Antitubercular drug discovery is a challenging strain in the recent era. Quinazolines are an important chemical compounds having diverse significant biological activities. Three dimensional Quantitative structure-activity relationships ( 3D QSAR) represent an attempt to correlate three dimensional structural features of compounds with biological activities. The pharmacophore identification and QSAR studies on C-2 and C-4 substituted quinazoline series was carried out by partial least-squares (PLS) method to identify the potential framework of the molecules responsible for the antitubercular activity. The QSAR models were developed considering training and test set approaches further validated for statistical significance and predictive ability by internal and external validation. The results of 3D QSAR model demonstrate the high degree of statistical importance and excellent predictive capability. The hydrogen bond accepter, hydrogen bond donor, positively charged, aromatic carbon, steric and hydrophobic parameter are the important features contributing towards the activity. The selected best QSAR model A has a training set of 20 molecules and test set of 6 molecules with correction coefficient of 0.9641.
