QSRR/QSAR Studies Based On Heuristic Method And Radial Basis Function Neural Networks

Quantitative structure-activity/property Relationship (QSAR/QSPR) methods are the most promising and successful tools to provide rapid and useful meaning for predicting the biological activity or toxicity of organic compounds by using of different statistical methods and various kinds of molecular descriptors. The aim of QSAR is to develop models on a training set of compounds, these models will then allow for the prediction of the biological activity of related chemicals. This kind of study can not only develop a method for the prediction of the property of compounds that have not been synthesized, but also can identify and describe important structural features of molecules that are relevant to variations in molecular properties, thus gain some insight into structural factors affecting molecular properties. Now, QSAR method has been introduced to environment chemistry and medical chemistry. In this dissertation, we mainly discussed radial basis function neural networks (RBFNN) to construct QSAR model.Chapter 1 of the dissertation included a brief description of the history, principle, realization process and research status of QSAR/QSPR. In this section, we also introduced the method RBFNN and a review of the application of RBFNN in medical and environment chemistry area.Chapter 2 of this dissertation described Quantitative Structure-Retention Relationships for Mycotoxins and Fungal Metabolites in LC-MS/MS. Quantitative structure-retention relationship (QSRR) models have been successfully developed for the prediction of the retention time of Mycotoxins and Fungal Metabolites in LC-MS /MS. Heuristic method (HM) and RBFNN were utilized to construct the linear and non-linear QSRR models, respectively. The RBFNN model gave a correlation coefficient (R2) of 0.8709 and root-mean-square error (RMSE) of 1.2892 for the test set. This work provided a useful model for the predicting tR of other mycotoxins when experiment data are unknown.Chapter 3 of dissertation described the prediction of the retention factor (log k) in the biopartitioning micellar chromatography (BMC) of 65 organic pollutants by HM and RBFNN. Heuristic method (HM) and RBFNN were utilized to construct the linear and non-linear QSRR models, respectively. The correlation coefficients (R2) of the nonlinear RBFNN model were 0.9301 and 0.9046 for the training and testing sets, respectively. This work provided a useful model for the predicting the log k of other organic compounds when experiment data are unknown. Compared with the results of HM, the RBFNN obtained more accurate prediction.Chapter 4 of dissertation described QSAR about multidrug resistance modulators. HM and RBFNN methods were proposed to generate QSAR models for a set of tetrahydroisoquinoline-ethyl-phenylamine substructure to predict their biological activity in the calcein AM assay. Descriptors calculated from the molecular structures alone were used to represent the characteristics of the compounds. Compared with the results of HM, the RBFNN obtained more accurate prediction. The correlation coefficients (R2) of the nonlinear RBFNN model were 0.9101 and 0.9276 for the training and testing sets, respectively. This paper proposed an effective method to design new MDR modulators based on QSAR.