• AutoDM² can design a deep GNN architecture for glycan molecular graph representaion learning.

• The framework of AutoDM² is as follows:

• Ensure you have installed CUDA 11.1 before installing other packages

1.Python environment: recommending using Conda package manager to install

conda create -n autodm2 python=3.7
source activate autodm2

2.Python package:

torch == 1.8.2
torch-geometric == 2.0.2
torch-scatter == 2.0.7
torch-sparse == 0.6.11
hyperopt == 0.1.2

1.Performance test with the optimal deep GNN architecture designed by AutoDM²

run main_test.py

2.Search new deep GNN architecture using AutoDM²

run main_search.py