FLAb: Fitness Landscapes for Antibodies with Developability Data

FLAb is the largest publicly available therapeutic antibody dataset designed for training and benchmarking protein AI models. It provides open-access, high-quality developability data on diverse therapeutic properties, including expression, thermostability, immunogenicity, aggregation, polyreactivity, binding affinity, and pharmacokinetics. The dataset was contributed by the Jeffrey Gray Lab at Johns Hopkins University and is available under a CC-BY-4.0 license.

Use Cases

• Train protein language models based on diverse therapeutic property data.
• Benchmark antibody developability prediction models based on features like thermostability and aggregation.
• Optimize antibody candidates for clinical development based on pharmacokinetics and immunogenicity data.
• Study fitness landscapes for antibody sequences based on binding affinity and expression data.

Strengths

• Described as the largest publicly available therapeutic antibody dataset.
• Provides high-quality data on multiple developability properties.
• Released under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and dataset size are unknown, which may limit suitability assessment.

Provenance

Source

Jeffrey Gray Lab, Johns Hopkins University

Collection Method

Likely contains experimental and/or computational measurements of antibody properties.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null