Abstract
Aim and Objective: Human dihydroorotate dehydrogenase (DHODH) catalyzes the fourth stage of the biosynthesis of pyrimidines in cells. Hence it is important to identify suitable inhibitors of DHODH to prevent virus replication. In this study, a quantitative structure-activity relationship was performed to predict the activity of one group of newly synthesized halogenated pyrimidine derivatives as inhibitors of DHODH.
Materials and Methods: Molecular structures of halogenated pyrimidine derivatives were drawn in the HyperChem and then molecular descriptors were calculated by DRAGON software. Finally, the most effective descriptors for 32 halogenated pyrimidine derivatives were selected using bee algorithm.
Results: The selected descriptors using bee algorithm were applied for modeling. The mean relative error and correlation coefficient were obtained as 2.86% and 0.9627, respectively, while these amounts for the leave one out−cross validation method were calculated as 4.18% and 0.9297, respectively. The external validation was also conducted using two training and test sets. The correlation coefficients for the training and test sets were obtained as 0.9596 and 0.9185, respectively.
Conclusion: The results of modeling of present work showed that bee algorithm has good performance for variable selection in QSAR studies and its results were better than the constructed model with the selected descriptors using the genetic algorithm method.
Keywords: Bee algorithm, Leaveoneout–cross-validation, quantitative structure-property relationship, variable selection method, halogenated pyrimidine derivatives, dihydroorotate dehydrogenase.
Related Journals
Current Computer-Aided Drug Design
25
3