A generative model for molecule generation based on chemical reaction trees

TL;DR

This paper introduces a generative model that creates molecules through multi-step chemical reaction trees, enabling the prediction of synthetic routes and desired chemical properties.

Contribution

The proposed model uniquely generates molecules along with their synthetic routes using reaction trees, advancing molecule generation by integrating synthesis planning.

Findings

Model successfully generates molecules with desired properties

Provides complete synthetic routes for generated molecules

Outperforms baseline models in reaction prediction

Abstract

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.