Coarse-Grained Crystal Graph Neural Networks for Reticular Materials Design

Reticular materials, including metal–organic frameworks and covalent organic frameworks, combine the relative ease of synthesis and an impressive range of applications in various fields from gas storage to biomedicine. Diverse properties arise from the variation of building unitsmetal centers and o...

Full description

Saved in:
Bibliographic Details
Published in:Journal of chemical information and modeling 2024-03, Vol.64 (6), p.1919-1931
Main Authors: Korolev, Vadim, Mitrofanov, Artem
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computing costs
Design of experiments
Graph neural networks
Inverse design
Machine Learning and Deep Learning
Message passing
Metal-Organic Frameworks
Network topologies
Neural networks
Neural Networks, Computer
Performance prediction
Pipeline design
Research Design
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reticular materials, including metal–organic frameworks and covalent organic frameworks, combine the relative ease of synthesis and an impressive range of applications in various fields from gas storage to biomedicine. Diverse properties arise from the variation of building unitsmetal centers and organic linkersin almost infinite chemical space. Such variation substantially complicates the experimental design and promotes the use of computational methods. In particular, the most successful artificial intelligence algorithms for predicting the properties of reticular materials are atomic-level graph neural networks, which optionally incorporate domain knowledge. Nonetheless, the data-driven inverse design involving these models suffers from the incorporation of irrelevant and redundant features such as a full atomistic graph and network topology. In this study, we propose a new way of representing materials, aiming to overcome the limitations of existing methods; the message passing is performed on a coarse-grained crystal graph that comprises molecular building units. To highlight the merits of our approach, we assessed the predictive performance and energy efficiency of neural networks built on different materials representations, including composition-based and crystal-structure-aware models. Coarse-grained crystal graph neural networks showed decent accuracy at low computational costs, making them a valuable alternative to omnipresent atomic-level algorithms. Moreover, the presented models can be successfully integrated into an inverse materials design pipeline as estimators of the objective function. Overall, the coarse-grained crystal graph framework is aimed at challenging the prevailing atom-centric perspective on reticular materials design.
ISSN:1549-9596
1549-960X
1549-960X
DOI:10.1021/acs.jcim.3c02083