Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Crystal Field Theory - Octahedral Complexes02:58

Crystal Field Theory - Octahedral Complexes

26.3K
Crystal Field Theory
To explain the observed behavior of transition metal complexes (such as colors), a model involving electrostatic interactions between the electrons from the ligands and the electrons in the unhybridized d orbitals of the central metal atom has been developed. This electrostatic model is crystal field theory (CFT). It helps to understand, interpret, and predict the colors, magnetic behavior, and some structures of coordination compounds of transition metals.
CFT focuses on...
26.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Data-driven prediction of ionic conductivity in solid-state electrolytes with machine learning and large language models.

The Journal of chemical physics·2026
Same author

A Master Isotherm Model Approach to Quantify Defects in UiO-66 from Nitrogen Adsorption Isotherms.

Langmuir : the ACS journal of surfaces and colloids·2025
Same author

MOFClassifier: A Machine Learning Approach for Validating Computation-Ready Metal-Organic Frameworks.

Journal of the American Chemical Society·2025
Same author

Correction to "Leveraging Machine Learning To Predict the Atmospheric Lifetime and the Global Warming Potential of SF6 Replacement Gases".

The journal of physical chemistry. A·2025
Same author

Computational Exploration of Adsorption-Based Hydrogen Storage in Mg-Alkoxide Functionalized Covalent-Organic Frameworks (COFs): Force-Field and Machine Learning Models.

ACS applied materials & interfaces·2024
Same author

Correction to "PACMAN: A Robust Partial Atomic Charge Predicter for Nanoporous Materials Based on Crystal Graph Convolution Networks".

Journal of chemical theory and computation·2024

Related Experiment Video

Updated: Jun 24, 2025

Ultrahigh Density Array of Vertically Aligned Small-molecular Organic Nanowires on Arbitrary Substrates
08:07

Ultrahigh Density Array of Vertically Aligned Small-molecular Organic Nanowires on Arbitrary Substrates

Published on: June 18, 2013

15.0K

PACMAN: A Robust Partial Atomic Charge Predicter for Nanoporous Materials Based on Crystal Graph Convolution

Guobin Zhao1, Yongchul G Chung1

  • 1School of Chemical Engineering, Pusan National University, Busan 46241, South Korea.

Journal of Chemical Theory and Computation
|June 1, 2024
PubMed
Summary

We developed PACMAN, a fast graph convolution network method for assigning atomic charges in metal-organic frameworks (MOFs) and covalent-organic frameworks (COFs). This tool accurately charges nanoporous materials, including ion-containing ones, in seconds.

More Related Videos

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

1.8K
High Resolution Physical Characterization of Single Metallic Nanoparticles
09:56

High Resolution Physical Characterization of Single Metallic Nanoparticles

Published on: June 28, 2019

5.8K

Related Experiment Videos

Last Updated: Jun 24, 2025

Ultrahigh Density Array of Vertically Aligned Small-molecular Organic Nanowires on Arbitrary Substrates
08:07

Ultrahigh Density Array of Vertically Aligned Small-molecular Organic Nanowires on Arbitrary Substrates

Published on: June 18, 2013

15.0K
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

1.8K
High Resolution Physical Characterization of Single Metallic Nanoparticles
09:56

High Resolution Physical Characterization of Single Metallic Nanoparticles

Published on: June 28, 2019

5.8K

Area of Science:

  • Materials Science
  • Computational Chemistry
  • Nanotechnology

Background:

  • Accurate partial atomic charges are crucial for predicting the behavior of porous materials like metal-organic frameworks (MOFs) and covalent-organic frameworks (COFs).
  • Existing methods for calculating these charges can be computationally expensive or lack accuracy for complex systems, particularly those containing ions.

Purpose of the Study:

  • To develop a rapid and accurate computational method for assigning partial atomic charges on MOF and COF crystal structures.
  • To enable reliable prediction of material properties, such as gas uptake and adsorption, using machine learning-based charge assignment.

Main Methods:

  • Utilized graph convolution networks (GCNs) trained on a large dataset (>1.8 million data points) from the Quantum Metal-Organic Framework (QMOF) database.
  • Developed the Predict Atomic Charges using Machine learning Networks (PACMAN) model, validated against established charge calculation methods (DDEC6, Bader, CM5).
  • Assessed the model's performance using Grand Canonical Monte Carlo (GCMC) simulations for CO2 and N2 uptake and Widom particle insertion for water Henry's Law constant.

Main Results:

  • The PACMAN model achieved high accuracy with a mean absolute error (MAE) of 0.0055 e on the test set.
  • Demonstrated consistent charge assignments across diverse MOF and COF chemistries and topologies, outperforming previous machine learning models.
  • Successfully assigned partial atomic charges for ion-containing nanoporous materials, a capability lacking in prior ML approaches.
  • PACMAN calculations showed excellent agreement with DDEC6 charges in predicting CO2, N2, and water adsorption properties.
  • Achieved a runtime of under 10 seconds for structures up to 500 atoms.

Conclusions:

  • PACMAN provides a fast, accurate, and versatile method for partial atomic charge assignment in MOFs and COFs.
  • The model's ability to handle ion-containing materials and its speed make it a valuable tool for materials discovery and property prediction.
  • An accessible web interface is available, promoting widespread adoption and accelerating research in nanoporous materials.