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
174 stars 35 forks source link

how to get the best pose #13

Open Chengeng-Yang opened 1 year ago

Chengeng-Yang commented 1 year ago

Thank you for sharing this amazing work and a few examples!

I just wanted to ask how could we know which pose is ranked as the best. I tested your model by running src/db5_inference.sh and I found 40 poses generated in the visualization path, but I was not sure which one is the best pose. By the way, does the numbering of 0-40 refer to the diffusion time? Many thanks!

TernencezzZ commented 8 months ago

Hi, @Chengeng-Yang Based on my experience, the larger the suffix numeral in generated filenames of protein, the better the effect, which may be opposite to the "t" value in diffusion process.

ahof1704 commented 5 months ago

Shouldn't we have a file that summarizes the energy or quality of the docking?