Models for anti-inflammatory activity of 8-substituted-4-anilino-6-aminoquinoline-3-carbonitriles

An in silico approach through decision tree (DT) and moving average analysis (MAA) has been employed for development of models for prediction of anti-inflammatory activity. A data set consisting of 44 analogues of 8-substituted-4-anilino-6-aminoquinoline-3-carbonitriles was selected for this study. These compounds act as anti-inflammatory agents through inhibition of tumor progression loci-2 (Tpl2) kinase and tumor necrosis factor-α (TNF-α) production. A total of 44 descriptors of diverse nature, from a large pool of molecular descriptors calculated through E-Dragon software (version 1.0) and an in-house computer program were selected for further analysis. DT was used to determine the importance of molecular descriptors. DT identified two topological indices as most important and classified the analogues involved in the data set with an accuracy of ~91% in training set and ~66% in 10 fold cross validated set. Three independent models were also developed through MAA. Accuracy of prediction of these models varied from 87.5 to 92.5%. The statistical significance of proposed models was assessed through intercorrelation analysis, sensitivity, specificity, and Matthew’s correlation coefficient. The proposed models offer a vast potential for providing lead structures for development of potent anti-inflammatory drugs.