Some of the well-known drawbacks of clinically approved Pt^II complexes can be overcome using six-coordinate Pt^IV complexes as inert prodrugs, which release the corresponding four-coordinate active Pt^II species upon reduction by cellular reducing agents. Therefore, the key factor of Pt^IV prodrug mechanism of action is their tendency to be reduced which, when the involved mechanism is of outer-sphere type, is measured by the value of the reduction potential. Machine learning (ML) models can be used to effectively capture intricate relationships within Pt^IV complex data, leading to highly accurate predictions of reduction potentials and other properties, and offering significant insights into their electrochemical behavior and potential applications. In this study, a machine learning-based approach for predicting the reduction potentials of Pt^IV complexes based on relevant molecular descriptors is presented. Leveraging a data set of experimentally determined reduction potentials and a diverse range of molecular descriptors, the proposed model demonstrates remarkable predictive accuracy (MSE = 0.016 V², RMSE = 0.13 V, R² = 0.92). Ab initio calculations and a set of different machine learning algorithms and feature engineering techniques have been employed to systematically explore the relationship between molecular structure and similarity and reduction potential. Specifically, it has been investigated whether the reduction potential of these compounds can be described by combining ML models across different combinations of constitutional, topological, and electronic molecular descriptors. Our results not only provide insights into the crucial factors influencing reduction potentials but also offer a rapid and effective tool for the rational design of Pt^IV complexes with tailored electrochemical properties for pharmaceutical applications. This approach has the potential to significantly expedite the development and screening of novel Pt^IV prodrug candidates. The analysis of principal components and key features extracted from the model highlights the significance of structural descriptors of the 2D Atom Pairs type and the lowest unoccupied molecular orbital energy. Specifically, with just 20 appropriately selected descriptors, a notable separation of complexes based on their reduction potential value is achieved.

中文翻译：

---

基于机器学习的 PtIV 复合物还原潜力预测

^{临床批准的 Pt II}复合物的一些众所周知的缺点可以使用六配位 Pt ^IV复合物作为惰性前药来克服，该复合物在被细胞还原剂还原后释放相应的四配位活性 Pt ^{II物质。因此，Pt IV}前药作用机制的关键因素是它们的还原倾向，当涉及的机制是外球型时，通过还原电位的值来测量。机器学习 (ML) 模型可用于有效捕获 Pt ^IV复杂数据中的复杂关系，从而对还原电位和其他特性进行高度准确的预测，并提供对其电化学行为和潜在应用的重要见解。在这项研究中，提出了一种基于机器学习的方法，用于根据相关分子描述符预测 Pt ^IV复合物的还原电位。利用实验确定的还原电位数据集和各种分子描述符，所提出的模型表现出显着的预测准确性（MSE = 0.016 V ²，RMSE = 0.13 V，R ² = 0.92）。采用从头计算以及一组不同的机器学习算法和特征工程技术来系统地探索分子结构与相似性和还原潜力之间的关系。具体来说，已经研究了是否可以通过组合跨结构、拓扑和电子分子描述符的不同组合的 ML 模型来描述这些化合物的还原潜力。我们的结果不仅提供了对影响还原电位的关键因素的见解，而且还为合理设计具有适合制药应用的电化学特性的 Pt ^IV配合物提供了快速有效的工具。这种方法有可能显着加快新型 Pt ^IV前药候选物的开发和筛选。对模型中提取的主成分和关键特征的分析突出了二维原子对类型和最低未占据分子轨道能量的结构描述符的重要性。具体来说，仅使用 20 个适当选择的描述符，就可以根据复合物的还原潜力值实现复合物的显着分离。