无需模板的分子逆合成预测，用图信息增强Transformer
Template-Free Retrosynthesis with Graph-Prior Augmented Transformers
- 将分子图结构注入注意力机制，融合SMILES序列与化学结构特征
- 在USPTO-50K上达到当前无模板方法最优，显著优于基础Transformer
- 适合需要高精度逆合成规划的药物研发人员
逆合成反应预测旨在为给定产物推断合理的反应物分子，是计算机辅助有机合成中的关键问题。尽管近期取得进展，现有模型仍难以满足实际部署所需的准确性和鲁棒性。本文提出一种无模板的Transformer框架，摒弃手工设计的反应模板或额外化学规则引擎。模型通过将分子图信息注入注意力机制，联合利用SMILES序列与结构线索，并采用配对数据增强策略提升训练多样性与规模。在USPTO-50K基准上的大量实验表明，该方法在无模板方法中达到最先进性能，显著优于基线Transformer模型。
原文摘要 · Abstract (English)
Retrosynthesis reaction prediction aims to infer plausible reactant molecules for a given product and is a important problem in computer-aided organic synthesis. Despite recent progress, many existing models still fall short of the accuracy and robustness required for practical deployment. In this paper, we present a template-free, Transformer-based framework that removes the need for handcrafted reaction templates or additional chemical rule engines. Our model injects molecular graph information into the attention mechanism to jointly exploit SMILES sequences and structural cues, and further applies a paired data augmentation strategy to enhance training diversity and scale. Extensive experiments on the USPTO-50K benchmark demonstrate that our approach achieves state-of-the-art performance among template-free methods and substantially outperforms a vanilla Transformer baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。