AI-Aided Search for New HIV-1 Protease Ligands.

The availability of drugs capable of blocking the replication of microorganisms has been one of the greatest triumphs in the history of medicine, but the emergence of an ever-increasing number of resistant strains poses a serious problem for the treatment of infectious diseases. The search for new potential ligands for proteins involved in the life cycle of pathogens is, therefore, an extremely important research field today. In this work, we have considered the HIV-1 protease, one of the main targets for AIDS therapy. Several drugs are used today in clinical practice whose mechanism of action is based on the inhibition of this enzyme, but after years of use, even these molecules are beginning to be interested by resistance phenomena. We used a simple artificial intelligence system for the initial screening of a data set of potential ligands. These results were validated by docking and molecular dynamics, leading to the identification of a potential new ligand of the enzyme which does not belong to any known class of HIV-1 protease inhibitors. The computational protocol used in this work is simple and does not require large computational power. Furthermore, the availability of a large number of structural information on viral proteins and the presence of numerous experimental data on their ligands, with which it is possible to compare the results obtained with computational methods, make this research field the ideal terrain for the application of these new computational techniques.