New Potential Drug Candidates Against SARS-CoV-2 Using Generative Model
<div>Since known approved drugs like liponavir and ritonavir failed to cure SARS-CoV-2 </div><div>infected patients, it is high time to generate new chemical entities against this virus. </div><div>3CL main protease acts as key enzyme for the growth of a virus which acts as </div><div>biocatalyst and helps to break protein and ultimately in the growth of coronavirus. </div><div>Based on a recently solved structure (PDB ID: 6LU7), we developed a novel </div><div>advanced deep Q-learning network with the fragment-based drug design </div><div>(ADQN-FBDD) along with variational autoencoder with KL annealing and circular </div><div>annealing for generating potential lead compounds targeting SARS-CoV-2 3CLpro. </div><div>Structure-based optimization policy (SBOP) is used in reinforcement learning. The </div><div>reason for using variational autoencoders is that it does not deviate much from actual </div><div>inhibitors, but since VAE suffers from KL diminishing we have used KL annealing </div><div>and circular annealing to address this issue. Researchers can use this compound as </div><div>potential drugs against SARS-CoV-2</div>