Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision

Josh Qixuan Sun, Morteza Babaie, Wenyang Hou, Mark Crowley, David Young
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:116380-116394, 2026.

Abstract

Antibody expression ranking is a critical task in antibody design, yet its modelling is severely hindered by the scarcity of labeled experimental data. To address this, we propose a unified preference-based learning framework that integrates scarce quantitative expression data with large-scale weak positive supervision from immunization data. We adapt Direct Preference Optimization (DPO) to protein language models by introducing a union-masked log-likelihood approximation and IMGT-based alignment, enabling efficient training on variable-length sequences. Evaluating on a diverse internal dataset of 1254 labeled sequences and 4 million unlabeled camelid-derived antibodies, we show that our method consistently outperforms baselines on most metrics. Our results demonstrate that preference learning can effectively learn from weak supervision, providing a scalable solution for antibody expressibility optimization in data-constrained settings. Project page: https://kisoji-biotechnology-inc.github.io/Preference-Expression-Ranking/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-sun26a, title = {Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision}, author = {Sun, Josh Qixuan and Babaie, Morteza and Hou, Wenyang and Crowley, Mark and Young, David}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {116380--116394}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/sun26a/sun26a.pdf}, url = {https://proceedings.mlr.press/v306/sun26a.html}, abstract = {Antibody expression ranking is a critical task in antibody design, yet its modelling is severely hindered by the scarcity of labeled experimental data. To address this, we propose a unified preference-based learning framework that integrates scarce quantitative expression data with large-scale weak positive supervision from immunization data. We adapt Direct Preference Optimization (DPO) to protein language models by introducing a union-masked log-likelihood approximation and IMGT-based alignment, enabling efficient training on variable-length sequences. Evaluating on a diverse internal dataset of 1254 labeled sequences and 4 million unlabeled camelid-derived antibodies, we show that our method consistently outperforms baselines on most metrics. Our results demonstrate that preference learning can effectively learn from weak supervision, providing a scalable solution for antibody expressibility optimization in data-constrained settings. Project page: https://kisoji-biotechnology-inc.github.io/Preference-Expression-Ranking/.} }
Endnote
%0 Conference Paper %T Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision %A Josh Qixuan Sun %A Morteza Babaie %A Wenyang Hou %A Mark Crowley %A David Young %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-sun26a %I PMLR %P 116380--116394 %U https://proceedings.mlr.press/v306/sun26a.html %V 306 %X Antibody expression ranking is a critical task in antibody design, yet its modelling is severely hindered by the scarcity of labeled experimental data. To address this, we propose a unified preference-based learning framework that integrates scarce quantitative expression data with large-scale weak positive supervision from immunization data. We adapt Direct Preference Optimization (DPO) to protein language models by introducing a union-masked log-likelihood approximation and IMGT-based alignment, enabling efficient training on variable-length sequences. Evaluating on a diverse internal dataset of 1254 labeled sequences and 4 million unlabeled camelid-derived antibodies, we show that our method consistently outperforms baselines on most metrics. Our results demonstrate that preference learning can effectively learn from weak supervision, providing a scalable solution for antibody expressibility optimization in data-constrained settings. Project page: https://kisoji-biotechnology-inc.github.io/Preference-Expression-Ranking/.
APA
Sun, J.Q., Babaie, M., Hou, W., Crowley, M. & Young, D.. (2026). Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak Supervision. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:116380-116394 Available from https://proceedings.mlr.press/v306/sun26a.html.

Related Material