Support vector machine (SVM) classification model based rational design of novel tetronic acid derivatives as potent insecticidal and acaricidal agents

Abstract

A novel support vector machine (SVM) classification model was established for distinguishing potent and weak/inactive insecticides. Classification model-based rational design of novel tetronic acid derivatives was then performed to choose the preferable site of spirotetramat for chemical modification.Afterwards, eleven C5 0 -oxime ether-derived spirotetramat analogues, which are indicated as "potent class", were synthesized and validated by biological assays, revealing that theoretical estimates are significantly consistent with experimental activities of these compounds. To be of interest, the most promising compound 91b exhibited excellent insecticidal and acaricidal activities. Moreover, molecular docking was further implemented to propose the possible interaction mode of acetyl-CoA carboxylase (ACCase) and compounds 91b, 91j, and 91k, providing some important and useful guidelines for further development.Scheme 1 The establishment of SVM classification model and its application in rational design of novel C5 0 -substituted spirotetramat derivatives as potent insecticidal and acaricidal agents. 49196 | RSC Adv., 2015, 5, 49195-49203 This journal is

Coronary artery decision algorithm trained by two-step machine learning algorithm

“…SVM is a widely used classier that uses supervised machine learning methods. 31,32 The purpose of the SVM is to construct an optimal hyperplane that separates the sample into its maximum margins. The SVM handles the classication of nonlinear data by nonlinear mapping the input space to the higher dimensional feature space using the appropriate kernel.…”

Integrating docking scores and key interaction profiles to improve the accuracy of molecular docking: towards novel B-RafV600E inhibitors

“…14 There is now growing interest in applying mathematical methods to improve the accuracy of molecular docking, including multiple linear regression (MLR), partial least squares (PLS) and support vector machines (SVMs). 15 In our previous study, 16 we have demonstrated that these regression methods are indeed feasible to establish a reliable structure-based QSAR model by employing a ligand fit scoring function and the structural characteristics of the compounds. In doing so, we have been able to significantly improve the performance of QSAR analysis.…”

“…In doing so, we have been able to significantly improve the performance of QSAR analysis. 17 As part of our continued interest in rational drug design, 16,[18][19][20][21][22] we herein describe the development and validation of linear as well as non-linear regression-and docking-based models for the computational identification of a series of B-Raf V600E inhibitors. Three regression methods were applied to establish reliable, structure-based QSAR models.…”

Integration of pharmacophore mapping and molecular docking in sequential virtual screening: towards the discovery of novel JAK2 inhibitors

“…Thus, we envisioned that an integration of ligand-based pharmacophore model and structure-based molecular docking can be conducted with respect to JAK2 inhibitors, and the development of JAK2 inhibitors with new scaffolds can be assisted and accelerated by such strategy. In connection with our previous work on computational medicinal chemistry, 17 herein, we reported the establishment of pharmacophore and molecular docking models of structurally diverse JAK2 inhibitors, and further sequential virtual screening on commercial SPECS database. To our delight, multiple-substituted aminothiazole derivative B2 bearing the novel scaffolds, the skeleton of which is remarkably different from the existing JAK2 inhibitors.…”