APPLICATION OF MULTIVARIATE IMAGE ANALYSIS IN QSPR STUDY OF pKa OF VARIOUS ACIDS BY PRINCIPAL COMPONENTS-LEAST SQUARES SUPPORT VECTOR MACHINE

Abstract

ABSTRACT A new implemented quantitative structure-property relationships (QSPR) method, whose descriptors achieved from bidimensional images, was suggested for the predicting of acidity constant (p K a ) of various acid. The resulted descriptors were subjected to principal component analysis (PCA) and the most significant principal components (PCs) were extracted. Multivariate image analysis applied to QSPR modeling was done by means of principal component-least squares support vector machine (PC-LSSVM) methods. The resulted model showed high prediction ability with root mean square error of prediction of 0.0195 for PC-LSSVM. Keywords: QSPR; PC-LSSVM; Multivariate image analysis; Acidity constant. INTRODUCTION Acidity constants are important parameters indicating the extent of ionization of molecules in solution at different pH values. The acidity constants of organic reagents play a fundamental role in many analytical procedures such as acid-base titration, solvent extraction, complex formation, and ion transport. It has been shown that acid-base properties affect the toxicity, chromatographic retention behavior, and pharmaceutical properties of organic acids and bases. Much of the theoretical foundation of modern organic chemistry is based on the observation of the effects on acid-base equilibrium of changing molecular structure