I wanted to ask whether it is possible to include the PAE (Predicted Aligned Error) output or Peak values, similar to those in AlphaFold, in the current analysis. Alternatively, do you have any index or metric that could provide insights into potential protein-protein interactions?
Thank you for your time and assistance. I look forward to your response.
The function run_folding_on_context returns a dataclass with the PAE scores included; while we don't write these out by default in predict_structure.py, you can write those scores out with np.save.
Hi,
I wanted to ask whether it is possible to include the PAE (Predicted Aligned Error) output or Peak values, similar to those in AlphaFold, in the current analysis. Alternatively, do you have any index or metric that could provide insights into potential protein-protein interactions?
Thank you for your time and assistance. I look forward to your response.