Predicting Antibody–Antigen Mutation ΔΔ G via Side-Specific Protein Language Models and Paired Geometric Graph Learning
Journal of Chemical Information and Modeling · 14.09.2026 · 66 (17) · 11503-11526
DOI: 10.1021/acs.jcim.6c01919 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 23.08.2026. Verfasst von Wenchi Ge und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan114051, China. Hauptthemen laut MEDLINE: Mutation, Antigens, Antibodies. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Science and Technology Plan Project of Liaoning Province, Fundamental Research Funds for the Liaoning Universities.
Abstract (Originalsprache)
Mutation-induced changes in binding free energy (ΔΔG) at antibody–antigen interfaces are important for antibody optimization, mutational scanning, and viral immune escape assessment. However, computational prediction remains challenging because antibodies and antigens have distinct sequence backgrounds, mutation effects are often localized at interfaces, and related complexes may remain across training and evaluation partitions. We present AbAgMut-GNN as a task-oriented paired graph framework that coordinates established sequence and geometric learning components around explicit comparison of wild-type (WT) and mutant (MUT) antibody–antigen complexes. AntiBERTy and ESM2 provide frozen residue-level embeddings for antibody and antigen chains, respectively, while mutation-centered, interface-aware, paired-residue, and contact-delta representations capture local perturbations and interaction remodeling. We evaluate AbAgMut-GNN under four complementary internal settings, including the PDB-based split, the complex-cluster split, the antibody-family preserving validation split, and the antigen-cluster-preserving validation split. Under the complex-cluster split, AbAgMut-GNN achieves Pearson correlation coefficients of 0.5841 on AB-Bind and 0.5480 on SKEMPI v2.0. External validation on SARS-CoV-2 and influenza antibody–antigen systems further shows useful mutation-effect correlation trends, although absolute-error performance varies across target systems. Contact-masking and residue-class enrichment analyses indicate that model-derived importance patterns are associated with biologically relevant interface interactions. Overall, AbAgMut-GNN is best viewed as a task-oriented computational tool for trend-level mutation ranking and pre-experimental candidate prioritization rather than as a high-precision substitute for quantitative biophysical measurement.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan114051, China.
- UCSC Baskin School of Engineering, University of California, Santa Cruz95054, United States.
ORCID-Profile: Qi Zhao
Förderung
- Science and Technology Plan Project of Liaoning Province
- Fundamental Research Funds for the Liaoning Universities
Zitieren
APA
Ge, W., Yu, Q., Shuai, J., & Zhao, Q. (2026). Predicting Antibody–Antigen Mutation ΔΔ G via Side-Specific Protein Language Models and Paired Geometric Graph Learning. Journal of Chemical Information and Modeling, 66(17), 11503-11526. https://doi.org/10.1021/acs.jcim.6c01919
Vancouver
Ge W, Yu Q, Shuai J, Zhao Q. Predicting Antibody–Antigen Mutation ΔΔ G via Side-Specific Protein Language Models and Paired Geometric Graph Learning. Journal of Chemical Information and Modeling. 2026;66(17):11503-11526. doi:10.1021/acs.jcim.6c01919
BibTeX
@article{Ge2026,
author = {Ge, Wenchi and Yu, Qijia and Shuai, Jincen and Zhao, Qi},
title = {Predicting Antibody–Antigen Mutation ΔΔ G via Side-Specific Protein Language Models and Paired Geometric Graph Learning},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {17},
pages = {11503--11526},
doi = {10.1021/acs.jcim.6c01919}
}
EUVIMED