Sharif Digital Repository

In the present work we report a quantitative structure-activity relationship (QSAR) study on S1P1 receptor’s agonists that have therapeutic potential for autoimmune disorders such as Multiple Sclerosis (MS). Such studies play an important role in drug design and lead optimization by developing a mathematical relationship between the chemical structures of compounds and their biological activities.
We used both linear and nonlinear techniques such as MLR and ANN respectively to model these compounds together with techniques such as Stepwise-MLR, GA-MLR and GA-ANN in the variable selection step as it is an important step in every QSAR study. Since topological descriptors are well... 

Metabonomics is a quantitative measurement of time dependent metabolic interactions for living systems in response to the pathological or genetic variations. NMR spectroscopy has emerged as a key tool for understanding metabolic processes in living systems. In this project, the study of metabolomics was performed as classification and regression on samples of parkinson’s disease, multiple sclerosis disease, celiac disease and crohn’s disease. In classification part, various methods were applied using optimal parameters.classification methods in Parkinson’s disease, multiple sclerosis disease, celiac disease and crohn’s disease were RF, CART, PLS-DA, RF and RF respectively. Based on the... 

Today with the development of technology in medical science, there is a need to develop new methods to analyze and process the medical images. Furthermore, increasing use of machines and computers to accomplish prediction goals delineates that these tools had promising results. Because of all the above, this research focuses on processing and analyzing medical images with using data mining tools in order to identify MS and tumor disease which have been ubiquitous in last decades, fast and meticulous. To do so, we introduce a new clustering algorithm based on the modularity measure of graph networks as well as a new machine learning algorithm based on Kalman filter for Tensor-based data....