AKT as a result of inactivation of tumor suppressor PTEN has been found in a variety of human tumors. AKT has long been considered an attractive target for the treatment of cancers. A computational multivariate regression was carried out on a set of 61 pyridine based analogs to study the influence of physico-chemical properties on AKT inhibition. A regression model was generated by dividing the complete set as a 51 molecule training set and a 6 molecule validation set based on selection criteria after rejecting outliers from the data set. The generated equation when applied on test set molecules suggested predictive ability. The model can be utilized to study the efficacy of AKT inhibition based on the properties evaluated.