search

mims-harvard / TDC

Therapeutics Commons (TDC-2): Multimodal Foundation for Therapeutic Science
https://tdcommons.ai
MIT License
983 stars 170 forks source link

PDB codes for structures in `Epitope` PDB_Jespersen #198

Open a-r-j opened 1 year ago

a-r-j commented 1 year ago

Hiya!

I'm looking for a (hopefully!) easy way to get the PDB codes for each of the examples in the PDB_Jespersen Epitope prediction dataset.

kexinhuang12345 commented 1 year ago

Hey Arian, sorry for the late reply. Seems like i stop receiving notifications from the repo issues. Here is the link to download the raw dataset: https://services.healthtech.dtu.dk/services/BepiPred-2.0/pdb_chains.fasta It should be super easy to parse the PDB ID from it:

>1A2Y_BA C 2
kvfgrcelaaamkrhglaNyrGYSlgNwvcaakfesnfntqatnrntdgstdygilqinsrwwcndgrtpgsrnlcnipcsallssditasvncakkivsdGNgmnawvawrnrcKGTDVQawIRgcrl

We will also add a function to grab the PDB ID for this dataset in the next release!