QSAR study of Quinazoline derivatives as tyrosine kinase inhibitors using multivariate image analysis and partial least squares

A quantitative structure0activity relationship (QSAR) modeling was carried out for the prediction of inhibitory activity of Quinazoline derivatives as tyrosine kinase inhibitors [1]. QSAR is mathematical model of activity in terms of structural descriptors. The QSAR model is useful for understanding the factors controlling activity, prediction of activity and for designing new potent compounds. The main aim of QSAR studies is to establish an empirical rule or function relating the descriptors of compounds under investigation to activities or properties. This rule of function is then utilized to predict the same activities/properties of the compounds not involved in the training set from their descriptors [2-4]. Partial least squares (PLS) algorithm was used for prediction of inhibitory activity as a function of the Bidimensional images. In the present study, it is investigated that the effect of pixel processing by application of orthogonal signal correction (OSC) for PLS model, because of the OSC is very useful in the preprocessing in modeling [5]. The results of all models are compared with statistical parameters such as RMSEP, RSEP, R2 and Q2. The resulted model showed high prediction ability with root mean square error of prediction of 0.0359 and 0.0107 for PLS and OSC-PLS. Results have shown that the introduction of OSC-PLS for pixel descriptors drastically enhances the ability of prediction in QSAR studies superior to other calibration algorithms.