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

Abstract 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.

Authors

Institutions

Publication Details

Journal
ACS Omega
Published
2026-11-12
DOI
https://doi.org/10.1021/acsomega.6c09062
Primary Topic
Protein Structure and Dynamics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

An Gong, Bing Yu, Shuhui Wu, Yuyang Zhan et al.
ACS Omega
Protein Structure and Dynamics
article

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

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

Abstract

Abstract 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.

ACS Omega
Army Medical University (CN), Xinjiang Medical University (CN), Xinqiao Hospital (CN), China University of Petroleum, East China (CN), Second Affiliated Hospital of Xinjiang Medical University (CN)
Chongqing Science and Technology Commission
Protein Structure and Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon