Machine Learning for Screening Large Organic Molecules

TL;DR

This paper introduces a machine learning model that accurately predicts HOMO and LUMO energies of organic molecules, including larger structures, to accelerate the discovery of materials for organic electronics.

Contribution

It develops an advanced ML model with Set2Set readout, extends training to larger molecules, and employs a multitask approach for different theoretical levels, achieving near chemical accuracy.

Findings

Model predicts HOMO/LUMO energies with high accuracy

Inclusion of larger molecules improves model generalization

Multitask training handles different theoretical sources effectively

Abstract

Organic semiconductors are promising materials for cheap, scalable and sustainable electronics, light-emitting diodes and photovoltaics. For organic photovoltaic cells, it is a challenge to find compounds with suitable properties in the vast chemical compound space. For example, the ionization energy should fit to the optical spectrum of sun light, and the energy levels must allow efficient charge transport. Here, a machine-learning model is developed for rapidly and accurately estimating the HOMO and LUMO energies of a given molecular structure. It is build upon the SchNet model (Sch\"utt et al. (2018)) and augmented with a `Set2Set' readout module (Vinyals et al. (2016)). The Set2Set module has more expressive power than sum and average aggregation and is more suitable for the complex quantities under consideration. Most previous models have been trained and evaluated on rather small molecules. Therefore, the second contribution is extending the scope of machine-learning methods by adding also larger molecules from other sources and establishing a consistent train/validation/test split. As a third contribution, we make a multitask ansatz to resolve the problem of different sources coming at different levels of theory. All three contributions in conjunction bring the accuracy of the model close to chemical accuracy.