Quantitative Structure Activity Relationships Study On Inhibitors Of Human Carbonic Anhydrase

With the development of the computer technology, Quantitative Structure-Activity Relationships (QSAR) as an important method in the computer-aided medicine design was used in much extensive area. The carbonic anhydrase (CA) is rich in the body. The lesions of carbonic anhydrase may cause many diseases, even cancer. The classical CA inhibitors (CAIs) are the sulfonamides. In this thesis, the quantitative structure-activity relationships between the sulfonamides structures and the activities of the inhibitors of human carbonic anhydraseâ…¡,â…¨were studied using the statistical method and machine learning algorithm, and several quantitative modelsfor prediction of the biological activity were established.In the first part of this thesis, a dataset of 125 sulfonamide inhibitors of human carbonic anhydraseâ…¡(hCAâ…¡) was investigated. All the 125 compounds were represented by 12 selected descriptors calculated by the ADRIANA.Code. The dataset was split into two sets of training sets and test sets using random method and Kohonen's self-organizing Neural Network (KohNN) method. Four models were obtained by using Multilinear Regression (MLR) analysis and Support Vector Machine (SVM) Regression methods. For the test sets of four models, the correlation coefficients are above 0.89.In the second part of this thesis, two quantitative models for the prediction of inhibitory activity of the 124 sulfonamide inhibitors of human carbonic anhydraseâ…¨(hCAâ…¨) enzyme were developed. The molecules were represented by 16 selected descriptors calculated by the ADRIANA.Code and MOE. The whole dataset was split into a training set and a test set using a Kohonen's self-organizing map (SOM). Then the inhibitory activity of the compounds was predicted using a multilinear regression (MLR) analysis and a support vector machine (SVM). For the test set, the correlation coefficients of 0.86 using the MLR method and of 0.88 using the SVM method were obtained.In summary, the prediction models of sulfonamide inhibitors of human carbonic anhydrase built in this thesis are helpful for further screening and design new sulfonamide drugs.