FLAb2: Fitness Landscapes for Antibodies 2

The Fitness Landscape for Antibodies (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 — expression, thermostability, immunogenicity, aggregation, polyreactivity, binding affinity, and pharmacokinetics — spanning 241 datasets and over 3 million antibody assay data points aggregated from public studies.

Each dataset is a CSV with heavy (and optionally light) amino acid sequence columns and a fitness column containing the experimental assay value. Additional metadata columns may also be present.