Boughter Antibody Polyreactivity: 914 Mouse VH Sequences with Binary Labels

Boughter Antibody Polyreactivity Dataset contains 914 antibody heavy chain variable domain (VH) sequences with binary polyreactivity labels. The data was originally published by Boughter et al. in 2020 and has been preprocessed according to the methodology described in Sakhnini et al. 2025. The dataset was uploaded to the platform by hugging-science on December 17, 2025.

Use Cases

• Train binary classifiers for antibody polyreactivity based on VH sequence data.
• Benchmark sequence-based models for predicting antibody binding characteristics.
• Analyze the relationship between antibody variable domain sequences and polyreactivity labels.

Strengths

• Contains 914 antibody sequences with associated labels.
• Preprocessed according to a defined methodology from a 2025 publication.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is known, but the number of features per row and file formats are unknown.

Provenance

Source

Boughter et al. 2020; preprocessing by Sakhnini et al. 2025 (Novo Nordisk & University of Cambridge).

Collection Method

Mouse antibodies with ELISA-based polyreactivity measurements.

Time Range

Original data from 2020.

Freshness

Last updated 2025-12-17 05:02:17.

Geography

Laboratory study; geographic coverage is not specified.