EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

TRACE-Net: A Physics-Inspired Geometric Deep Learning Framework for Antibody–Antigen Docking Ranking

An Gong, Peidong Bai, Bing Yu, Yuyang Zhan, Yong Liu, Shuhui Wu

ACS Omega · 12.11.2026

DOI: 10.1021/acsomega.6c09062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Omega, online erschienen am 12.11.2026. Verfasst von An Gong und 5 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Chongqing Municipal Science and Technology Bureau.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Elucidating antibody–antigen interactions at atomic resolution is fundamental for therapeutic antibody design. However, accurately discriminating near-native conformations from massive decoy pools remains a critical bottleneck for current high-accuracy structure prediction, as existing scoring functions often fail to capture complex interfacial interactions and monomeric deformation. To address this challenge, we present TRACE-Net, a physics-inspired geometric deep learning framework. TRACE-Net introduces three innovative modules: Context-Aware Edge Feature Recalibration (CEER), Internal Deformation-Aware Gated Fusion (IDGF), and Top-Weighted Combined Ranking Loss (TWCRL). Trained on a comprehensive data set of 1442 complexes, the model effectively reduces geometric noise and quantifies spatial divergence as a structural indicator of localized geometric deformation forced during flexible interface adaptation. Experimental results demonstrate that TRACE-Net effectively mitigates the severe ranking inversion of near-native decoys, yielding a competitive improvement in the Top-1 success rate, particularly on challenging targets. Overall, this framework offers a sensitive and informative scoring strategy for assessing predicted structures and advancing computational immunology.

Förderung

  • Chongqing Municipal Science and Technology Bureau

Zitieren

APA

Gong, A., Bai, P., Yu, B., Zhan, Y., Liu, Y., & Wu, S. (2026). TRACE-Net: A Physics-Inspired Geometric Deep Learning Framework for Antibody–Antigen Docking Ranking. ACS Omega. https://doi.org/10.1021/acsomega.6c09062

Vancouver

Gong A, Bai P, Yu B, Zhan Y, Liu Y, Wu S. TRACE-Net: A Physics-Inspired Geometric Deep Learning Framework for Antibody–Antigen Docking Ranking. ACS Omega. 2026. doi:10.1021/acsomega.6c09062

BibTeX
@article{Gong2026,
  author = {Gong, An and Bai, Peidong and Yu, Bing and Zhan, Yuyang and Liu, Yong and Wu, Shuhui},
  title = {TRACE-Net: A Physics-Inspired Geometric Deep Learning Framework for Antibody–Antigen Docking Ranking},
  journal = {ACS Omega},
  year = {2026},
  doi = {10.1021/acsomega.6c09062}
}
Kostenlos starten →