Guided Generation for Developable Antibodies
This work addresses the challenge of optimizing antibody sequences for clinical effectiveness, which is crucial for drug development, though it appears incremental as it builds on existing diffusion models with a new guidance method.
The authors tackled the problem of designing therapeutic antibodies with favorable manufacturability and stability by introducing a guided discrete diffusion model trained on natural sequences and developability data. They achieved significant enrichment in predicted developability scores over unguided baselines, enabling an iterative pipeline for antibody design.
Therapeutic antibodies require not only high-affinity target engagement, but also favorable manufacturability, stability, and safety profiles for clinical effectiveness. These properties are collectively called `developability'. To enable a computational framework for optimizing antibody sequences for favorable developability, we introduce a guided discrete diffusion model trained on natural paired heavy- and light-chain sequences from the Observed Antibody Space (OAS) and quantitative developability measurements for 246 clinical-stage antibodies. To steer generation toward biophysically viable candidates, we integrate a Soft Value-based Decoding in Diffusion (SVDD) Module that biases sampling without compromising naturalness. In unconstrained sampling, our model reproduces global features of both the natural repertoire and approved therapeutics, and under SVDD guidance we achieve significant enrichment in predicted developability scores over unguided baselines. When combined with high-throughput developability assays, this framework enables an iterative, ML-driven pipeline for designing antibodies that satisfy binding and biophysical criteria in tandem.