Modelling and docking a single protein while providing .pdb for the remaining multimer

Hi all,
would it be possible to provide a complex/multimer pdb structure and model only one new protein on top of it? essentially by-passing the initial predictions by feeding it a .pdb file for the already known complex structure and then only model and dock the last one on top of it? That would be a great addition to the already great alphafold.

Best,
Lena