Department of Computer Science and Engineering, University of Texas at Arlington, 701 S. Nedderman Drive, TX 76019, United States.
Public Health, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, TX 75390, United States.
Brief Bioinform. 2024 May 23;25(4). doi: 10.1093/bib/bbae343.
The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR-epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR-epitope interaction networks. In this study, we present $GTE$, a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR-epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR-epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE.
T 细胞受体（TCR）与主要组织相容性复合物分子（MHC）呈递的肽（表位）之间的相互作用是免疫反应的基础。准确预测 TCR-表位相互作用对于深入了解各种疾病及其预防和治疗至关重要。现有的方法主要依赖于基于序列的方法，忽略了 TCR-表位相互作用网络的固有拓扑结构。在这项研究中，我们提出了 GTE，这是一种基于归纳学习的新型异构图神经网络模型，用于捕获 TCR 和表位之间的拓扑结构。此外，我们通过提出一种动态边更新策略来解决图中构建负样本的挑战，通过非结合 TCR-表位对增强模型学习。此外，为了克服数据不平衡，我们将 Deep AUC Maximization 策略应用于图领域。我们在四个公共数据集上进行了广泛的实验，以证明在预测 TCR-表位相互作用中探索潜在拓扑结构的优越性，说明了深入研究复杂分子网络的好处。实现代码和数据可在 https://github.com/uta-smile/GTE 上获得。
