AF2_UniRef50: SaProt Structure-Aware Pre-training Set
- Provider
- Westlake University REPL lab (Su, Han, Zhou, Shan, Zhou and Yuan; SaProt)
- License
- CC-BY-4.0 (source)
- Size
- 8 files
- Format
- CSV (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/westlake-repl/AF2_UniRef50)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Structural Biology
- Source
- https://openreview.net/forum?id=6MRm3G4NiU
About AF2_UniRef50: SaProt Structure-Aware Pre-training Set
Pre-training dataset for SaProt (Protein Language Modeling with Structure-aware Vocabulary, ICLR 2024) from the Westlake University REPL lab, linked from the SaProt repository as the dataset used to pre-train the model. Proteins are UniRef50 representatives with AlphaFold2 predicted structures from the AlphaFold Protein Structure Database, each encoded as a structure-aware sequence that interleaves the amino acid letter with the Foldseek 3Di structural letter for every residue; per the SaProt documentation the character # marks residues in low-confidence regions (pLDDT below 70). Measured 2026-11-14: train.csv (21.9 GB) and valid.csv (11 MB) with columns uniprot_id and seq, plus the same training data as an LMDB database (train/data.mdb, 36.2 GB); repository storage about 62 GB. Open the CSVs with pandas, pyarrow or datasets; open the LMDB with the lmdb package as shown on the dataset card, where each record is JSON. Uses include pre-training or fine-tuning protein language models on combined sequence and structure tokens, Foldseek 3Di modelling, and transfer to mutation effect, stability and function prediction. The structures derive from AlphaFold DB, which EMBL-EBI and Google DeepMind distribute under CC BY 4.0; cite SaProt and AlphaFold DB.
How to load AF2_UniRef50: SaProt Structure-Aware Pre-training Set in Python
import pandas as pd
df = pd.read_csv("hf://datasets/westlake-repl/AF2_UniRef50/train.csv")
df.head()Data structure
File types in sampled files: CSV
Files
Example file: train.csv
Analyze this dataset without downloading it
On Scigantic, AF2_UniRef50: SaProt Structure-Aware Pre-training Set opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Structural Biology datasets
- Structural basis of GAIN domain autoproteolysis and cleavage-resistance in the adhesion G-protein coupled receptors
- Thal-Kak Multiple Sequence Alignment Databases (prebuilt MMseqs2 and HH-suite databases for structure prediction)
- EMPIAR: Electron Microscopy Public Image Archive
- Molecular Dynamics Trajectories for GPR6 Basal Activity (Volume 01)
- Dataset for article Morphology control in benzoic imine-linked polymer-drug conjugates for adaptive drug delivery and enhanced in vivo efficacy
- MGnify Mega-Scale Protein Stability Dataset
- DPAM Domain Classification of Human Proteins against ECOD Reference
- High-throughput screening approach identifies substrate-selective Hsp104 variants that counter amyloid seeding with diminished off-target effects