Towards efficient discovery of green synthetic pathways with Monte Carlo tree search and reinforcement learning,Chemical Science

当前位置： X-MOL 学术 › Chem. Sci. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Towards efficient discovery of green synthetic pathways with Monte Carlo tree search and reinforcement learning
Chemical Science ( IF 7.6 ) Pub Date : 2020-09-14 , DOI: 10.1039/d0sc04184j
Xiaoxue Wang _{1,

2} , Yujie Qian ₃ , Hanyu Gao ₁ , Connor W Coley ₁ , Yiming Mo ₁ , Regina Barzilay ₃ , Klavs F Jensen ₁

Affiliation

Computer aided synthesis planning of synthetic pathways with green process conditions has become of increasing importance in organic chemistry, but the large search space inherent in synthesis planning and the difficulty in predicting reaction conditions make it a significant challenge. We introduce a new Monte Carlo Tree Search (MCTS) variant that promotes balance between exploration and exploitation across the synthesis space. Together with a value network trained from reinforcement learning and a solvent-prediction neural network, our algorithm is comparable to the best MCTS variant (PUCT, similar to Google's Alpha Go) in finding valid synthesis pathways within a fixed searching time, and superior in identifying shorter routes with greener solvents under the same search conditions. In addition, with the same root compound visit count, our algorithm outperforms the PUCT MCTS by 16% in terms of determining successful routes. Overall the success rate is improved by 19.7% compared to the upper confidence bound applied to trees (UCT) MCTS method. Moreover, we improve 71.4% of the routes proposed by the PUCT MCTS variant in pathway length and choices of green solvents. The approach generally enables including Green Chemistry considerations in computer aided synthesis planning with potential applications in process development for fine chemicals or pharmaceuticals.

中文翻译：

通过蒙特卡罗树搜索和强化学习有效发现绿色合成途径

具有绿色工艺条件的合成途径的计算机辅助合成规划在有机化学中变得越来越重要，但合成规划固有的巨大搜索空间和预测反应条件的困难使其成为重大挑战。我们引入了一种新的蒙特卡罗树搜索（MCTS）变体，可以促进整个合成空间中探索和利用之间的平衡。结合强化学习训练的价值网络和溶剂预测神经网络，我们的算法在固定搜索时间内找到有效合成路径方面可与最佳 MCTS 变体（PUCT，类似于 Google 的 Alpha Go）相媲美，并且在识别方面更胜一筹在相同的搜索条件下，使用更环保的溶剂可以缩短路线。此外，在相同的根化合物访问计数的情况下，我们的算法在确定成功路线方面比 PUCT MCTS 提高了 16%。总体而言，与应用于树 (UCT) MCTS 方法的置信上限相比，成功率提高了 19.7%。此外，我们在路径长度和绿色溶剂的选择方面改进了 PUCT MCTS 变体提出的路线的 71.4%。该方法通常能够将绿色化学考虑因素纳入计算机辅助合成规划中，并在精细化学品或药品的工艺开发中具有潜在的应用。

更新日期：2020-09-22

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11