A similar model is EPGCNDS which usesGraphConvolutions to generate drug representations. Take a look at the layer definition here. You should use the layers from torchdrug not the models.
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 hyper-ammeters 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?
Dear @kajocina,
EPGCNDS
which usesGraphConvolutions
to generate drug representations. Take a look at the layer definition here. You should use the layers fromtorchdrug
not the models../chemicalx/models/
./examples/
and./tests/
../tests/
and make sure that your model/layer is tested with real data../examples/
. What is the AUC on the test set? Is it reasonable?