search

ketatam / DiffDock-PP

Implementation of DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models in PyTorch (ICLR 2023 - MLDD Workshop)
https://arxiv.org/abs/2304.03889
188 stars 36 forks source link

Obtaining confidence values from the model #26

Open yoavatsmonraz81 opened 6 months ago

yoavatsmonraz81 commented 6 months ago

Hi there, thanks a lot for your work on this software, its quite impressive. However, I'm trying to understand if their is a way to obtain the confidence values of each predicted pose ?

I printed out the prediction pickle and got a list composed of this data structure (40 copies of it per number of sampled structures):

name='2Q3A', center=[1, 3], receptor={ pos=[117, 3], x=[117, 1281], }, ligand={ pos=[117, 3], x=[117, 1281], }, (receptor, contact, receptor)={ edge_index=[2, 2340] }, (ligand, contact, ligand)={ edge_index=[2, 2340] } ), -7.416438102722168)]]

I suspected the -7.41 to be the gradient value and not the confidence one, but I also couldn't find any clear way how to get a handle on this via main_inf.py Could you please advise ?

Kindest regards, Yoav

YFeriel commented 4 months ago

Hi @yoavatsmonraz81 ,

Did you find a solution? I'm facing a similar issue and would appreciate any insights.

Thanks!