Application Of QSAR And Molcular Docking Studies In Medicinal Analytical Chemistry

Quantitative Structure-Activity Relationship (QSAR) studies are important research topics in computational chemistry and chemoinformatics. They have been widely used for the prediction of various properties of compounds by the used of different statistical methods and various kinds of molecular descriptors. Now, QSAR method has been introduced to medicinal analytical chemistry. In this dissertation, we mainly discussed hybrid Genetic-based Support Vector Machine, hybrid Genetic-based Artificial Neural Network, and molecular docking-guided active conformation selection were used in a Quantitative Structure-Activity Relationship (QSAR) study.In this dissertation, a brief description of the QSAR and Molecular Docking principle and research status were given in Chapter 1. Much emphasis was put on the realization process of QSAR and Molecular Docking. All kinds of statistical learning methods were used to study the relationship between the structure and the activity for various systems.A QSAR study of the binding modes and binding affinities of the interactions between 30 antibiotic compounds and DNA was performed. A large number of descriptors that encode hydrophobic, topological, geometrical, and electronic properties were calculated to represent the structures of the antibiotic compounds. Aiming at the system with multi-dimension, small samples, we utilized the Genetic Algorithm-Support Vector Machine (GA-SVM) to develop the quantitative structure activity relationship, which can select an optimized feature subset and can optimize SVM parameters simultaneously. Binary QSAR model for predicting binding mode and conventional QSAR models for predicting binding affinity were built based on the GA-SVM approach. The selected descriptors using the GA-SVM represented the overall descriptor space and can account well for the binding nature of the considered data set. The selected descriptors using the GA-SVM method were then used for developing the conventional QSAR models by using the Artificial Neural Network (ANN) approach. A comparison between the conventional QSAR models using the GA-SVM with those using the ANN revealed that the GA-SVM models were much better than the ANN models. The GA-SVM models can be useful for predicting the binding modes and the binding activities of the new antibiotic compounds interactions with DNA.Molecular docking-guided active conformation selection was used in a Quantitative Structure-Activity Relationship (QSAR) study of a series of novel (V600)^EBRAF inhibitors. The developed model can be used for the rational and accurate prediction IC₅₀ values of these inhibitors from their molecular structures. Molecular docking study was carried out to dock the inhibitors into the ATP active site and to obtain the rational active conformations. Based on the conformations generated from molecular docking, satisfactory predictive results were obtained by a genetic algorithm-Artificial Neural Network (GA-ANN) model according to the internal and external validations. The results from this work demonstrate that the molecular docking-guided active conformation selection strategy is rational and useful in the QSAR study of these (V600)^EBRAF inhibitors and for the quantitative prediction of their IC₅₀ values. The results obtained could be helpful to the design of new derivatives with potential activitiesA series of 9-Arylpurines as a novel class of Enterovirus inhibitors was subjected to Quantitative Structure-Activity Relationship (QSAR) analysis. Two chemometrics methods including Genetic Algorithms-Support Vector Machine (GA-SVM) and principal component (PCA) analysis combined with Artificial Neural Network (ANN) were employed to develop the quantitative structure activity relationship. A comparison between the QSAR models using the GA-SVM with those using the PCA-ANN revealed that the GA-SVM models were much better than the ANN models. GA-SVM can select an optimized feature subset and can optimize SVM parameters simultaneously.