datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
PISCES-CulledPDB
PISCES-CulledPDB database as of January 2026
Recurated on Hugging Face on March 5th 2026
The PISCES dataset provides curated sets of protein sequences from the Protein Data Bank (PDB) based on sequence identity and structural quality criteria. PISCES yields non-redundant subsets of protein chains by applying filters such as sequence identity, experimental resolution, R-factor, chain length, and experimental method (e.g., X-ray, NMR, cryo-EM). The goal is to maximize structural… See the full description on the dataset page: https://huggingface.co/datasets/RosettaCommons/PISCES-CulledPDB.PISCES
PISCES-CulledPDB
Curated protein chain tables from PISCES/CullPDB: one row per chain with sequence and metadata.
Dataset: PRMegathon26/PISCES-CulledPDB
Use the subset dropdown in the Hugging Face Data Viewer to switch between the main table and 242 curation subsets.
Summary
Item
Description
Main CSV
curated_csv/cullpdb_combined_chains.csv — full chain table
Subsets
curated_csv/subsets/*.csv — 242 files (same columns)
Index… See the full description on the dataset page: https://huggingface.co/datasets/PRMegathon26/PISCES.2022-12-17-pdb-intersect-pisces_pc30_r2.52022-12-17-pdb-intersect-pisces_pc30_r2.5_processed_1024_ankh_testpisces-track-a-runs