Closed mahdip72 closed 10 months ago
Hi,
1.) no, from what I know this is not possible, yet. 2.) TM-score requires 3D structures for 3D-alignment and distance computation. So if you only have predicted 3Di, this won't be possible. For comparing true/predicted 3Di, I usually used simple classification accuracy. If you want to make it a bit more complicated, you can also compute alignment of true/predicted 3Di using the 3Di-substitution matrix provided by Foldseek.
Hello, I have a few questions which might be very basic to others.
Can we convert the 3Di tokens produced by foldseek into the actual 3D structure format like PDB files?
How can I compare two sequences of predicted and true 3Di tokens? Can I use something like the TM Score for that? I am working on a model to predict 3Di tokens from amino acids and am searching for the best metric to evaluate the model.
I would be very greatful to whom can answer my questions.