[Consensus ensemble neural network multitarget model of RAGE inhibitory activity of chemical compounds]. / Konsensusnaia ansamblevaia neirosetevaia mul'titargetnaia model' RAGE-ingibiruiushchei aktivnosti khimicheskikh soedinenii.

RAGE signal transduction via the RAGE-NF-κB signaling pathway is one of the mechanisms of inflammatory reactions that cause severe complications in diabetes mellitus. RAGE inhibitors are promising pharmacological compounds that require the development of new predictive models. Based on the methodology of artificial neural networks, consensus ensemble neural network multitarget model has been constructed. This model describes the dependence of the level of the RAGE inhibitory activity on the affinity of compounds for 34 target proteins of the RAGE-NF-κB signal pathway. For this purpose an expanded database of valid three-dimensional models of target proteins of the RAGE-NF-κB signal chain was created on the basis of a previously created database of three-dimensional models of relevant biotargets. Ensemble molecular docking of known RAGE inhibitors from a verified database into the sites of added models of target proteins was performed, and the minimum docking energies for each compound in relation to each target were determined. An extended training set for neural network modeling was formed. Using seven variants of sampling by the method of artificial multilayer perceptron neural networks, three ensembles of classification decision rules were constructed to predict three level of the RAGE-inhibitory activity based on the calculated affinity of compounds for significant target proteins of the RAGE-NF-κB signaling pathway. Using a simple consensus of the second level, the predictive ability of the created model was assessed and its high accuracy and statistical significance were shown. The resultant consensus ensemble neural network multitarget model has been used for virtual screening of new derivatives of different chemical classes. The most promising substances have been synthesized and sent for experimental studies.

[Neural network modeling of multitarget RAGE inhibitory activity]. / Neirosetevoe modelirovanie mul'titargetnoi RAGE-ingibiruiushchei aktivnosti.

Based on the methodology of artificial neural networks, models describing the dependence of the level of RAGE inhibitory activity on the affinity of compounds for target proteins of the RAGE-NF-kB signal pathway have been costructed. A validated database of the structures and activity levels of 183 known compounds, which were tested for RAGE inhibitory activity was formed. The analysis of the AGE-RAGE signaling pathways was carried out, 14 key RAGE-NF-kB signal pathway nodes were found, for which 34 relevant target proteins were identified. A database of 66 valid 3D models of 22 target proteins of the RAGE-NF-kB signal chain was compiled. Ensemble molecular docking of 3D models of 183 known RAGE inhibitors into sites of 66 valid 3D models of 22 relevant RAGE target proteins was performed and minimum docking energies for each compound were determined for each target. According to the method of artificial multilayer perceptron neural networks, classification models were constructed to predict level of RAGE inhibitory activity based on the calculated affinity of compounds for significant target proteins of the RAGE-NF-kB signaling chain. The prognostic ability of these models of RAGE-inhibitory activity was evaluated, the maximum accuracy according to ROC-analysis was 90% for a high level of activity. The sensitivity analysis of the developed multitarget models were carried out, the most significant targets of the RAGE-NF-kB signal transmission chain were determined. It was found that for high level of RAGE inhibitory activity, the most significant biotargets are not AGE receptors, but eight signaling kinases of the RAGE-NF-kB pathway and transcription factor NF-kB1. Thus, it is suggested that known compounds with high RAGE-inhibitory activity are preferential inhibitors of signal kinases.