RetroG: Retrosynthetic Planning with Tree Search and Graph Learning

Abstract

Retrosynthesis Planning (RP) is one of the challenging problems in organic chemistry. It involves designing target molecules using compounds which are commercially available or easy to synthesize by following a series of backward steps. While the conventional RP methods were majorly expert-based, successful computer-aided RP methods have emerged in the recent past. This success is critical to the development of new drugs and the synthesis of target compounds in material science and agrochemicals domains. In this paper, we present an RP model called RetroG. Its design is based on tree search with a Graph Neural Network (GNN) as a value function. The model adapts successful reaction templates and product molecules to the route length. The evaluation of RetroG on the test benchmark datasets records new results while also presenting interesting future research areas.