RetroGraph: Retrosynthetic Planning with Graph Search

TL;DR

RetroGraph introduces a graph-based search method guided by a graph neural network for retrosynthetic planning, significantly improving success rates and efficiency over previous tree-based approaches.

Contribution

The paper presents a novel graph search policy and neural network guidance that reduce redundant exploration and enable batch processing for retrosynthetic planning.

Findings

Achieves 99.47% success rate on USPTO benchmark.

Outperforms previous methods by 2.6 points in success rate.

Demonstrates improved efficiency and scalability in retrosynthetic search.

Abstract

Retrosynthetic planning, which aims to find a reaction pathway to synthesize a target molecule, plays an important role in chemistry and drug discovery. This task is usually modeled as a search problem. Recently, data-driven methods have attracted many research interests and shown promising results for retrosynthetic planning. We observe that the same intermediate molecules are visited many times in the searching process, and they are usually independently treated in previous tree-based methods (e.g., AND-OR tree search, Monte Carlo tree search). Such redundancies make the search process inefficient. We propose a graph-based search policy that eliminates the redundant explorations of any intermediate molecules. As searching over a graph is more complicated than over a tree, we further adopt a graph neural network to guide the search over graphs. Meanwhile, our method can search a batch of targets together in the graph and remove the inter-target duplication in the tree-based search methods. Experimental results on two datasets demonstrate the effectiveness of our method. Especially on the widely used USPTO benchmark, we improve the search success rate to 99.47%, advancing previous state-of-the-art performance for 2.6 points.