Data-driven, efficient synthesis of metal complexes for imaging and drug discovery

金属配合物在传感、成像、催化和药物开发等方面有着重要的应用。金属配合物的一个吸引人的特点是，通过改变金属的氧化态以及配体的数量和性质，它们的性质可以很容易地根据给定的应用进行调整。然而，其中一些配合物的合成及其性质的预测往往具有挑战性。该项目将探索使用高通量合成方法，结合深入的数据分析和机械机器学习，以优化具有定制性能的新型金属配合物的合成。该项目将首先专注于合成具有不同光学和氧化还原特性的铂配合物库，这些配合物作为“智能”抗癌剂、成像光学探针和检测有毒物种的可切换化学传感器具有很大的兴趣。在这个项目中工作的学生将学习和应用最先进的合成化学和原位表征技术，结合深入的数据分析和机器学习推理方法，制备具有独特特性的新型金属配合物。

Metal complexes have several important applications in sensing, imaging, catalysis and drug development. One of the attractive features of metal complexes is that their properties can be readily tuned for a given application by changing the oxidation state of the metal as well as the number and nature of the coordinated ligands. However, the synthesis of some of these complexes and the prediction of their properties is often challenging. This project will explore the use of high-throughput synthetic methods coupled with in-depth data analysis and mechanistic machine learning to optimise the synthesis of new metal complexes with tailored properties. The project will start by focusing on the synthesis of a library of platinum complexes with different optical and redox properties, which are of great interest as 'smart' anticancer agents, optical probes for imaging, and switchable chemical sensors to detect toxic species. The student working in this project will learn and apply state-of-the art synthetic chemistry and in situ characterisation techniques, linked with in-depth data analytics and machine learning inference methods to prepare novel metal complexes with uniquely tailored properties.