A generative model for molecule generation based on chemical reaction trees
This work addresses a practical problem for chemists and drug discovery by providing synthetic routes alongside molecule generation, though it is incremental as it builds on existing generative approaches.
The paper tackles the limitation of existing deep generative models in recommending synthetic routes for generated molecules by proposing a model that generates molecules via multi-step chemical reaction trees, resulting in product molecules with desired chemical properties and complete synthetic routes.
Deep generative models have been shown powerful in generating novel molecules with desired chemical properties via their representations such as strings, trees or graphs. However, these models are limited in recommending synthetic routes for the generated molecules in practice. We propose a generative model to generate molecules via multi-step chemical reaction trees. Specifically, our model first propose a chemical reaction tree with predicted reaction templates and commercially available molecules (starting molecules), and then perform forward synthetic steps to obtain product molecules. Experiments show that our model can generate chemical reactions whose product molecules are with desired chemical properties. Also, the complete synthetic routes for these product molecules are provided.