Message-Passing Neural Networks for High-Throughput Polymer Screening

Peter St. John, Caleb Phillips, Nolan Wilson, Michael Crowley, Mark Nimlos, Ross Larsen, Yanfei Guan, Travis Kemper

Research output: Contribution to journalArticlepeer-review

68 Scopus Citations


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 density functional theory functional.

Original languageAmerican English
Article number234111
Number of pages7
JournalThe Journal of Chemical Physics
Issue number23
StatePublished - 21 Jun 2019

Bibliographical note

Publisher Copyright:
© 2019 Author(s).

NREL Publication Number

  • NREL/JA-2700-74021


  • artificial neural networks
  • chemical compounds and components
  • isomerism
  • machine learning
  • molecular properties
  • optoelectronic properties
  • photovoltaics
  • regression analysis


Dive into the research topics of 'Message-Passing Neural Networks for High-Throughput Polymer Screening'. Together they form a unique fingerprint.

Cite this