In order to investigate the relationship between activities and structures, a QSAR study is applied to a set of 23 phenol derivatives compounds. This study is conducted using the principal component analysis (PCA) method, the linear multiple regression method (MLR), the non-linear regression (MNLR) and the artificial neural network (ANN). We accordingly propose a quantitative model, and we interpret the activity of the compounds relying on the multivariate statistical analysis. Density functional theory (DFT) and ab-initio molecular orbital calculations have been carried out in order to get insights into the structure, chemical reactivity and property information for the series of study compounds. This study shows that the MRA and MNLR are served also to predict activities, but when compare with the results given by the ANN, we realize that the predictions fulfilled by this latter is more effective. To validate the predictive power of the resulting models, external validation multiple correlation coefficient are 0.80 and 0.78 for the MLR and the MNLR respectively. This model gives statistically significant results and shows good stability to data variation in leave-one-out cross-validation. The obtained results suggested that the proposed combination of several calculated parameters could be useful to predict the biological activity of phenol derivatives over Tetrahymena pyriformis.
