FLAb: Fitness Landscapes for Antibodies

Description

FLAb is the largest publicly available therapeutic antibody dataset designed to train and benchmark 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.

Update Frequency

Any new public release of antibody developabilty data is deposited into FLAb

License

https://creativecommons.org/licenses/by/4.0/

Documentation

https://github.com/Graylab/FLAb/blob/main/README.md

Managed By

Jeffrey Gray Lab, Johns Hopkins University

See all datasets managed by Jeffrey Gray Lab, Johns Hopkins University.

Contact

mchungy1@jhu.edu

How to Cite

FLAb: Fitness Landscapes for Antibodies was accessed on DATE from https://registry.opendata.aws/flab. FLAb was accessed on [DATE] at registry.opendata.aws/flab

Usage Examples

Tutorials

• FLAb tutorial: Benchmarking a protein language model for antibody expression prediction by Michael Chungyoun
  

Publications

• FLAb: Benchmarking deep learning methods for antibody fitness prediction by Michael Chungyoun and Jeffrey J. Gray