There is a newer version of the record available.

Published July 6, 2025 | Version v2
Dataset Open

RareFold

Authors/Creators

Description

All compressions are made with zstd here. You can get it here (and it's amazing - thank me later): https://github.com/facebook/zstd

 

params20000.npy - parameters for RareFold single-chain protein structure prediction

finetuned_params25000.npy - parameters for RareFold peptide binder design

1ssc.tar.zst - design results for PDB ID 1ssc

val.tar.zst - validation results

test.tar.zst - RareFold test set predictions (The same data AF3 is/can be evaluated on)

af3.tar.zst - AF3 predictions

native_valid_structures.tar.zst - native validation structures from the PDB

train_meta_20.csv - meta for train/val/test splits and 20% sequence identity cluster annotations

aa_count_per_chain.csv - Number of AAs of each type per chain id

aa_hist.csv - total occurrence of AA types in the dataset

Files

aa_count_per_chain.csv

Files (11.7 GB)

Name Size Download all
md5:7f25f9eb6efe302a6c9b2fa968f4bf52
9.2 GB Download
md5:305e20715aa52deb30b6eb1bbe0c3cc3
100.5 MB Preview Download
md5:677bd8a7448b04ef7480a93329101f8d
2.2 kB Preview Download
md5:3da6b1c79f487be4dfd4b9bdc39c036b
1.2 GB Download
md5:c2ff48594dbbbac2986e11905e808eea
371.6 MB Download
md5:4866c200dfba93be01df73db14af3d84
44.9 MB Download
md5:8dfb06be64fcbe1c3c62d39a1c6b4a25
371.6 MB Download
md5:89b0a48a4fe1d26fc86c623f8b072589
10.6 MB Download
md5:a52b719fef4ac0fff22916d05e6d24fa
6.0 MB Preview Download
md5:5c16b74a74e2f06eb8a07150d76371b8
412.3 MB Download