PoroNet: An Intrinsically Interpretable Pore Graph Neural Network for Resolving Pore-Level Adsorption in Metal–Organic Frameworks
Journal of Chemical Theory and Computation · 09.06.2026 · 22 (11) · 5716-5730
DOI: 10.1021/acs.jctc.6c00100 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 29.05.2026. Verfasst von Chao Zheng und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biological Engineering, University at Buffalo, The State University of New York, Buffalo, New York 14260, United States. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: American Chemical Society Petroleum Research Fund.
Abstract (Originalsprache)
Machine learning (ML) models have been widely used as efficient surrogates to predict adsorption in metal-organic frameworks (MOFs) for gas storage, chemical separations, and catalysis applications. The "black box" nature of these ML models, however, remains a significant barrier between predictions and the design of novel MOFs. In this work, we introduce PoroNet, an intrinsically interpretable graph neural network architecture built on a graph representation of the pore network (i.e., pore graph). In a pore graph, nodes represent individual pores, and edges represent pore connections. PoroNet shows highly accurate predictions of hydrogen (H2) uptake and deliverable capacity in MOFs, as well as on a benchmark simulated adsorption data set that contains spherical and linear alkane adsorbates. More importantly, accurate pore-level contributions to total adsorption can be learned using PoroNet either through direct supervised learning or as latent representations while fitting the total adsorption capacity. In direct supervised learning with explicit pore-level labels, we show that the PoroNet architecture is data-efficient, achieving comparable performance to the standard approach with only a fraction of simulation runs needed for model training. The pore-level contribution helps interpret the ML predictions of the total adsorption behavior, identify the key pore properties that govern the adsorption, and provide significant insights into pore engineering. We demonstrate that PoroNet is a powerful tool for high-throughput pore screening and for deriving valuable MOF design rules for cryogenic H2 storage applications. Lastly, we discuss the potential of leveraging interpretable ML for scalable scientific and material discovery.
Autor:innen und Institutionen
- Department of Chemical and Biological Engineering, University at Buffalo, The State University of New York, Buffalo, New York 14260, United States.
ORCID-Profile: Chao Zheng, Kaihang Shi
Förderung
- American Chemical Society Petroleum Research Fund
Zitieren
APA
Zheng, C., Gopalan, A., & Shi, K. (2026). PoroNet: An Intrinsically Interpretable Pore Graph Neural Network for Resolving Pore-Level Adsorption in Metal–Organic Frameworks. Journal of Chemical Theory and Computation, 22(11), 5716-5730. https://doi.org/10.1021/acs.jctc.6c00100
Vancouver
Zheng C, Gopalan A, Shi K. PoroNet: An Intrinsically Interpretable Pore Graph Neural Network for Resolving Pore-Level Adsorption in Metal–Organic Frameworks. Journal of Chemical Theory and Computation. 2026;22(11):5716-5730. doi:10.1021/acs.jctc.6c00100
BibTeX
@article{Zheng2026,
author = {Zheng, Chao and Gopalan, Arun and Shi, Kaihang},
title = {PoroNet: An Intrinsically Interpretable Pore Graph Neural Network for Resolving Pore-Level Adsorption in Metal–Organic Frameworks},
journal = {Journal of Chemical Theory and Computation},
year = {2026},
volume = {22},
number = {11},
pages = {5716--5730},
doi = {10.1021/acs.jctc.6c00100}
}
EUVIMED