Meta-GAT

Meta Learning with Graph Attention Networks for Low Data Drug Discovery

Meta-GAT is used to deal with the molecular property prediction task of the scarce marker data in drug discovery.

Requirements

PyTorch >= 1.2.0
Numpy >= 1.18.5
Rdkit >= 2020.09.1.0
scikit-learn >= 0.23.2
scipy >= 1.1.0

Usage

python Meta-GAT.py

Reference

@article{lv2023meta, title={Meta Learning With Graph Attention Networks for Low-Data Drug Discovery}, author={Lv, Qiujie and Chen, Guanxing and Yang, Ziduo and Zhong, Weihe and Chen, Calvin Yu-Chian}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2023}, publisher={IEEE} }