Application of deep learning and molecular modeling to identify small drug-like compounds as potential HIV-1 entry inhibitors.

A generative adversarial autoencoder for the rational design of potential HIV-1 entry inhibitors able to block CD4-binding site of the viral envelope protein gp120 was developed. To do this, the following studies were carried out: (i) an autoencoder architecture was constructed; (ii) a virtual compound library of potential anti-HIV-1 agents for training the neural network was formed by the concept of click chemistry allowing one to generate a large number of drug candidates by their assembly from small modular units; (iii) molecular docking of all compounds from this library with gp120 was made and calculations of the values of binding free energy were performed; (iv) molecular fingerprints of chemical compounds from the training dataset were generated; (v) training of the developed autoencoder was implemented followed by the validation of this neural network using more than 21 million molecules from the ZINC15 database. As a result, three small drug-like compounds that exhibited the high-affinity binding to gp120 were identified.

In Silico Identification of Novel Aromatic Compounds as Potential HIV-1 Entry Inhibitors Mimicking Cellular Receptor CD4.

Despite recent progress in the development of novel potent HIV-1 entry/fusion inhibitors, there are currently no licensed antiviral drugs based on inhibiting the critical interactions of the HIV-1 envelope gp120 protein with cellular receptor CD4. In this connection, studies on the design of new small-molecule compounds able to block the gp120-CD4 binding are still of great value. In this work, in silico design of drug-like compounds containing the moieties that make the ligand active towards gp120 was performed within the concept of click chemistry.