search

jonathanking / sidechainnet

An all-atom protein structure dataset for machine learning.
BSD 3-Clause "New" or "Revised" License
330 stars 38 forks source link

Order of crds #50

Closed ychnh closed 2 years ago

ychnh commented 2 years ago

Hi,

I was reading through the documentation and I could not find the ordering of the atom information for crds. I did find some information that makes me guess that the ordering is [N, C_alpha, C, O]. Could I get a confirmation for this? Also, would you see if there are any issues if I computed Cb from N ,C_alpha, C to recompute the bond angles?

Thanks,

jonathanking commented 2 years ago

Hello,

Thanks for your interest and for the question.

You are correct regarding the coordinate ordering. Please see this file for more information.

Regarding Cbeta, can you please clarify what you are trying to accomplish?

Best, Jonathan

ychnh commented 2 years ago

Coordinate ordering: Ah, thank you for the link.

Cbeta: I was mistaken.. Sorry. The N, Calpha, C should be sufficient for representing the general structure of the protein.

jonathanking commented 2 years ago

SidechainNet includes the Cbeta atoms in its coordinate representation (see the same file I linked above). Please let me know if you need any more help.