LLM-Augmented Chemical Synthesis and Design Decision Programs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Haorui, Guo, Jeff, Kong, Lingkai, Ramprasad, Rampi, Schwaller, Philippe, Du, Yuanqi, Zhang, Chao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917475673702400
author Wang, Haorui
Guo, Jeff
Kong, Lingkai
Ramprasad, Rampi
Schwaller, Philippe
Du, Yuanqi
Zhang, Chao
author_facet Wang, Haorui
Guo, Jeff
Kong, Lingkai
Ramprasad, Rampi
Schwaller, Philippe
Du, Yuanqi
Zhang, Chao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07027
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Augmented Chemical Synthesis and Design Decision Programs
Wang, Haorui
Guo, Jeff
Kong, Lingkai
Ramprasad, Rampi
Schwaller, Philippe
Du, Yuanqi
Zhang, Chao
Artificial Intelligence
Computation and Language
Machine Learning
Neural and Evolutionary Computing
Chemical Physics
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.
title LLM-Augmented Chemical Synthesis and Design Decision Programs
topic Artificial Intelligence
Computation and Language
Machine Learning
Neural and Evolutionary Computing
Chemical Physics
url https://arxiv.org/abs/2505.07027