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

Explainability #27

Open MichailChatzianastasis opened 1 year ago

MichailChatzianastasis commented 1 year ago

Hello,

Is there any code available for the explainability experiment in Section K in the appendix of your paper https://arxiv.org/pdf/2203.06125.pdf?

Thank you.

Oxer11 commented 1 year ago

Hi, thanks for asking the question. It's a little complicated to release the code and model for interpretation, so I'm sorry that we don't plan to release it. But it should be easy to implement. You can refer to the interpretation script in LM-GVP. The only things you need to do are processing binding site data and using Integrated Gradients, both of which are shown in their script.