مرجـع دانـش پارس

The goal of the present study is the exploration of data from different families of compounds through the use of a variety of machine learning techniques so that robustQSAR-based models can be developed to further guide in the quest for new potent Hepatitis B virus compounds. In this work quantitative structure-activity relationship (QSAR) study has been done on 6-chloro-4-(2-chlorophenyl)-3-(2-hydroxyethyl) quinolin-2(1H)-one and related compounds as Hepatitis B drugs. Multiple linearregressions (stepwise-MLR) and genetic algorithm(GA),were used to create the nonlinear and linear QSAR models. The root-mean square errors of the training set and the test set for MLR models, were 0.2252, 0.1220 and R=0.5513. The results obtainedfrom this work indicate that MLR models are more effective than other statistical methods and exhibit reasonable prediction capabilities. Also the best descriptors are mor12v , H4e , HATS8m and Pol . Van der Waals volumes, Atomic Electronegativity , Atomic mass and Atomic polarization were important descriptors in this study.

Hepatitis B, quantitative structure-activity relationship, genetic algorithm and Multiple linear regressions