arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.10090physics.chem-phcs.AIcs.LG
收藏

ReactAIvate:一种用于预测反应机理并揭示反应活性热点的深度学习方法

ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots

Indian Institute of Technology Bombay(印度理工学院孟买分校);Indian Institute of Technology(印度理工学院);Tata Consultancy Services Research(塔塔咨询服务公司研究院);Centre for Machine Intelligence and Data Science, Indian Institute of Technology Bombay(印度理工学院孟买分校机器智能与数据科学中心)

Ajnabiul Hoque, Manajit Das, Mayank Baranwal, Raghavan B. Sunoj

AI总结:

针对量子力学计算反应机理成本高、相关数据集稀缺的问题,研究构建了7类基元步骤数据集,提出可解释注意力GNN模型ReactAIvate,在反应步骤分类和活性原子预测上表现优异,具备分布外泛化能力,助力新分子反应活性研究。

摘要:

化学反应机理(CRM)是一系列涉及键断裂/形成过程的分子层面事件,在反应物转化为产物的反应路径中会生成瞬态中间体。理解此类机理对于设计和发现新反应至关重要。目前用于探究化学反应机理的方法之一是量子力学(QM)计算。量子力学方法资源消耗大,且基于机理的数据集稀缺,这促使我们开发可靠的机器学习模型来预测反应机理。在本研究中,我们创建了一个包含7个不同类别的综合数据集,每个类别代表具有独特特征的基元步骤。随后,我们开发了一种可解释的基于注意力机制的图神经网络(GNN),该模型在反应步骤分类和每个步骤中反应原子的预测上分别达到了接近1的准确率和96%的准确率,能够捕捉更广泛的反应环境与局部活性区域之间的相互作用。近乎完美的分类效果使得单个反应事件和整个化学反应机理都能被准确预测,缓解了Seq2Seq方法的潜在缺陷——即一个字符预测错误就会导致化学反应机理识别不连贯。除了可解释性,我们的模型甚至能从分布外类别中精准识别关键原子。这种泛化性使得新反应类型可以以模块化方式被纳入,因此对专家理解新分子的反应活性具有价值。

英文摘要:

A chemical reaction mechanism (CRM) is a sequence of molecular-level events involving bond-breaking/forming processes, generating transient intermediates along the reaction pathway as reactants transform into products. Understanding such mechanisms is crucial for designing and discovering new reactions. One of the currently available methods to probe CRMs is quantum mechanical (QM) computations. The resource-intensive nature of QM methods and the scarcity of mechanism-based datasets motivated us to develop reliable ML models for predicting mechanisms. In this study, we created a comprehensive dataset with seven distinct classes, each representing uniquely characterized elementary steps. Subsequently, we developed an interpretable attention-based GNN that achieved near-unity and 96% accuracy, respectively for reaction step classification and the prediction of reactive atoms in each such step, capturing interactions between the broader reaction context and local active regions. The near-perfect classification enables accurate prediction of both individual events and the entire CRM, mitigating potential drawbacks of Seq2Seq approaches, where a wrongly predicted character leads to incoherent CRM identification. In addition to interpretability, our model adeptly identifies key atom(s) even from out-of-distribution classes. This generalizabilty allows for the inclusion of new reaction types in a modular fashion, thus will be of value to experts for understanding the reactivity of new molecules.

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。

↑