Generative Humanization for Therapeutic Antibodies

TL;DR

This paper introduces a novel generative modeling approach for antibody humanization, enabling the creation of diverse, highly-human antibodies with preserved or enhanced therapeutic properties, streamlining drug development.

Contribution

It reframes antibody humanization as a conditional generative task using language models, integrating therapeutic attribute models for optimized candidate generation.

Findings

Generated antibodies are highly human-like and diverse.

Produced candidates show improved antigen binding.

Validated both in silico and in lab experiments.

Abstract

Antibody therapies have been employed to address some of today's most challenging diseases, but must meet many criteria during drug development before reaching a patient. Humanization is a sequence optimization strategy that addresses one critical risk called immunogenicity - a patient's immune response to the drug - by making an antibody more "human-like" in the absence of a predictive lab-based test for immunogenicity. However, existing humanization strategies generally yield very few humanized candidates, which may have degraded biophysical properties or decreased drug efficacy. Here, we re-frame humanization as a conditional generative modeling task, where humanizing mutations are sampled from a language model trained on human antibody data. We describe a sampling process that incorporates models of therapeutic attributes, such as antigen binding affinity, to obtain candidate sequences that have both reduced immunogenicity risk and maintained or improved therapeutic properties, allowing this algorithm to be readily embedded into an iterative antibody optimization campaign. We demonstrate in silico and in lab validation that in real therapeutic programs our generative humanization method produces diverse sets of antibodies that are both (1) highly-human and (2) have favorable therapeutic properties, such as improved binding to target antigens.