通过蒸学习增强回复合成预测
Yiping Liu1,2, Zhou Yu1, Jiayi Zhang1
1College of Computer Science and Electronic Engineering, Hunan University, Changsha 410023 Hunan, PR China.
Journal of chemical information and modeling
|March 16, 2026
概括
我们开发了两种新的蒸学习策略,即逆合成互蒸 (Retro-MD) 和逆合成自蒸 (Retro-SD),以提高所有反应类的单步逆合成预测准确度.
科学领域:
- 计算化学计算化学
- 机器学习在化学中的应用
- 合成化学 合成化学
背景情况:
- 预测单步逆合成对于化学合成路径规划至关重要.
- 目前的方法在高资源和低资源反应类之间存在性能差距,限制了整体有效性.
- 解决这些差异对于推进自动化合成设计至关重要.
研究的目的:
- 引入新的蒸学习策略,以减轻反合成预测中的性能差异.
- 为了提高无模板回复合成预测模型的准确性和稳定性.
- 改进各种化学反应类别的预测模型的通用性.
主要方法:
- 开发了使用双采样温度和跨模型知识转移的复合互蒸 (Retro-MD).
- 开发了使用固定温度和代自蒸的复合自蒸 (Retro-SD).
- 将这些策略应用于基于变压器的模型,以预测无模板的回复合成.
主要成果:
- 在没有模板的回复合成预测方法中实现了最先进的性能.
- 在预测准确度方面取得了显著的改进,特别是对于低资源反应类.
- 废弃性研究证实了反应类意识任务分区的有效性.
结论:
- 复古MD和复古SD有效地弥合了回复合成预测中的性能差距.
- 蒸学习提供了一种强大的方法来增强化学反应预测模型.
- 提出的方法提升了自动回复合成和途径规划的能力.
相关概念视频
Distillation: Vapor–Liquid Equilibria
5.0K
Distillation is a separation technique that takes advantage of the boiling point properties of disparate elements in a mixture. To perform distillation, we begin by heating a miscible mixture of two liquids with a significant difference in boiling points (at least 20°C). As the solution heats up and reaches the bubble point of the more volatile component, some molecules of the more volatile component transition into the gas phase and travel upward into the condenser, which is a glass tube...
5.0K
Predicting Reaction Outcomes
11.3K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
11.3K


