Computational Modeling of New Drugs for the Treatment of Alzheimer’s Disease (AD) using Functional Correlations and Artificial Intelligence (AI)

The study aims to modify current medications of Alzheimer’s disease (AD) with the use of our computational modeling methods. The modifications are designed to enhance the binding affinity of the newly designed drugs to protein molecules involved in Alzheimer’s, measured by the half maximal inhibitory concentration (IC50) value. This value is a measure of the concentration needed for the drug to inhibit a specific biological function. Two techniques are used to predict the anticipated modified IC50 values. First, by using the energies and the experimentally determined IC50 values, the functional graph approaches create correlations that lead to projected IC50 values for the changed drug molecules. The second approach in this research predicted the IC50 values of changed drug compounds using an artificial intelligence programme called NETS. Four modified drug molecules produced promising results in which the IC50 values were enhanced by one order of magnitude or more. The findings demonstrate that computational modelling can be a novel, time-saving, and great step in drug discovery.