KKXR

Hi, this is expected because this is only a summary of the dataset. You can see there is a 'pdb_data_path' key in the json, which refers to the path of...

Hi, I'm wondering if the problem has been solved? If so, could you please close the issue?

Thanks for the insightful questions. 1. Actually we adopt the inner-product radial due to its representation completeness. EGNN is designed for single-channel nodes, and we do not know whether the...

The common way is to first use [Rosetta](https://new.rosettacommons.org/demos/latest/tutorials/Optimizing_Sidechains_The_Packer/Optimizing_Sidechains_The_Packer) to add and pack the sidechains, then optimize the energy with softwares of molecular dynamics (e.g. [OpenMM](https://openmm.org/)).

Codes for creating these layers: internal context encoder: https://github.com/THUNLP-MT/MEAN/blob/main/models/MCAttGNN/mc_egnn.py#L273 external attentive encoder: https://github.com/THUNLP-MT/MEAN/blob/main/models/MCAttGNN/mc_egnn.py#L278

Yes, this figure is wrong. We have corrected it in the camera ready version but the arxiv preprint has not been updated. It will be updated soon. The predicted coordinates...

Hi, did you run scripts/setup.sh first to create the right environment?

Could you please provide the traceback of the error?

Did you pass --pre_numbered when running download.py? It looks that the post process is renumbering the pdbs, which is unnecessary because SAbDab has already renumbered them. Also, I think this...

Could you provide the full command you run with download.py? I'm trying to reproduce this error.