Application of multivariate image analysis in QSPR study of 13C chemical shifts of naphthalene derivatives: A comparative study

A new implemented QSPR method, whose descriptors achieved from bidimensional images, was applied for predicting 13C NMR chemical shifts of 25 mono substituted naphthalenes. The resulted descriptors were subjected to principal component analysis (PCA) and the most significant principal components (PCs) were extracted. MIA-QSPR (multivariate image analysis applied to quantitative structure–property relationship) modeling was done by means of principal component regression (PCR) and principal component-artificial neural network (PC-ANN) methods. Eigen value ranking (EV) and correlation ranking (CR) were used here to select the most relevant set of PCs as inputs for PCR and PC-ANN modeling methods. The results supported that the correlation ranking-principal component-artificial neural network (CR-PC-ANN) model could predict the 13C NMR chemical shifts of all 10 carbon atoms in mono substituted naphthalenes with R2 ≥ 0.922 for training set, R2 ≥ 0.963 for validation set and R2 ≥ 0.936 for the test set. Comparison of the results with other existing factor selection method revealed that less accurate results were obtained by the eigen value ranking procedure.