search

DeepGraphLearning / torchdrug

A powerful and flexible machine learning platform for drug discovery
https://torchdrug.ai/
Apache License 2.0
1.41k stars 198 forks source link

constrained property optimization #100

Open dgm2 opened 2 years ago

dgm2 commented 2 years ago

Hello, Is there a way to reproduce the Constrained property optimization experiments from GCPN and GraphAF on torchdrug? Similarly to the property optimization from https://torchdrug.ai/docs/tutorials/generation.html

Thanks!

shichence commented 2 years ago

Yes, you can. The only difference between Constrained property optimization and property optimization is that we start from an existing subgraph in the former case. To implement it, you basically need to modify the part of codes that handle the graph initialization for training and inference.