Abiotic Reduction of Organic and Inorganic Compounds by Fe(II)-Associated Reductants: Comprehensive Data Sets and Machine Learning Modeling
Abiotic Reduction of Organic and Inorganic Compounds by Fe(II)-Associated Reductants: Comprehensive Data Sets and Machine Learning Modeling
复制标题
Fe(II) 相关还原剂对有机和无机化合物的非生物还原：综合数据集和机器学习建模
DOI：
10.1021/acs.est.2c09724
复制
发表时间：
2023
影响因子：
11.4
通讯作者：
Zhang, Huichun
中科院分区：
文献类型：
--
作者：
Gao, Yidan;Zhong, Shifa;Zhang, Kai;Zhang, Huichun
铁缔合还原剂在为各种还原转化提供电子方面发挥着至关重要的作用。然而，开发可靠的预测工具来估计此类系统中的非生物还原率常数 (logk) 一直受到这些系统复杂性的阻碍。我们最近的研究开发了一种基于 60 种有机化合物对一种可溶性 Fe(II) 还原剂的机器学习 (ML) 模型。在这项研究中，我们建立了一个全面的动力学数据集，涵盖 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。针对有机和无机化合物开发了单独的 ML 模型，特征重要性分析证明了共振结构、可还原官能团、还原剂描述符和 pH 在 logk 预测中的重要性。机理解释验证了该模型准确地了解了各种因素的影响，例如芳香族取代基、络合、键解离能、还原势、LUMO 能量和主要还原剂种类。最后，我们发现分布式结构可搜索毒性（DSSTox）数据库中的 850,000 种化合物中有 38% 至少包含一个可还原官能团，并且可以使用我们的模型合理预测 285,184 种化合物的 logkof。总体而言，这项研究是朝着可靠的预测工具迈出的重要一步，该工具可用于预测铁相关还原剂系统中的非生物还原速率常数。
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 (logk) 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 logkprediction. 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 logkof 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.