🤖 AI Summary
Inverse synthesis planning confronts dual challenges: combinatorial explosion in multi-branch pathway search and inherent chemical uncertainty in reaction feasibility. This paper introduces the first probabilistic graphical model–based framework for inverse synthesis, modeling synthetic pathways as stochastic processes to maximize the probability of successful target molecule synthesis. Methodologically, it integrates reverse reaction graph search, chain-rule–driven gradient acceleration, Monte Carlo sampling, and deterministic backtracking—ensuring chemical validity while enhancing search efficiency. Evaluated on the Paroutes benchmark, our approach achieves a 12% improvement in pathway quality and a 3.2× speedup in planning time over Retro* and Retro-Fallback, striking a superior balance between synthesis success rate and computational scalability.
📝 Abstract
Retrosynthesis is a fundamental but challenging task in organic chemistry, with broad applications in fields such as drug design and synthesis. Given a target molecule, the goal of retrosynthesis is to find out a series of reactions which could be assembled into a synthetic route which starts from purchasable molecules and ends at the target molecule. The uncertainty of reactions used in retrosynthetic planning, which is caused by hallucinations of backward models, has recently been noticed. In this paper we propose a succinct probabilistic model to describe such uncertainty. Based on the model, we propose a new retrosynthesis planning algorithm called retro-prob to maximize the successful synthesis probability of target molecules, which acquires high efficiency by utilizing the chain rule of derivatives. Experiments on the Paroutes benchmark show that retro-prob outperforms previous algorithms, retro* and retro-fallback, both in speed and in the quality of synthesis plans.