Better antibodies engineered with a GLIMPSE of human data

Abstract excerpt

GLIMPSE-1 is a protein language model trained solely on paired human antibody sequences. It captures immunological features and achieves best-in-class performance in humanization benchmarks. We demonstrate the utility of GLIMPSE-1 in humanization; engineering of antibodies for affinity, species cross-reactivity, and key developability parameters; and the creation of highly divergent functional variants with <90% s...

Topics

Open a Topic to create a Post that cites this publication.

• Antibodies, Neutralizing
• Antibodies, Viral
• Monoclonal and Polyclonal Antibodies Research
• Mutation
• Neutralization Tests
• SARS-CoV-2
• SARS-CoV-2 and COVID-19 Research
• vaccines and immunoinformatics approaches

Identifiers and source

Literature Corpus work

adef8aa9-2e2d-5233-9a3f-2d84e09ea583

DOI

10.1101/2025.06.08.658113