arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15820cs.LGcs.AIstat.ML
收藏

Retro*:使用神经引导的A* 搜索学习逆合成规划

Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

Georgia Institute of Technology(佐治亚理工学院);Galixir(星亢原);Google Research(谷歌研究院);Ant Financial(蚂蚁金服)

Binghong Chen, Chengtao Li, Hanjun Dai, Le Song

摘要:

逆合成规划是有机化学中的一项重要任务,它确定了一系列可以导致目标产物合成的反应。大量可能的化学转化使得搜索空间的大小非常大,并且逆合成规划即使对于有经验的化学家也是具有挑战性的。然而,现有的方法要么需要昂贵的回报估计推出高方差,或优化搜索速度,而不是质量。在本文中,我们提出了Retro*,一种基于神经的A* 类算法,可以有效地找到高质量的合成路线。它将搜索保持为AND-OR树,并使用非策略数据学习神经搜索偏差。然后在此神经网络的指导下,在新的规划事件中有效地执行最佳优先搜索。在基准USPTO数据集上的实验表明,我们提出的方法在成功率和解决方案质量方面优于现有的最先进的方法,同时更高效。

英文摘要:

Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possible chemical transformations makes the size of the search space very big, and retrosynthetic planning is challenging even for experienced chemists. However, existing methods either require expensive return estimation by rollout with high variance, or optimize for search speed rather than the quality. In this paper, we propose Retro*, a neural-based A*-like algorithm that finds high-quality synthetic routes efficiently. It maintains the search as an AND-OR tree, and learns a neural search bias with off-policy data. Then guided by this neural network, it performs best-first search efficiently during new planning episodes. Experiments on benchmark USPTO datasets show that, our proposed method outperforms existing state-of-the-art with respect to both the success rate and solution quality, while being more efficient at the same time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑