دراسة العلاقة الكمية بين الفاعلية والصيغة البنائية باستخدام طريقتي (MLR وPC-ANN ) لبعض المركبات التي لها فعالية على بروتين Translocator (TSPO Exploring QSARs of some Translocator protein (TSPO) ligands using MLR and PC-ANN techniques

Date
2016-01-05
Authors
هناء سليم حسين بني عودة
hanaa Saleem Hussein Baniowda
Journal Title
Journal ISSN
Volume Title
Publisher
AL-Quds University
جامعة القدس
Abstract
Quantitative structure-activity relationship study was performed to understand the activity of a set of 136 ligands of Translocator protein (TSPO) compounds. QSAR models were developed using multiple linear regression (MLR) as linear method. While principal component - artificial neural networks (PC-ANN) modeling method was used as nonlinear method. The results obtained offer good regression models having good prediction ability. The MLR resulted with models (12-24) which have coefficient of determination (R 2 ) >0.6, the best model (number 24) resulted with correlation coefficient (R) = 0.909, coefficient of determination (R 2 ) = 0.826, and adjusted coefficient of determination (R 2 adj) = 0.788. Cross Validation leave one out (LOO) and leave many out (LMO) were performed on the resulted MLR models, models 19-24 showed a good predictive power. After that principle component analysis (PCA) performed to divide the data into three data sets, then the ANN performed on the chosen models (19-24) from leave one out (LOO) and leave many out (LMO) validation. ANN resulted models were validated through randomization test, then the conditions proposed by Golbraikh and Tropsha were applied to conclude that the QSAR models has acceptable prediction power or not. However the best ANN model with a good predictivepower was model #24, with R test values 0.832
Description
Keywords
العلوم الصيدلانية, Pharmaceutical Sciences
Citation