No abstract

No abstract

A new approach is introduced for the construction of a predictive quantitative structure–activity relationship model in which only ligand–receptor (LR) interaction features are used as relevant descriptors. This approach combines the benefit of the random forest (RF) as a new variable selection method with the intrinsic capability of the artificial neural network (ANN). The interaction information of the ligand–receptor (LR) complex was used as molecular docking descriptors. The most relevant descriptors were selected using the RF technique and used as inputs of ANN. The proposed RF ANN (RF‐LM‐ANN) method was optimized and then evaluated by the prediction of pEC50 for some of the azine derivatives as non‐nucleoside reverse transcriptase inhibitors. RF‐LM‐ANN model under the optimal conditions was evaluated using internal (validation) and external test sets. The determination coefficients of the external test and validation sets were 0.88 and 0.89, respectively. The mean square deviation (MSE) values for the prediction of biological activities in the external test and validation sets were found to be 0.10 and 0.11, respectively. The results obtained demonstrated the good prediction ability and high generalizability of the proposed RF‐LM‐ANN model based on the MMDs alone.

No abstract

A combination of ligand-receptor interactions and drug-like indexes have been used to develop a quantitative structure-activity relationship model to predict anti-HIV activity (pEC 50 ) of 73 azine derivatives as non-nucleoside reverse transcriptase inhibitors. Ligand-receptor interactions were derived from the best position (best pose) of studied compounds, as ligands, in the active site of receptors using Autodock 4.2 software and named as molecular docking descriptors. The drug-like indexes were calculated using DRAGON 5.5 software. Two groups of descriptors were mixed, and the stepwise regression method was used for the selection of the most relevant descriptors. Four selected descriptors were subsequently used to construct the quantitative structure-activity relationship model using the Levenberg-Marquardt artificial neural network method. Dataset was randomly divided into the train (53 compounds), validation (10 compounds) and test set (10 compounds). The best model was selected according to the lowest mean square error value of the validation set. The accuracy and predictability of the model were evaluated using test and validation sets and the leave-one-out technique. According to the predicted results, the coefficient of determination of the test set (R 2 = 0.86) and all data ( Q 2 LOO = 0.73) were acceptable. The mean square error value for the test set was equal to 0.11. The obtained results emphasized the good prediction ability and generalizability of the developed model in the prediction of pEC 50 values for new compounds.