مرجـع دانـش پارس

نوع فایل:PDF

تعداد صفحات :7

سال انتشار : 1394

چکیده

The aim of this study was to explore data from different families of compounds through the use of a variety of machine learning techniques. The robust quantitative structure-activity relationship (QSAR)-based models were developed to further guide in the quest for new potent anti-cardiovascular disease compounds. QSAR study was conducted on 1-Phenylsulfinyl-3-(pyridin-3-yl)naphthalen-2-ols and related compounds to determine their efficacy as anti-cardiovascular disease drugs. Multiple linear regressions (stepwise-MLR) and Imperialist Competitive Algorithm (ICA), were used to create nonlinear and linear QSAR models. The root-mean square errors of the training set and test set for ICA models, were 212213, 211122 and R = 21.01. The results obtained from this study indicate that ICA models are more effective than other statistical methods and exhibit reasonable prediction capabilities. Also, the best descriptors were Jhetp, JGI3, G(N..S), RDF260u and R87v+. Radial distribution function, atomic van der Waals volumes, atomic polarizabilities and Balaban-type index are important descriptors in this study.

واژگان کلیدی

Cardiovascular diseases, quantitative structure-activity relationship, Imperialist Competitive Algorithm and Multiple linear regressions.