TempRe: Template generation for single and direct multi-step retrosynthesis
- URL: http://arxiv.org/abs/2507.21762v2
- Date: Wed, 30 Jul 2025 11:59:42 GMT
- Title: TempRe: Template generation for single and direct multi-step retrosynthesis
- Authors: Nguyen Xuan-Vu, Daniel P Armstrong, Zlatko JonĨev, Philippe Schwaller,
- Abstract summary: Retrosynthesis is a central challenge in molecular discovery due to the vast and complex chemical reaction space.<n>Traditional template-based methods offer tractability, but they suffer from poor scalability and limited generalization.<n>We propose TempRe, a generative framework that reformulates template-based approaches as sequence generation.
- Score: 0.32883397652681257
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: 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.
Related papers
- DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning [0.0]
DeepRetro is an open-source, iterative, hybrid LLM-based retrosynthetic framework.<n>Our approach integrates the strengths of conventional template-based/Monte Carlo tree search tools with the generative power of LLMs in a step-wise, feedback-driven loop.<n>This approach successfully generates novel pathways for complex natural product compounds.
arXiv Detail & Related papers (2025-07-07T19:41:39Z) - One Step Diffusion via Shortcut Models [109.72495454280627]
We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples.<n>Shortcut models condition the network on the current noise level and also on the desired step size, allowing the model to skip ahead in the generation process.<n>Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
arXiv Detail & Related papers (2024-10-16T13:34:40Z) - UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment [51.49238426241974]
This paper introduces UAlign, a template-free graph-to-sequence pipeline for retrosynthesis prediction.
By combining graph neural networks and Transformers, our method can more effectively leverage the inherent graph structure of molecules.
arXiv Detail & Related papers (2024-03-25T03:23:03Z) - A Quality-based Syntactic Template Retriever for
Syntactically-controlled Paraphrase Generation [67.98367574025797]
Existing syntactically-controlled paraphrase generation models perform promisingly with human-annotated or well-chosen syntactic templates.
The prohibitive cost makes it unfeasible to manually design decent templates for every source sentence.
We propose a novel Quality-based Syntactic Template Retriever (QSTR) to retrieve templates based on the quality of the to-be-generated paraphrases.
arXiv Detail & Related papers (2023-10-20T03:55:39Z) - RetroBridge: Modeling Retrosynthesis with Markov Bridges [2.256703675017117]
Retrosynthesis planning aims at designing reaction pathways from commercially available starting materials to a target molecule.
We introduce the Markov Bridge Model, a generative framework aimed to approximate the dependency between two discrete distributions.
We then address the retrosynthesis planning problem with our novel framework and introduce RetroBridge, a template-free retrosynthesis modeling approach.
arXiv Detail & Related papers (2023-08-30T15:09:22Z) - Mind the Retrosynthesis Gap: Bridging the divide between Single-step and
Multi-step Retrosynthesis Prediction [0.9134244356393664]
Multi-step approaches repeatedly apply the chemical information stored in single-step retrosynthesis models.
We show that models designed for single-step retrosynthesis, when extended to multi-step, can have a tremendous impact on the route finding capabilities of current multi-step methods.
arXiv Detail & Related papers (2022-12-12T18:06:24Z) - Retrieval-based Controllable Molecule Generation [63.44583084888342]
We propose a new retrieval-based framework for controllable molecule generation.
We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria.
Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
arXiv Detail & Related papers (2022-08-23T17:01:16Z) - RetroComposer: Discovering Novel Reactions by Composing Templates for
Retrosynthesis Prediction [63.14937611038264]
We propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates.
Experimental results show that our method can produce novel templates for 328 test reactions in the USPTO-50K dataset.
arXiv Detail & Related papers (2021-12-20T05:57:07Z) - Multi-span Style Extraction for Generative Reading Comprehension [90.6069071495214]
We propose a new framework which enables generative MRC to be smoothly solved as multi-span extraction.
Thorough experiments demonstrate that this novel approach can alleviate the dilemma between generative models and single-span models.
arXiv Detail & Related papers (2020-09-15T23:06:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.