Strategy-first synthesis planning for complex natural products

2026-08-07

AI Summary

Traditional retrosynthetic tools are constrained by reaction databases and struggle to devise creative synthetic routes for highly functionalized, polycyclic natural products. This work proposes SynthEx, a framework that leverages large language models to construct an intelligent agent system employing a strategy-first planning mechanism. By generating competitive synthetic strategies, integrating critical and routine steps, and incorporating self-reflection for iterative refinement, SynthEx achieves high-quality retrosynthetic planning. Notably, it produces key disconnections comparable to those devised by human experts—validated as authentic and feasible by chemists in blind evaluations. The method successfully designs highly convergent routes for over a thousand natural products and introduces SynthAtlas, an open-access database of these pathways, which has garnered recognition from domain experts.

Abstract

The total synthesis of a complex molecule is among the most demanding intellectual and experimental feats in chemistry: a chemist must plan many steps ahead for how to assemble simple building blocks into an intricate target, devise backup strategies, and anticipate procedural challenges. It is also a profoundly creative activity. For half a century, efforts to automate the retrosynthetic design of natural products and other complex molecules have drawn on catalogued reactions, and the resulting tools now report near-complete success on benchmarks built from that same source. But these tools were shaped to fit benchmarked chemistry, and they falter on many natural products, the frontier of the field, whose densely functionalized, polycyclic architectures demand precisely the inventive chemistry the record contains least. Whether a machine could reasonably design such syntheses like an expert chemist does has remained unclear. Here, we show that SynthEx, an agentic framework built on large language models, plans routes to complex natural products that lie beyond the reach of conventional design algorithms. SynthEx proposes competing strategies, assembles a sequence of routine and key steps into a cohesive route, and critiques and improves its own design; the chemistry it favours is more convergent than existing tools produce, and spans a region of reaction space that catalogue-based tools cannot match. Most notably, in blinded assessments, expert chemists judged its key steps comparable to those of published human syntheses and engaged with them as genuine synthesis plans, a response algorithmic route prediction has not previously accomplished. We release routes to more than a thousand natural products as SynthAtlas, an open, interactive database, and anticipate it will become a shared resource for a collection of complex target molecules that lack existing literature routes.

Problem

• retrosynthetic planning
• complex natural products
• automated synthesis design
• inventive chemistry
• polycyclic architectures

Innovation

• agentic framework
• large language models
• retrosynthetic planning
• convergent synthesis
• reaction space exploration