arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04580cs.LG
收藏

超越主要产物预测:利用在大规模机理数据集上训练的机器学习模型复现反应机理

Beyond Major Product Prediction: Reproducing Reaction Mechanisms with Machine Learning Models Trained on a Large-Scale Mechanistic Dataset

Massachusetts Institute of Technology(麻省理工学院)

Joonyoung F. Joung, Mun Hong Fong, Jihye Roh, Zhengkai Tu, John Bradshaw, Connor W. Coley

AI总结:

本研究构建了含518万余基元步骤的大规模有机反应机理数据集,训练机器学习模型实现反应路径预测等功能,展现杂质预测潜力,同时指出模型泛化面临的相关挑战。

摘要:

对有机反应的机理性理解可推动反应开发、杂质预测,且原则上有助于反应发现。尽管已有多个机器学习模型尝试解决反应产物预测任务,但由于缺乏相应的机理数据集,将其扩展至反应机理预测的工作一直受阻。本研究中,我们利用专家反应模板补全实验报道的反应物与产物之间的中间体,构建了这样一个数据集,并在包含5,184,184个基元步骤的所得数据集上训练了多个机器学习模型。我们探究了这些模型的性能与能力,重点关注其预测反应路径、重现催化剂与试剂作用的能力。此外,我们展示了机理模型在预测常被传统模型忽略的杂质方面的潜力。最后,我们评估了机理模型对新反应类型的泛化能力,揭示了与数据集多样性、连续预测及原子守恒违反相关的挑战。

英文摘要:

Mechanistic understanding of organic reactions can facilitate reaction development, impurity prediction, and in principle, reaction discovery. While several machine learning models have sought to address the task of predicting reaction products, their extension to predicting reaction mechanisms has been impeded by the lack of a corresponding mechanistic dataset. In this study, we construct such a dataset by imputing intermediates between experimentally reported reactants and products using expert reaction templates and train several machine learning models on the resulting dataset of 5,184,184 elementary steps. We explore the performance and capabilities of these models, focusing on their ability to predict reaction pathways and recapitulate the roles of catalysts and reagents. Additionally, we demonstrate the potential of mechanistic models in predicting impurities, often overlooked by conventional models. We conclude by evaluating the generalizability of mechanistic models to new reaction types, revealing challenges related to dataset diversity, consecutive predictions, and violations of atom conservation.

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。

↑