search

DeepGraphLearning / GearNet

GearNet and Geometric Pretraining Methods for Protein Structure Representation Learning, ICLR'2023 (https://arxiv.org/abs/2203.06125)
MIT License
253 stars 28 forks source link

atom view #42

Open karel-w opened 11 months ago

karel-w commented 11 months ago

I was wondering how atom view is implemented? I'm getting a shape mismatch.

In mc-gearnet_edge.yaml I changed the view and entity level to 'atom' and input dimension to 38. As i find 38 atom types in the torchdrug protein class. Is there another setting i need to change?

Thanks for creating GearNet!

Oxer11 commented 11 months ago

Hi, thanks for raising the question. The atom view is set to changing the node features from residue features to atom features. You can find the implementation here: https://github.com/DeepGraphLearning/torchdrug/blob/6066fbd82360abb5f270cba1eca560af01b8cc90/torchdrug/data/protein.py#L113. I think you also need to check the implementation of Multiview Contrast to make sure the shape of node features can match.