Calculation of Formation Energies of Ligand Protected Gold Nanoclusters

The stability of gold nanocluster, which is modulated by different ligands and doped metal atoms, is a prerequisite for the potential applications in materials, catalysis, sensors, bio-imaging, and therapy. For screening out the stable candidates from the complex combination space formed by different metal cores and ligands, it is crucial to predict the stability of the Au nanoclusters before the synthesis in experiment. A formation energy dataset is established for various Au nanocluster structures (including 21 different core sizes, 22 kinds of ligands, 7 kinds of doped metal atoms) using density functional theory (DFT) calculations. A deep learning model, graph convolutional neural network is able to achieve good performance for formation energy predictions. The applicability is further demonstrated by using some external test sets including the synthesized nanoclusters of particular interest due to their responsiveness to stimuli and biocompatibility. The oil-water partition coefficient of ligand has great influence in the solubility of Au clusters and cell activity. The predictive model also guided the successful synthesis of some novel structures, e.g., Au10(PPh3)7Cl3 and Au38OT24 (OT = octane-1-thiol), with the predicted formation energies close to those known nanoclusters. The proposed machine learning scheme holds promise in facilitating the high-throughput discovery and synthesis of nanoclusters in experiment.