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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bui, Tien-Cuong, Chung, Injae, Lee, Wonjun, Ko, Junsu, Lee, Juyong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912967717552128
author Bui, Tien-Cuong
Chung, Injae
Lee, Wonjun
Ko, Junsu
Lee, Juyong
author_facet Bui, Tien-Cuong
Chung, Injae
Lee, Wonjun
Ko, Junsu
Lee, Juyong
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2603_14870
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
Bui, Tien-Cuong
Chung, Injae
Lee, Wonjun
Ko, Junsu
Lee, Juyong
Machine Learning
Artificial Intelligence
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).
title IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.14870