School of Medicine, Tsinghua University, 100084, Beijing, China.
Centre for Life Sciences, Tsinghua University, 100084, Beijing, China.
Commun Biol. 2024 Jun 4;7(1):684. doi: 10.1038/s42003-024-06380-6.
Identifying interactions between T-cell receptors (TCRs) and immunogenic peptides holds profound implications across diverse research domains and clinical scenarios. Unsupervised clustering models (UCMs) cannot predict peptide-TCR binding directly, while supervised predictive models (SPMs) often face challenges in identifying antigens previously unencountered by the immune system or possessing limited TCR binding repertoires. Therefore, we propose HeteroTCR, an SPM based on Heterogeneous Graph Neural Network (GNN), to accurately predict peptide-TCR binding probabilities. HeteroTCR captures within-type (TCR-TCR or peptide-peptide) similarity information and between-type (peptide-TCR) interaction insights for predictions on unseen peptides and TCRs, surpassing limitations of existing SPMs. Our evaluation shows HeteroTCR outperforms state-of-the-art models on independent datasets. Ablation studies and visual interpretation underscore the Heterogeneous GNN module's critical role in enhancing HeteroTCR's performance by capturing pivotal binding process features. We further demonstrate the robustness and reliability of HeteroTCR through validation using single-cell datasets, aligning with the expectation that pMHC-TCR complexes with higher predicted binding probabilities correspond to increased binding fractions.
鉴定 T 细胞受体 (TCRs) 与免疫原性肽之间的相互作用在不同的研究领域和临床情况下都具有深远的意义。无监督聚类模型 (UCMs) 不能直接预测肽-TCR 结合，而监督预测模型 (SPMs) 通常在识别免疫系统以前未遇到或具有有限 TCR 结合谱的抗原时面临挑战。因此，我们提出了基于异质图神经网络 (GNN) 的 SPM HeteroTCR，以准确预测肽-TCR 结合概率。HeteroTCR 捕获了同种型内（TCR-TCR 或肽-肽）相似性信息和异型间（肽-TCR）相互作用的见解，可用于预测未见的肽和 TCR，克服了现有 SPM 的局限性。我们的评估表明，HeteroTCR 在独立数据集上优于最先进的模型。消融研究和可视化解释强调了异质 GNN 模块在通过捕获关键结合过程特征来增强 HeteroTCR 性能方面的关键作用。我们通过使用单细胞数据集进行验证进一步证明了 HeteroTCR 的稳健性和可靠性，这与预期一致，即具有较高预测结合概率的 pMHC-TCR 复合物对应于增加的结合分数。
