Binary classification of compounds

I was just starting out with picture convolutional networks, and I wanted to do a binary model of compounds.I looked at the molecular transformation diagram with rdkit.But I don’t know how to turn this into an input for DGL.I have 2,500 compounds in total, and I couldn’t find any similar tutorials.For help!

  1. We have a tutorial on graph classification. For binary classification of compounds the general workflow is quite similar.
  2. Recently we have released DGL-LifeSci, a DGL-based package for life science. We provide an example for performing compound classification here.

Thank you very much, I will try to follow these tutorials.

Thank you very much, I will try to follow these tutorials. :innocent: