De novo Drug Design against SARS-CoV-2 Protein Targets using SMILES-based Deep Reinforcement Learning
Xiuyuan Hu, Yanghepu Li, Guoqing Liu, Yang Zhao, Hao Zhang, Liang Zhao · 2023
De novo drug design is an important task within the field of computer-aided drug design, and in recent years, numerous machine learning algorithms have been proposed for this purpose. The SARS-CoV-2 virus has posed a severe crisis to humanity over the past few years, making drug design targeting its protein targets a critical challenge. In this paper, we introduce a SMILES-based deep reinforcement learning algorithm to design small molecule inhibitors that bind well with SARS-CoV-2 targets. Experimental results demonstrate that our algorithm is capable of generating satisfactory drug candidates against SARS-CoV-2 protein targets and has the potential to be extended to other targets.