Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xuan-Vu, Nguyen, Armstrong, Daniel P, Jončev, Zlatko, Schwaller, Philippe
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.21762
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911083481006080
author Xuan-Vu, Nguyen
Armstrong, Daniel P
Jončev, Zlatko
Schwaller, Philippe
author_facet Xuan-Vu, Nguyen
Armstrong, Daniel P
Jončev, Zlatko
Schwaller, Philippe
contents Retrosynthesis planning remains a central challenge in molecular discovery due to the vast and complex chemical reaction space. While traditional template-based methods offer tractability, they suffer from poor scalability and limited generalization, and template-free generative approaches risk generating invalid reactions. In this work, we propose TempRe, a generative framework that reformulates template-based approaches as sequence generation, enabling scalable, flexible, and chemically plausible retrosynthesis. We evaluated TempRe across single-step and multi-step retrosynthesis tasks, demonstrating its superiority over both template classification and SMILES-based generation methods. On the PaRoutes multi-step benchmark, TempRe achieves strong top-k route accuracy. Furthermore, we extend TempRe to direct multi-step synthesis route generation, providing a lightweight and efficient alternative to conventional single-step and search-based approaches. These results highlight the potential of template generative modeling as a powerful paradigm in computer-aided synthesis planning.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TempRe: Template generation for single and direct multi-step retrosynthesis
Xuan-Vu, Nguyen
Armstrong, Daniel P
Jončev, Zlatko
Schwaller, Philippe
Machine Learning
Retrosynthesis planning remains a central challenge in molecular discovery due to the vast and complex chemical reaction space. While traditional template-based methods offer tractability, they suffer from poor scalability and limited generalization, and template-free generative approaches risk generating invalid reactions. In this work, we propose TempRe, a generative framework that reformulates template-based approaches as sequence generation, enabling scalable, flexible, and chemically plausible retrosynthesis. We evaluated TempRe across single-step and multi-step retrosynthesis tasks, demonstrating its superiority over both template classification and SMILES-based generation methods. On the PaRoutes multi-step benchmark, TempRe achieves strong top-k route accuracy. Furthermore, we extend TempRe to direct multi-step synthesis route generation, providing a lightweight and efficient alternative to conventional single-step and search-based approaches. These results highlight the potential of template generative modeling as a powerful paradigm in computer-aided synthesis planning.
title TempRe: Template generation for single and direct multi-step retrosynthesis
topic Machine Learning
url https://arxiv.org/abs/2507.21762