https://github.com/Luckick/EAGCN

Multi-View Spectral Graph Convolution with Consistent Edge Attention for Molecular Modeling
https://github.com/Luckick/EAGCN

Last synced: 3 months ago
JSON representation

Multi-View Spectral Graph Convolution with Consistent Edge Attention for Molecular Modeling

• Host: GitHub
• URL: https://github.com/Luckick/EAGCN
• Owner: Luckick
• Created: 2018-02-10T21:40:33.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-10-01T02:38:08.000Z (over 2 years ago)
• Last Synced: 2024-01-16T19:12:52.800Z (5 months ago)
• Language: Python
• Homepage:
• Size: 2.26 MB
• Stars: 200
• Watchers: 9
• Forks: 44
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Lists

• awesome-graph-classification - [Python Reference
• awesome-gcn - Luckick/EAGCN - relational Graph Convolutional Networks, (Implement:)
• benedekrozemberczki-awesome-graph-classification - [Python Reference

README

        


# EAGCN

This is a PyTorch implementation of paper "[Multi-View Spectral Graph Convolution with Consistent Edge Attention for Molecular Modeling](https://www.sciencedirect.com/science/article/abs/pii/S092523122100271X)" published at Neurocomputing. 

## Installation

Install pytorch and torchvision. 

## Train EAGCN model

### Dataset

Four benchmark datasets ([Tox21, HIV, Freesolv and Lipophilicity](http://moleculenet.ai/datasets-1)) are utilized in this study to evaluate the predictive performance of built graph convolutional networks.  They are all downloaded from the [MoleculeNet](http://moleculenet.ai/) that hold various benchmark datasets for molecular machine learning.

Datasets are also provided in folder "Data".

### Train the model

Open the folder "eagcn_pytorch".

When you train the model, you can use:

    python train.py

support files:    

EAGCN_dataset.py: pre-processing data      

neural_fp.py: from smiles to graph     

layers.py: define layers     

models.py: define models     

utils.py: other tools     

### Visualization Tools

check_model.py: check parameters (edge attention for each layer).     

mol_to_vec.py: visualize the molecule in 2D space, compare with other molecules which have similiar SMILEs.      

plot.py: show model training process.      

tsnes.py: tsne visualization about atom subtype, also provide umap option.     

kmeans_atomrep.py: kmeans clustering for atom subtype.     

plot_molecule.py: plot single molecule.    

## Citation

If you use this repository, e.g., the code and the datasets, in your research, please cite the following paper:

```

@article{shang2021multi,

  title={Multi-view spectral graph convolution with consistent edge attention for molecular modeling},

  author={Shang, Chao and Liu, Qinqing and Tong, Qianqian and Sun, Jiangwen and Song, Minghu and Bi, Jinbo},

  journal={Neurocomputing},

  volume={445},

  pages={12--25},

  year={2021},

  publisher={Elsevier}

}

```

## Acknowledgments

Code is inspired by [GCN](https://github.com/tkipf/gcn) and [conv_qsar_fast](https://github.com/connorcoley/conv_qsar_fast)