Lab-in-the-loop therapeutic antibody design with deep learning
Frey, N. C.; Hotzel, I.; Stanton, S. D.; Kelly, R. L.; Alberstein, R. G.; Makowski, E. K.; Martinkus, K.; Berenberg, D.; Bevers, J.; Bryson, T.; Chan, P.; Czubaty, A.; D'Souza, T. A.; Dwyer, H.; Dziewulska, A.; Fairman, J. W.; Goodman, A.; Hofmann, J. L.; Isaacson, H. H.; Ismail, A. A.; James, S.; Joren, T.; Kelow, S. P.; Kiefer, J. R.; Kirchmeyer, M.; Kleinhenz, J.; Koerber, J. T.; Lafrance-Vanasse, J.; Leaver-Fay, A.; Lee, J. H.; Lee, E.; Lee, D. W.; Liang, W.-C.; Lin, J. Y.-Y.; Lisanza, S.; Loukas, A.; Ludwiczak, J.; Mahajan, S. P.; Mahmood, O.; MohammadiPeyhani, H.; Nerli, S.; Park, J. W.;
10.1101/2025.02.19.639050 bioRxivShow abstract
Therapeutic antibody design is a complex multi-property optimization problem with substantial promise for improvement with the application of machine-learning methods. Towards realizing that promise, we introduce "Lab-in-the-loop," a new approach that orchestrates state-of-the-art repertoire mining methods, generative machine learning models, multi-task property predictors, active learning ranking and selection, and in vitro experimentation in a semi-autonomous, iterative optimization loop. By automating the design of antibody variants, property prediction, ranking and selection of designs to assay in the lab, and ingestion of in vitro data, we enable an end-to-end approach to developing computationally-informed therapeutic antibody design pipelines. We apply lab-in-the-loop to eleven seed antibodies obtained via animal immunization with four clinically relevant antigen targets: EGFR, IL-6, HER2, and OSM. Over 1,800 unique antibody variants are tested throughout four rounds of iterative optimization identifying 3-100x better binding variants for all targets and 10/11 seeds, with the best binders exceeding 100 pM affinity, demonstrating a process by which end-to-end machine learning can be developed for therapeutic antibody development.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Paraplume: A fast and accurate paratope prediction method provides insights into repertoire-scale binding dynamics 98%
- Generative and interpretable machine learning for aptamer design and analysis of in vitro sequence selection 95%
- Nucleotide context models outperform protein language models for predicting antibody affinity maturation 95%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.