PRISM Antibody Training Data: 66 Million Unpaired and 764k Paired Human Antibody Sequences from OAS with Germline Labels (Romero Lab, Duke)
- Provider
- Romero Lab, Duke University
- License
- CC-BY-4.0 (source)
- Size
- 5 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/RomeroLab-Duke/prism-antibody-data)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Biology
- Source
- https://opig.stats.ox.ac.uk/webapps/oas/
About this dataset
Curated human antibody sequence data used to train PRISM, a germline-aware antibody language model from the Romero Lab at Duke University. Sequences come from the Observed Antibody Space (OAS), human studies only (70 studies, 2021 to 2022 data freeze), passed through quality filters (missing conserved cysteine, heavy fragmentation, non-canonical amino acids), exact deduplication, a somatic mutation filter (more than 3 non-germline mutations in heavy and 2 in light chains), CDR3 and whole-sequence clustering, and ANARCI re-numbering. Two Parquet files hold 66,435,576 unpaired heavy and light chains for pretraining and 763,989 paired VH and VL antibodies for fine-tuning, with amino acid and nucleotide sequences, germline alignments, B-cell type, somatic mutation codes and counts, V and J gene calls, IMGT region masks, cluster IDs and a train/valid/test split column. The OAS download manifest is included; most of the Briney 2019 heavy-chain study was left out for size. Use it for antibody language models, somatic hypermutation and B-cell repertoire analysis. Derived from OAS under CC BY 4.0; cite Olsen et al. 2022, Protein Science, and PRISM.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("RomeroLab-Duke/prism-antibody-data")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: paired_anarci_relabeled.parquet
Analyze this dataset without downloading it
On Scigantic, PRISM Antibody Training Data: 66 Million Unpaired and 764k Paired Human Antibody Sequences from OAS with Germline Labels (Romero Lab, Duke) 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 Biology datasets
- PDB seqres FASTA 2022-09-28 (AlphaFold 3 training set)
- RNAcentral clustered ncRNA 90% identity (AlphaFold 3 training set)
- PDB mmCIF structures 2022-09-28 (AlphaFold 3 training set)
- Raw flow cytometry FCS files from a BD FACSAria II: 29 specimens and 9 compensation controls (Caerin 1.1/1.9 antitumour immunity study)
- Observed Antibody Space (OAS) unpaired heavy and light chains, Parquet
- 2018 NEON ground beetles: group and segmented individual specimen images with elytra morphometrics
- MGnify clustered sequences 2022-05 (AlphaFold 3 training set)
- Cell counting instrument output with ASM: 32 exports from Beckman Coulter Vi-Cell BLU, Beckman Coulter Vi-Cell XR, ChemoMetec NC View, ChemoMetec NucleoView and 2 more