Recently, molecular
generation models based on deep learning have attracted significant attention
in drug discovery. However, most existing molecular generation models have a
serious limitation in the context of drug design wherein they do not
sufficiently consider the effect of the three-dimensional (3D) structure of the
target protein in the generation process. In this study, we developed a new
deep learning-based molecular generator, SBMolGen, that integrates a recurrent
neural network, a Monte Carlo tree search, and docking simulations. The results
of an evaluation using four target proteins (two kinases and two G
protein-coupled receptors) showed that the generated molecules had a better
binding affinity score (docking score) than the known active compounds, and they
possessed a broader chemical space distribution. SBMolGen not only generates
novel binding active molecules but also presents 3D docking poses with target
proteins, which will be useful in subsequent drug design.