用生成数据增强解决抗体抗原结合预测难题
IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
- 构建合成抗原模型库，弥补实验结构数据不足
- 结合几何与进化特征，实现高精度结合构象识别
- 适合抗体药物设计与高通量筛选研究者使用
由于实验解析的抗体-抗原复合物稀缺，且从头预测抗体结构精度有限，抗体-抗原结合预测仍面临重大挑战。我们提出IgPose，一个通用的结合构象识别与评分框架，基于生成式数据增强流程。为缓解数据匮乏，构建了高保真合成伪构象数据库SIDD。IgPose融合等变图神经网络、ESM-2嵌入和门控循环单元，协同捕捉几何与进化特征。采用面向接口的k-hop采样与生物引导池化策略，提升跨不同界面的泛化能力。框架包含两个子网络：IgPoseClassifier用于结合构象判别，IgPoseScore用于预测DockQ得分，在内部测试集和CASP-16基准上表现优于物理模型与深度学习基线。IgPose可作为高通量抗体发现流程中的可靠计算工具，实现精准构象筛选与排序。代码已开源（https://github.com/arontier/igpose）。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。