https://github.com/tata1661/par-neurips21
Codes for "Property-Aware Relation Networks for Few-shot Molecular Property Prediction (NeurIPS 2021)".
https://github.com/tata1661/par-neurips21
drug-discovery few-shot-learning graph-structure-learning meta-learning molecular-property molecular-representation-learning one-shot-learning
Last synced: 12 months ago
JSON representation
Codes for "Property-Aware Relation Networks for Few-shot Molecular Property Prediction (NeurIPS 2021)".
- Host: GitHub
- URL: https://github.com/tata1661/par-neurips21
- Owner: tata1661
- Created: 2021-09-29T04:54:24.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2022-02-22T07:46:17.000Z (over 4 years ago)
- Last Synced: 2025-03-27T22:07:10.588Z (over 1 year ago)
- Topics: drug-discovery, few-shot-learning, graph-structure-learning, meta-learning, molecular-property, molecular-representation-learning, one-shot-learning
- Language: Python
- Homepage:
- Size: 23.5 MB
- Stars: 47
- Watchers: 4
- Forks: 8
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
This is the PyTorch implementation of ["Property-Aware Relation Networks (PAR) for Few-Shot Molecular Property Prediction (spotlight)"](https://papers.nips.cc/paper/2021/hash/91bc333f6967019ac47b49ca0f2fa757-Abstract.html) published in NeurIPS 2021 as a spotlight paper.
The PaddlePaddle implementation is a part of PaddleHelix, which can be reached [here](https://github.com/PaddlePaddle/PaddleHelix/tree/dev/apps/fewshot_molecular_property).
Please cite our paper if you find it helpful. Thanks.
```
@InProceedings{wang2021property,
title={Property-Aware Relation Networks for Few-Shot Molecular Property Prediction},
author={Wang, Yaqing and Abuduweili, Abulikemu and Yao, Quanming and Dou, Dejing},
booktitle = {Advances in Neural Information Processing Systems},
year={2021},
}
```
## Environment
We used the following Python packages for core development. We tested on `Python 3.7`.
```
- pytorch 1.7.0
- torch-geometric 1.7.0
```
## Datasets
Tox21, SIDER, MUV and ToxCast are previously downloaded from [SNAP](http://snap.stanford.edu/gnn-pretrain/data/chem_dataset.zip). You can download the data [here](https://drive.google.com/file/d/1K3c4iCFHEKUuDVSGBtBYr8EOegvIJulO/view?usp=sharing), unzip the file and put the resultant ``muv, sider, tox21, and toxcast" in the data folder.
## Experiments
To run the experiments, use the command (please check and tune the hyper-parameters in [parser.py](parser.py):
```
python main.py
```
If you want to quickly run PAR method on tox21 dataset, please use the command:
```
bash script_train.sh
```