Abstract
Increasing the binding affinity of an antibody to its target antigen is a crucial task in antibody therapeutics development. This paper presents a pretrainable geometric graph neural network, GearBind, and explores its potential in in silico affinity maturation. Leveraging multi-relational graph construction, multi-level geometric message passing and contrastive pretraining on mass-scale, unlabeled protein structural data, GearBind outperforms previous state-of-the-art approaches on SKEMPI and an independent test set. A powerful ensemble model based on GearBind is then derived and used to successfully enhance the binding of two antibodies with distinct formats and target antigens. ELISA EC50 values of the designed antibody mutants are decreased by up to 17 fold, and KD values by up to 6.1 fold. These promising results underscore the utility of geometric deep learning and effective pretraining in macromolecule interaction modeling tasks.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
1. Replaced the bar plots in Figure 3 with tables that display the fitted EC50 values along with their 95% confidence intervals. This change was made to clearly display the uncertainty of the calculated EC50 values. 2. Corrected typographical errors and revised unclear sentences throughout the manuscript and supplementary materials to enhance clarity, readability and reproducibility. 3. Released our code to GitHub and Zenodo and cited the Zenodo upload in the manuscript. 4. Added or updated the acknowledgement, data availability and code availability sections, and separated the figures from the main text.
Data Availability
The raw SKEMPI database can be accessed via https://life.bsc.es/pid/skempi2. The CATH database can be accessed via https://www.cathdb.info/. The raw HER2 binders data can be accessed via https://github.com/AbSciBio/unlocking-de-novo-antibody-design/blob/main/spr-controls.csv.
