E(n) Equivariant Graph Neural Network for Learning Interactional Properties of Molecules

Kieran Nehil-Puleo, Co D. Quach, Nicholas C. Craven, Clare McCabe, Peter T. Cummings

Research output: Contribution to journalArticlepeer-review

15 Downloads (Pure)

Abstract

We have developed a multi-input E(n) equivariant graph convolution-based model designed for the prediction of chemical properties that result from the interaction of heterogeneous molecular structures. By incorporating spatial features and constraining the functions learned from these features to be equivariant to E(n) symmetries, the interactional-equivariant graph neural network (IEGNN) can efficiently learn from the 3D structure of multiple molecules. To verify the IEGNN's capability to learn interactional properties, we tested the model's performance on three molecular data sets, two of which are curated in this study and made publicly available for future interactional model benchmarking. To enable the loading of these data sets, an open-source data structure based on the PyTorch Geometric library for batch loading multigraph data points is also created. Finally, the IEGNN's performance on a data set consisting of an unknown interactional relationship (the frictional properties resulting between monolayers with variable composition) is examined. The IEGNN model developed was found to have the lowest mean absolute percent error for the predicted tribological properties of four of the six data sets when compared to previous methods.

Original languageEnglish
Pages (from-to)1108-1117
Number of pages10
JournalJournal of Physical Chemistry B
Volume128
Issue number4
Early online date17 Jan 2024
DOIs
Publication statusPublished - 1 Feb 2024

Fingerprint

Dive into the research topics of 'E(n) Equivariant Graph Neural Network for Learning Interactional Properties of Molecules'. Together they form a unique fingerprint.

Cite this