SynthStrategy: Extracting and Formalizing Latent Strategic Insights from LLMs in Organic Chemistry

TL;DR

This paper presents SynthStrategy, a method using Large Language Models to extract, formalize, and test strategic insights in organic synthesis planning, improving route retrieval and analysis.

Contribution

It introduces a novel approach to formalize strategic synthesis principles as Python code, enabling interpretable, verifiable, and strategic-aware synthesis route analysis in CASP.

Findings

Achieved 75% Top-3 accuracy in route retrieval

Created a dataset with strategic annotations of synthesis routes

Enabled granular clustering and historical trend analysis

Abstract

Modern computer-assisted synthesis planning (CASP) systems show promises at generating chemically valid reaction steps but struggle to incorporate strategic considerations such as convergent assembly, protecting group minimization, and optimal ring-forming sequences. We introduce a methodology that leverages Large Language Models to distill synthetic knowledge into code. Our system analyzes synthesis routes and translates strategic principles into Python functions representing diverse strategic and tactical rules, such as strategic functional group interconversions and ring construction strategies. By formalizing this knowledge as verifiable code rather than simple heuristics, we create testable, interpretable representations of synthetic strategy. We release the complete codebase and the USPTO-ST dataset -- synthesis routes annotated with strategic tags. This framework unlocks a novel capability for CASP: natural language-based route retrieval, achieving 75\% Top-3 accuracy on our benchmark. We further validate our library through temporal analysis of historical trends and chemically intuitive route clustering that offers more granular partitioning than common previous methods. This work bridges the tactical-strategic divide in CASP, enabling specification, search, and evaluation of routes by strategic criteria rather than structure alone.