Structure-Activity Relationships on Purine and 2,3-Dihydropurine Derivatives as Antitubercular Agents: a Data Mining Approach

Nowadays, many people still fall victim to tuberculosis, the disease that has a worldwide spreading. Moreover, the problem of resistance to isoniazid and rifampin, the two most effective antitubercular drugs, is assuming an ever-growing importance. The need for new drugs active against Mycobacterium tuberculosis represents nowadays a quite relevant problem in medicinal chemistry. Several purine and 2,3-dihydropurine derivatives have recently emerged, showing considerable antitubercular properties. In this work, a quantitative structure– activity relationship (QSAR) model was developed, which is able to predict whether new purine and 2,3-dihydropurine derivatives belong to an ’Active’ or ’Inactive’ class against the above micro-organism. The obtained prediction model is based on a classification tree; it was built with a small number of descriptors, which allowed us to outline structural features important to predict antitubercular activity of such classes of compounds.