Automatic Screen-out of Ir(III) Complex Emitters by Combined Machine Learning and Computational Analysis

Abstract

The organic light-emitting diode (OLED) has gained widespread commercial use, yet there is a continuous need to identify innovative emitters that offer higher efficiency and a broader color gamut. To effectively screen out promising OLED molecules that are yet to be synthesized, representation learning aided high throughput virtual screening (HTVS) over millions of Ir(III) complexes, which are prototypical types of phosphorescent OLED material constructed via a random combination of 278 reported ligands. This study successfully screens out a decent amount of promising candidates for both display and lighting purposes, which are worth further experimental investigation. The high efficiency and accuracy of this model are largely attributed to the pioneering attempt of using representation learning to organic luminescent molecules, which is initiated by a pre-training procedure with over 1.6 million 3D molecular structures and frontier orbital energies predicted via semi-empirical methods, followed by a fine-tuning scheme via the quantum mechanical computed properties over around 1500 candidates. Such workflow enables an effective model construction process that is otherwise hindered by the scarcity of labeled data and can be straightforwardly extended to the discovery of other novel materials.