HGNNPIP: A Hybrid Graph Neural Network framework for Protein-protein Interaction Prediction

A deep understanding of Protein-protein interactions (PPIs) can provide comprehensive insights into many biological functions, thereby facilitating drug target identification and novel therapeutic design. Recent developments in artificial intelligence (AI)-driven computational methods have enabled the discovery of previously uncharacterized PPIs from large-scale interactome datasets. Almost all existing machine learning methods rely on Subcellular Localization (SL) to construct balanced datasets based on positive interactions to achieve predictions. Despite high fitting accuracy, the generalization ability of these models is questionable. To solve this problem, we analyzed existing methods and found that the high false positives in these methods are due to the bias in data distribution caused by SL. Therefore, we proposed a new strategy for negative instance sampling in PPI prediction and developed a Hybrid Graph Neural Network framework for Protein-protein Interaction Prediction (HGNNPIP). The experimental results showed that HGNNPIP works well on six benchmark datasets. Comparison analysis demonstrated that our model outperformed the other four existing methods. We also used HGNNPIP to explore the molecular contacts involved in the rice-pathogen interaction system. In vivo experiments confirmed multiple regulations related to disease resistance in rice. In summary, this study provides new insights into establishing a computational framework for PPI prediction with high reliability.

对蛋白质-蛋白质相互作用（Protein-protein Interactions, PPIs）的深入解析，可为诸多生物学功能提供全面洞察，进而助力药物靶点挖掘与新型治疗方案设计。近年来，人工智能（Artificial Intelligence, AI）驱动的计算方法取得显著进展，得以从大规模相互作用组数据中发掘此前未被表征的PPIs。当前绝大多数机器学习方法均依托亚细胞定位（Subcellular Localization, SL）构建基于阳性相互作用的平衡数据集以开展预测任务。尽管此类模型的拟合精度较高，但其泛化能力却饱受质疑。为解决该问题，我们对现有方法展开分析，发现此类模型假阳性率偏高的根源在于SL带来的数据分布偏差。据此，我们提出了一种用于PPI预测的负样本采样新策略，并开发了蛋白质相互作用预测混合图神经网络框架（Hybrid Graph Neural Network framework for Protein-protein Interaction Prediction, HGNNPIP）。实验结果表明，HGNNPIP在6个基准数据集上均表现优异。对比分析显示，我们的模型性能优于其余4种现有方法。此外，我们还利用HGNNPIP对水稻-病原体互作系统中的分子接触进行了探索，体内实验验证了多项与水稻抗病性相关的调控机制。综上，本研究为构建高可靠性的PPI预测计算框架提供了全新视角。