BorgwardtLab / proteinshake

Protein structure datasets for machine learning.
https://proteinshake.ai
BSD 3-Clause "New" or "Revised" License
101 stars 9 forks source link

Could you provide the script for building structure-similarity splits? #267

Closed LTEnjoy closed 9 months ago

LTEnjoy commented 9 months ago

Hi, thank you for your wonderful work!

I'm very interested in your proposed novel way to construct datasets based on structure similarity using foldseek. I wonder that if you could share the script to build the structure-similarity split as described in your paper?

Thank you very much and looking forward to your reply!

cgoliver commented 9 months ago

Thanks for your interest in ProteinShake!

All of the pre-processing scripts can be found in our release script repository here

Please let us know if you have any other questions!