Detection of molecules that may be effective against 2019-nCoV virus with drug reconstruction and machine learning approach methods

Within the scope of the project, it was aimed to find novel inhibitors of the SARS-CoV-2 in order to prevent the rapid spread and self-replication of the virus. In order to design inhibitors, it was aimed to produce molecules similar to the RdRp inhibitor drug Favipiravir by using the deep learning method. For this purpose, a Trained Neural Network was used to produce 75 molecules similar to Favipiravir by using SMILES representations. The binding properties of molecules to RdRp were studied by using molecular docking studies. These compounds were also tested against 3Clpro which is another important enzyme for the SARS-CoV-2 life cycle. Compounds having better binding energies and RMSD values than favipiravir were searched with similarity analysis on the ChEMBL drug database in order to find similar structures having with RdRp and 3CLpro inhibitory activities. Similarity search found new 200 potential RdRp and 3CLpro inhibitors structurally similar to produced molecules, and these compounds were again evaluated of their receptor interactions with molecular docking studies. Compounds showed better interaction with RdRp protease than 3CLpro. This result presented that artificial intelligence correctly produced structures similar to favipiravir that act more specifically as RdRp inhibitors. In addition, Lipinski's rules have applied to the molecules which show the best interaction with RdRp, and 7 compounds were determined to be potential drug candidates.