Give binding site as input

[ahof1704]

Hi,

I have two proteins that I would like to test the docking. I have adapted your example script (single_pairs) to run with my proteins. The output of the DiffDock seems to be quite off regarding the ground truth position of the ligand (which is available in the structure downloaded from the PDB server).

Is there a way to input some bias toward the binding site? or something that could perform a similar function?

Thanks in advance!