simultaneously, which may significantly cut down the probability of achieving the global optimum. Theoretically, parameters of C, γ and ε are interactive and should be optimized as a whole, which ensures that any point in the combinatorial parametric space of C, γ and ε would be included and evaluated.…”

Quantitative structure–activity relationship (QSAR) study of interleukin-1 receptor associated kinase 4 (IRAK-4) inhibitor activity by the genetic algorithm and multiple linear regression (GA-MLR) method

“…QSAR studies can express the biological activities of compounds as a function of their various structural parameters and also describes how the variation in biological activity depends on changes in the chemical structure [9]. Recently, a QSAR study of biological activity has been published by our group [10][11][12]. If such a relationship can be derived from the structure-activity data, the model equation allows medicinal chemists to say with some confidence which properties are important in the mechanism of drug action.…”

Development of a New Combined Chemometrics Method, Applied in the Simultaneous Voltammetric Determination of Cinnamic Acid and 3, 4-Dihydroxy Benzoic Acid

“…Chemometrics is applied in different branches of chemistry in the recent years [1][2][3][4][5][6][7]. Calibration is nowadays one of the most important fields of chemometrics.…”