bioRxiv · 10.1101/2024.08.06.606780
p-IgGen: A Paired Antibody Generative Language Model
Abstract
A key challenge in antibody drug discovery is designing novel sequences that are free from developability issues - such as aggregation, polyspecificity, poor expression, or low solubility. Here, we present p-IgGen, a protein language model for paired heavylight chain antibody generation. The model generates diverse, antibody-like sequences with pairing properties found in natural antibodies. We also create a finetuned version of p-IgGen that biases the model to generate antibodies with 3D biophysical properties that fall within distributions seen in clinical-stage therapeutic antibodies.
Source connections
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Turnbull, O. M., Oglic, D., Croasdale-Wood, R., Deane, C. M.. 2024-08-08. p-IgGen: A Paired Antibody Generative Language Model. https://doi.org/10.1101/2024.08.06.606780
Cite the original work for its findings. Save a collection to share your selection of sources.