Retrosynthetic Planning with Experience-Guided Monte Carlo Tree Search

TL;DR

This paper introduces an experience-guided Monte Carlo tree search method for retrosynthetic planning, improving efficiency and accuracy by learning from synthetic experiences, outperforming existing approaches on benchmark datasets and aiding chemists.

Contribution

The paper presents a novel EG-MCTS approach that replaces traditional score functions with an experience guidance network, enhancing retrosynthetic route prediction.

Findings

EG-MCTS outperforms state-of-the-art methods in efficiency and effectiveness

Generated routes mostly match reported routes in literature

Routes for real drug compounds demonstrate practical utility

Abstract

In retrosynthetic planning, the huge number of possible routes to synthesize a complex molecule using simple building blocks leads to a combinatorial explosion of possibilities. Even experienced chemists often have difficulty to select the most promising transformations. The current approaches rely on human-defined or machine-trained score functions which have limited chemical knowledge or use expensive estimation methods for guiding. Here we an propose experience-guided Monte Carlo tree search (EG-MCTS) to deal with this problem. Instead of rollout, we build an experience guidance network to learn knowledge from synthetic experiences during the search. Experiments on benchmark USPTO datasets show that, EG-MCTS gains significant improvement over state-of-the-art approaches both in efficiency and effectiveness. In a comparative experiment with the literature, our computer-generated routes mostly matched the reported routes. Routes designed for real drug compounds exhibit the effectiveness of EG-MCTS on assisting chemists performing retrosynthetic analysis.