Requirements

Python == 3.7
PyTorch == 1.9.0
PyTorch Geometry == 2.0.3
rdkit == 2020.09.2

Installation

conda create -n AutoDDI python=3.7
conda activate AutoDDI
conda install pytorch==1.9.0 cudatoolkit=10.2 -c pytorch
pip install https://data.pyg.org/whl/torch-1.9.0%2Bcu102/torch_scatter-2.0.9-cp37-cp37m-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-1.9.0%2Bcu102/torch_sparse-0.6.12-cp37-cp37m-linux_x86_64.whl
pip install torch-geometric==2.0.3
pip install https://data.pyg.org/whl/torch-1.9.0%2Bcu102/torch_cluster-1.5.9-cp37-cp37m-linux_x86_64.whl
pip install https://data.pyg.org/whl/torch-1.9.0%2Bcu102/torch_spline_conv-1.2.1-cp37-cp37m-linux_x86_64.whl
conda install -c rdkit rdkit

Dataset Preparation

cd AutoDDI-master/

download the datasets from Google Drive:

https://drive.google.com/open?id=1h_lYXoPEuLygOsMD9yyLmVqkeEGfob5r

then unzip the file

unzip AutoDDI_dataset.zip

Quick Start

A quick start example is given by:

$ python autoddi_main.py

An example of auto search is as follows:

first, modify the code in set_config.py file

gnn_parameter['mode'] = 'test'

as

gnn_parameter['mode'] = 'search'

then, run the autoddi_main.py

$ python autoddi_main.py