Message-passing neural networks for high-throughput polymer screening

TL;DR

This paper demonstrates that message-passing neural networks can accurately predict properties of large molecules without requiring costly 3D structural data, enabling efficient high-throughput screening in material discovery.

Contribution

It introduces a new large-scale dataset for organic photovoltaic molecules and shows that 2D-based message-passing neural networks perform comparably to 3D-based models for large molecules.

Findings

Similar accuracy with and without 3D structural info

Large molecules up to 200 atoms included in the dataset

Reduced training data needed for transfer learning

Abstract

Machine learning methods have shown promise in predicting molecular properties, and given sufficient training data machine learning approaches can enable rapid high-throughput virtual screening of large libraries of compounds. Graph-based neural network architectures have emerged in recent years as the most successful approach for predictions based on molecular structure, and have consistently achieved the best performance on benchmark quantum chemical datasets. However, these models have typically required optimized 3D structural information for the molecule to achieve the highest accuracy. These 3D geometries are costly to compute for high levels of theory, limiting the applicability and practicality of machine learning methods in high-throughput screening applications. In this study, we present a new database of candidate molecules for organic photovoltaic applications, comprising approximately 91,000 unique chemical structures.Compared to existing datasets, this dataset contains substantially larger molecules (up to 200 atoms) as well as extrapolated properties for long polymer chains. We show that message-passing neural networks trained with and without 3D structural information for these molecules achieve similar accuracy, comparable to state-of-the-art methods on existing benchmark datasets. These results therefore emphasize that for larger molecules with practical applications, near-optimal prediction results can be obtained without using optimized 3D geometry as an input. We further show that learned molecular representations can be leveraged to reduce the training data required to transfer predictions to a new DFT functional.