Prediction of Multicomponent Reaction Yields Using Machine Learning,Chinese Journal of Chemistry

当前位置： X-MOL 学术 › Chin. J. Chem. › 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.)

Prediction of Multicomponent Reaction Yields Using Machine Learning
Chinese Journal of Chemistry ( IF 5.5 ) Pub Date : 2021-08-04 , DOI: 10.1002/cjoc.202100434
Xing‐Yong Zhu ₁ , Chuan‐Kun Ran ₁ , Ming Wen ₁ , Gui‐Ling Guo ₁ , Yuan Liu ₁ , Li‐Li Liao ₁ , Yi‐Zhou Li ₂ , Meng‐Long Li ₁ , Da‐Gang Yu _{1,

3}

Affiliation

Prediction of reaction yields using machine learning (ML) can help chemists select high-yielding reactions and provide prior experience before wet-lab experimenting to improve efficiency. However, the exploration of a multicomponent organic reaction features many complex variables and limited number of experimental data, which are challenging for the application of ML. Herein, we perform yield prediction for the synthesis of 2-oxazolidones via Cu-catalyzed radical-type oxy-alkylation of allylamines and herteroarylmethylamines with CO₂, which is a three-component reaction. Using physicochemical descriptors as features to launch ML modelling, we find that XGBoost shows significantly improved performance over linear models and these features are effective for the yield prediction. Moreover, out-of-sample prediction indicates the application potential of the model. This study demonstrates great potential of regression-modelling-based ML in organic synthesis even with complex factors and a general small size of reaction data, which are generated from the classical research pattern of method for the inquiry of multicomponent reactions.

中文翻译：

使用机器学习预测多组分反应产率

使用机器学习 (ML) 预测反应产率可以帮助化学家选择高产率反应，并在湿实验室实验之前提供先前的经验以提高效率。然而，多组分有机反应的探索具有许多复杂的变量和有限的实验数据，这对机器学习的应用具有挑战性。在此，我们通过铜催化的烯丙胺和杂芳基甲基胺与 CO _{2 的}自由基型氧烷基化反应合成 2-恶唑烷酮的产率预测，这是一个三组分反应。使用物理化学描述符作为启动 ML 建模的特征，我们发现 XGBoost 显示出比线性模型显着提高的性能，并且这些特征对于产量预测是有效的。此外，样本外预测表明了该模型的应用潜力。这项研究证明了基于回归建模的 ML 在有机合成中的巨大潜力，即使是复杂的因素和一般小规模的反应数据，这些都是从多组分反应的研究方法的经典研究模式中产生的。

更新日期：2021-08-04

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11