Chemistry tool uses AI to plan complex molecule synthesis routes
ReTRACE: Feedback-Guided LLM Agent in a Chemistry Harness for Retrosynthesis Planning
Artificial Intelligence
Summary
Planning how to make complex molecules is hard because many factors like cost and safety must be considered across multiple steps. The authors created ReTRACE, a system that combines a large language model with chemistry tools to suggest full synthesis routes. It checks these routes using automated tests and expert-like reviews, learning to improve suggestions over time. The system showed strong success on standard benchmarks and was tested in real lab experiments after expert refinement.
What this means in practice
- •For chemical process engineers: Generate and evaluate multi-step synthetic routes to complex molecules with integrated criteria for cost and feasibility to aid development decisions.
- •For pharmaceutical chemists: Produce candidate synthesis paths that can be adapted by experts into lab procedures for drug compound preparation.
Authors
Jinxiang Xie, Yijian Zhang, Qingyuan Yi, Jianyi Wang, Hao Dong
Abstract
Computer-aided retrosynthesis has advanced through single-step prediction, tree search and route scoring, but complex targets still require judgement over the whole route, where stereochemistry, functional-group compatibility, cost and greenness interact. Here we present \textbf{\mbox{ReTRACE}} (\textbf{RE}trosynthesis with \textbf{T}ool-orchestrated \textbf{R}easoning \textbf{A}nd \textbf{C}ontext-aware \textbf{E}vidence), an agent that places a large language model (LLM) in a chemistry harness that integrates molecular tools, complementary single-step prediction engines, a purchasable starting-material library, a route memory and a multi-criterion route evaluator. Routes are judged by a new metric that combines programmatic checks with adversarial LLM review, and its verdicts are compared with a synthetic chemist's. The agent learns continually from evaluator feedback during search, diagnosing weak routes and backtracking to revise them. With Claude Opus 4.8, at least one of the top 10 routes proposed by ReTRACE passed the audit for 87.4\%, 95.0\% and 86.7\% of targets on the three benchmarks. Two prospective wet-lab syntheses show that ReTRACE route proposals can be converted into executable procedures after expert revision.