用检索+隐式提取，让AI更聪明地设计无机物合成路径。
Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
- 从知识库检索相似材料，用注意力机制隐式提取前驱体信息
- 考虑目标物与前驱体的热力学关系，提升预测准确率
- 擅长发现新合成路径，适合材料研发人员使用
无机逆合成规划在化学科学中至关重要，但相比有机逆合成，机器学习应用仍相对不足。本文提出 Retrieval-Retro 模型，通过从知识库中检索参考材料并隐式提取其前驱体信息，实现无机逆合成规划。不同于直接使用参考材料的前驱体数据，该模型采用多层注意力机制，使模型能更有效学习新的合成路径。此外，在检索过程中引入目标材料与前驱体之间的热力学关系，体现领域专家知识，有助于在多种可能组合中识别最合理的前驱体集合。大量实验表明，Retrieval-Retro 在逆合成规划中表现优异，尤其在发现新型合成路径方面具有显著优势，对材料发现至关重要。代码已公开于 https://github.com/HeewoongNoh/Retrieval-Retro。
原文摘要 · Abstract (English)
While inorganic retrosynthesis planning is essential in the field of chemical science, the application of machine learning in this area has been notably less explored compared to organic retrosynthesis planning. In this paper, we propose Retrieval-Retro for inorganic retrosynthesis planning, which implicitly extracts the precursor information of reference materials that are retrieved from the knowledge base regarding domain expertise in the field. Specifically, instead of directly employing the precursor information of reference materials, we propose implicitly extracting it with various attention layers, which enables the model to learn novel synthesis recipes more effectively. Moreover, during retrieval, we consider the thermodynamic relationship between target material and precursors, which is essential domain expertise in identifying the most probable precursor set among various options. Extensive experiments demonstrate the superiority of Retrieval-Retro in retrosynthesis planning, especially in discovering novel synthesis recipes, which is crucial for materials discovery. The source code for Retrieval-Retro is available at https://github.com/HeewoongNoh/Retrieval-Retro.
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。