Lasinavir

The machine learning methods artificial neural network (ANN) and support vector machine (SVM) techniques were used to model intrinsic solubility of 74 generic drugs. The models obtained were compared with those obtained using multiple linear regression (MLR) analysis. Cluster analysis was used to split the data into a training set and test set. The appropriate descriptors were selected using a wrapper approach with multiple linear regressions as target learning algorithm. The descriptor selection and model building were performed with 10 fold cross validation using the training data set. The linear model fits the training set (n = 60) with R(2) = 0.814, while ANN and SVM higher values of R(2) = 0.823 and 0.835, respectively. Though the SVM model shows improvement of training set fitting, the ANN model was slightly superior to SVM and MLR in predicting the test set. The quantitative structure-property relationship study suggests that the theoretically calculated descriptors log P, first-order valence connectivity index ((1)chi(v)), delta chi (Delta(2)chi) and information content ((2)IC) have relevant relationships with intrinsic solubility of generic drugs studied.

In this paper we describe a comparative analysis between multivariate and docking methods in the study of the drug resistance to the reverse transcriptase and the protease inhibitors. In our early papers we developed a simple but efficient method to evaluate the features of compounds that are less likely to trigger resistance or are effective against mutant HIV strains, using the multivariate statistical procedures PCA and DA. In the attempt to create a more solid background for the prediction of susceptibility or resistance, we carried out a comparative analysis between our previous multivariate approach and molecular docking study. The intent of this paper is not only to find further support to the results obtained by the combined use of PCA and DA, but also to evidence the structural features, in terms of molecular descriptors, similarity, and energetic contributions, derived from docking, which can account for the arising of drug-resistance against mutant strains.