Add the GCNBMP model

[Charles Tapley Hoyt]

• Please read the paper first. It is here.
• There is also code-release with the paper here.
• After that read the contributing guidelines.
• If there is an existing open-source version of the model please take a look.
• ChemicalX is built on top of PyTorch 1.10. and torchdrug.
• The library heavily builds on top on torchdrug and molecules in batches are PackedGraphs.
• There is already a model class under ./chemicalx/models/
• Context features, drug level features, and labels are all FloatTensors.
• Look at the examples and tests under ./examples/ and ./tests/.
• Add auxiliary layers as you see fit - please document these, add tests, and add these layers to the main readme.md if needed.
• Add typing to the initialization and forward pass.
• Non-data-dependent hyperparameters should have default values.
• Please add tests under ./tests/ and make sure that your model/layer is tested with real data.
• Write an example under ./examples/. What is the AUC on the test set? Is it reasonable?

[Michaël Ughetto]

Hey @cthoyt

I discussed with @benedekrozemberczki and I'm gonna implement this one. I've had a look at the original code and the paper and I think the architecture is pretty clear for me now. Will let you know how it goes.

[Charles Tapley Hoyt]

Excellent!