LLM-Augmented Chemical Synthesis and Design Decision Programs

TL;DR

This paper investigates leveraging large language models to improve multi-step retrosynthesis planning and molecular design, addressing the complexity of chemical pathway exploration.

Contribution

It introduces a novel encoding scheme and route-level search strategy that enhance LLMs' ability to plan chemical synthesis routes more effectively.

Findings

LLM-augmented approach outperforms traditional methods in retrosynthesis planning.

The method extends to broader molecular design challenges.

Proposed encoding and search strategies improve pathway exploration efficiency.

Abstract

Retrosynthesis, the process of breaking down a target molecule into simpler precursors through a series of valid reactions, stands at the core of organic chemistry and drug development. Although recent machine learning (ML) research has advanced single-step retrosynthetic modeling and subsequent route searches, these solutions remain restricted by the extensive combinatorial space of possible pathways. Concurrently, large language models (LLMs) have exhibited remarkable chemical knowledge, hinting at their potential to tackle complex decision-making tasks in chemistry. In this work, we explore whether LLMs can successfully navigate the highly constrained, multi-step retrosynthesis planning problem. We introduce an efficient scheme for encoding reaction pathways and present a new route-level search strategy, moving beyond the conventional step-by-step reactant prediction. Through comprehensive evaluations, we show that our LLM-augmented approach excels at retrosynthesis planning and extends naturally to the broader challenge of synthesizable molecular design.