RosettaCommons
Picking Hotspot
Hello community, In the Design Binder feature of RFdiffusion, the authors have stated that “define an interface hotspot residues as any residue on the target chain that is within 10 Angstrom Cbeta-Cbeta distance of the binder chain.” As I understand, their “binder” here is protein/peptide. However, my target (I got it from PBD) is in a complex with a small molecule. So, in my case, how can I pick hotspots?
Is does your 'target site' for the binder involve the small molecule?
Also keep in mind that while what you quoted is their definition for a hotspot residue, but only a small subset of those hotspots need to be given to RFdiffusion: "Of all of the hotspots which are identified on the target 0-20% of these hotspots are actually provided to the model and the rest are masked. This is important for understanding how you should pick hotspots at inference time.; the model is expecting to have to make more contacts than you specify. We normally recommend between 3-6 hotspots"
