Quantitative Structure Activity Relationships (QSAR or SAR) have helped scientists to\nestablish mathematical relationships between molecular structures and their biological activities. In the\npresent article, SAR studies have been carried out on 89 tetrahydroimidazo[4,5,1-jk][1,4]benzodiazepine\n(TIBO) derivatives using different classifiers, such as support vector machines, artificial neural\nnetworks, random forests, and decision trees. The goal is to propose classification models that\nwill be able to classify TIBO compounds into two groups: high and low inhibitors of HIV-1\nreverse transcriptase. Each molecular structure was encoded by 10 descriptors. To check the\nvalidity of the established models, all of them were subjected to various validation tests: internal\nvalidation, Y-randomization, and external validation. The established classification models have\nbeen successful. The correct classification rates reached 100% and 90% in the learning and test\nsets, respectively. Finally, molecular docking analysis was carried out to understand the interactions\nbetween reverse transcriptase enzyme and the TIBO compounds studied. Hydrophobic and hydrogen\nbond interactions led to the identification of active binding sites. The established models could help\nscientists to predict the inhibition activity of untested compounds or of novel molecules prior to\ntheir synthesis. Therefore, they could reduce the trial and error process in the design of human\nimmunodeficiency virus (HIV) inhibitors.
Loading....