LICHEN: Light-chain Immunoglobulin sequence generation Conditioned on the Heavy chain and Experimental Needs (Dataset and Model weights)

This data is released alongside "LICHEN: Light-chain Immunoglobulin sequence generation Conditioned on the Heavy chain and Experimental Needs", which contains full details on the model and the data processing and cleaning. Data: Cleaned paired human antibody sequence data for machine learning applications. Model: Model weights for LICHEN. Preprint: https://doi.org/10.1101/2025.08.06.668938 GitHub: https://github.com/oxpig/LICHEN WebApp: https://opig.stats.ox.ac.uk/webapps/lichen/OAS: https://opig.stats.ox.ac.uk/webapps/oas/