There is a newer version of the record available.

Published March 15, 2024 | Version 1
Model Open

A Partial Atomic Charge Predicter for Porous Materials based on Graph Convolutional Neural Network (PACMAN)

  • 1. ROR icon Pusan National University

Description

Installation

pip install -r requirements.txt

 

Charge Assignment      

 
You can put your cif files in any folder, but please run the code and jupyter notebook in this folder.                

bash


python GCNCharge.py [folder name] [MOF/COF]
example: python GCNCharge.py test_file MOF

notebook


import GCNCharge4notebook
GCNCharge4notebook.GCNChagre(file="./test/test_cubtc/",model="MOF")


file: your folder contains cif files                               
model: MOF or COF                                                   
there is an example in GCNCharge.ipynb

 

Website


IF you do not want to install GCN Charge, you can go to this :point_right: [link](https://gcn-charge-predicter-mtap.streamlit.app/)        

 

Reference

If you use GCN Charge, please cite:
bib
@article{,
    title={},
    DOI={},
    journal={},
    author={},
    year={},
    pages={}
}

 

Bugs

 

 If you encounter any problem during using GCN Charge, please talk to me [email protected].  

Files

GCNCharge.zip

Files (5.8 GB)

Name Size Download all
md5:05a983c047479f97bfd4fb09a85f36e1
5.8 GB Preview Download

Additional details

Dates

Created
2024-03-16
upload

Software

Repository URL
https://github.com/sxm13/PACMAN
Programming language
Python
Development Status
Active