Anton Bushuiev

Hi, thank you for your fantastic work with Foldseek! How does `easy-complexsearch` actually work? Does it just do TM-align of whole complexes or does it somehow use Foldseek on all...

Wow, thank you! Looking forward to the preprint!

Hi, @AxelGiottonini! Thank you very much for you response. Foldseek looks perfect, I did not know about it. What exactly do you mean by using a graph library? To cluster...

Thank you for sharing! Yes, I am also considering to create a split based on interface similarity using a tool like [this](https://github.com/haddocking/arctic3d).

Hi! I do not use EquiDock and I was mainly interested in the data split. I am working on a related problem of predicting binding affinity change upon mutation (based...

Hi @a-r-j, thank you for writing! It is intended that `7lgq_D_H.pdb` has only one atom for chain H because in the original [PDB file](https://files.rcsb.org/view/7LGQ.pdb) there is only one ATOM record...

It also seems that here the sign is swapped if I understand correctly (i.e. destabilizing mutations are a positive class): https://github.com/luost26/RDE-PPI/blob/f6d68a7331a9f65290f525f0a491848245b072b3/rde/utils/skempi.py#L127

Hi Amin! Thank you very much for this analysis! This is extremely valuable. It will be a great case study to test with a new version of the model. I...

Dear @AmingWu , Yes, the code and the dataset are already available and the documentation will be added in June. Specifically, the [`run.py`](https://github.com/anton-bushuiev/PPIformer/blob/main/scripts/run.py) script can be used for both training...

Hi @AmingWu ! I have added examples of training and testing. Please let me know if you encounter any issues. I apologise for the delay.