QSAR And Its Application In Pesticides

One of the important steps of agricultural production is the control for agricultural pest such as pests, weeds and germs. To develop new pesticides with property of highly active and low toxicity can speed up our agricultural development as well as implement environmental protection and based on the quantitative structure activity relationship model for the development of new pesticides is the best way, on the one hand, it can reduce drug development cycle, on the other hand, can synthetic pesticides with the foresight. In this study, the quantitative structure activity relationship study on fungicidal activity of flavanone derivatives and toxicity of sulfonylure pesticides were conducted in order to guide the synthesis of pesticide.In order to study the relationship between structure and fungicidal activity, in this article, 34 kinds of flavanone derivatives'bactericidal activity was used as an indicator, stoichiometry software PCLIENT were used to obtain initial molecular descriptors for each compound, then, High-dimensional feature selection and worst descriptor elimination multi-round (WDEM) method were successively applied to filter the selected descriptors, and 14 molecular descriptors were retained. Finally, multiple linear regression and support vector regression were used to build the model for all retained descriptors respectively, and analyzed the important influence of each retained descriptor based on the SVR nonlinear explanatory system. The model accuracy is higher based support vector nonlinear regression than multiple linear regression; the importance of 14 retained molecular descriptors is SssO > MATS6e> SeaC2C2aa> EEig04d> EEig03x> C-028> R7v+> L2e> X4A> Mor25m> Glm> Mor17m> BEHvl> RDF045m. The high accuracy nonlinear SVR-QSAR model will plays the important role in conducting fungicides synthesis.For the development of low polluting sulfonylurea pesticides,26 kinds of sulfonylurea pesticides were studied in this paper. Firstly,1773 initial molecular descriptors for each compound were given using stoichiometry software PCLIENT, and 18 kinds of the molecular connective indices were given using software of Dragon. Secondly, high-dimensional feature selection and worst descriptor elimination multi-round (WDEM) method were successively applied to filter these descriptors. Thirdly, the QSAR model was constructed based on support vector regression and selected descriptors. Lastly, the important influences of each selected descriptor were analyzed using the SVR nonlinear explanatory system. Positive correlation between SpDiam_B(m)?3XVC?SpAbs_Dz(m)? SpMAD_AEA(ed)?SpMax_G/D and VR2_G and toxicity of sulfonylurea pesticides can be observed, negative correlation between 2XV?RDCHI?0XV5?XVP?VE2_B(s) and toxicity of sulfonylurea pesticides can be observed, and the relationship between DELS and toxicity of sulfonylurea pesticides is parabola.