Department of Civil and Environmental Engineering, Case Western Reserve University, Cleveland, Ohio 44106, United States.
Environ Sci Technol. 2023 Nov 21;57(46):18026-18037. doi: 10.1021/acs.est.2c09724. Epub 2023 May 17.
Iron-associated reductants play a crucial role in providing electrons for various reductive transformations. However, developing reliable predictive tools for estimating abiotic reduction rate constants (log) in such systems has been impeded by the intricate nature of these systems. Our recent study developed a machine learning (ML) model based on 60 organic compounds toward one soluble Fe(II)-reductant. In this study, we built a comprehensive kinetic data set covering the reactivity of 117 organic and 10 inorganic compounds toward four major types of Fe(II)-associated reductants. Separate ML models were developed for organic and inorganic compounds, and the feature importance analysis demonstrated the significance of resonance structures, reducible functional groups, reductant descriptors, and pH in log prediction. Mechanistic interpretation validated that the models accurately learned the impact of various factors such as aromatic substituents, complexation, bond dissociation energy, reduction potential, LUMO energy, and dominant reductant species. Finally, we found that 38% of the 850,000 compounds in the Distributed Structure-Searchable Toxicity (DSSTox) database contain at least one reducible functional group, and the log of 285,184 compounds could be reasonably predicted using our model. Overall, the study is a significant step toward reliable predictive tools for anticipating abiotic reduction rate constants in iron-associated reductant systems.
铁相关还原剂在为各种还原转化提供电子方面起着至关重要的作用。然而，由于这些系统的复杂性，开发可靠的预测工具来估计此类系统中的非生物还原速率常数（log）一直受到阻碍。我们最近的研究针对一种可溶性 Fe(II)-还原剂，基于 60 种有机化合物开发了一种机器学习 (ML) 模型。在这项研究中，我们建立了一个综合的动力学数据集，涵盖了 117 种有机化合物和 10 种无机化合物对四种主要类型的 Fe(II)相关还原剂的反应性。为有机和无机化合物分别开发了 ML 模型，特征重要性分析表明共振结构、可还原官能团、还原剂描述符和 pH 在 log 预测中的重要性。机理解释验证了模型准确地学习了各种因素的影响，如芳香取代基、络合、键离解能、还原电位、LUMO 能量和主要还原剂种类。最后，我们发现分布结构可搜索毒性 (DSSTox) 数据库中的 850,000 种化合物中有 38%至少含有一个可还原官能团，并且可以使用我们的模型合理地预测 285,184 种化合物的 log 值。总的来说，这项研究是朝着开发可靠的预测工具以预测铁相关还原剂系统中非生物还原速率常数迈出的重要一步。
