Research

Paper

TESTING March 16, 2026

IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction

Authors

Tien-Cuong Bui, Injae Chung, Wonjun Lee, Junsu Ko, Juyong Lee

Abstract

Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction. We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks--IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation--and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. IgPose is available on GitHub (https://github.com/arontier/igpose).

Metadata

arXiv ID: 2603.14870
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.14870v1</id>\n    <title>IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction</title>\n    <updated>2026-03-16T06:16:03Z</updated>\n    <link href='https://arxiv.org/abs/2603.14870v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.14870v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction. We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks--IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation--and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. IgPose is available on GitHub (https://github.com/arontier/igpose).</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-16T06:16:03Z</published>\n    <arxiv:comment>11 pages, 4 figures, Bioinformatics</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <arxiv:journal_ref>Bioinformatics 42 (2026) btag076</arxiv:journal_ref>\n    <author>\n      <name>Tien-Cuong Bui</name>\n    </author>\n    <author>\n      <name>Injae Chung</name>\n    </author>\n    <author>\n      <name>Wonjun Lee</name>\n    </author>\n    <author>\n      <name>Junsu Ko</name>\n    </author>\n    <author>\n      <name>Juyong Lee</name>\n    </author>\n    <arxiv:doi>10.1093/bioinformatics/btag076</arxiv:doi>\n    <link href='https://doi.org/10.1093/bioinformatics/btag076' rel='related' title='doi'/>\n  </entry>"
}