Guided Generation for Developable Antibodies
Authors:
- Siqi ZhaoSZSiqi Zhao
- Joshua MollerJMJoshua Moller
- Porfi Quintero-CadenaPQPorfi Quintero-Cadena
- Lood van NiekerkLNLood van Niekerk
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Machine Learning Models for Predicting Monoclonal Antibody Biophysical Properties from Molecular Dynamics Simulations and Deep Learning-Based Surface DescriptorsMolecular Pharmaceutics, 2024
- Cancer therapy with antibodiesNature Reviews Cancer, 2024
- Contextualising the developability risk of antibodies with lambda light chains using enhanced therapeutic antibody profilingCommunications Biology, 2024
- DeepSCM: An efficient convolutional neural network surrogate model for the screening of therapeutic antibody viscosityComputational and Structural Biotechnology Journal, 2022
- Observed Antibody Space: A diverse database of cleaned, annotated, and translated unpaired and paired antibody sequencesProtein Science, 2021
- Application of machine learning to predict monomer retention of therapeutic proteins after long term storageInternational Journal of Pharmaceutics, 2020
- Five computational developability guidelines for therapeutic antibody profilingProceedings of the National Academy of Sciences, 2019
- MMseqs2 enables sensitive protein sequence searching for the analysis of massive data setsNature Biotechnology, 2017
- In-silico prediction of concentration-dependent viscosity curves for monoclonal antibody solutionsmAbs, 2017
- Therapeutic antibodies for autoimmunity and inflammationNature Reviews Immunology, 2010