Niu Mengting, Wang Chunyu, Chen Yaojia, Zou Quan, Luo Ximei
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, China.
Macao Polytechnic University, Gomes Street, Macau Peninsula, Macau, 999078, China.
BMC Biol. 2025 May 14;23(1):131. doi: 10.1186/s12915-025-02223-w.
Different expression levels of circular RNAs (circRNAs) affect the sensitivity of human cells to drugs, thus producing different responses to the therapeutic effects of drugs. Using traditional biomedical experiments to discover and confirm sensitivity relationships is not only time-consuming but also costly. Therefore, developing an effective method to accurately predict new associations between circRNAs and drug sensitivity is crucial and urgent. Therefore, we constructed a heterogeneous graph network MiGNN2CDS on the basis of multi-instance learning (MIL).
We first extracted similar features of circRNAs and drugs and the structural features of drugs to construct a heterogeneous network. To learn the deep embedding features of the heterogeneous network, we designed a heterogeneous graph convolutional network (GCN) architecture. By introducing instance learning, we subsequently designed a pseudo-metapath instance generator and a bidirectional translation embedding projector BiTrans to learn the metapath-level representation of circRNA-drug pairs. Finally, an interpretable multiscale attention network joint predictor was designed to achieve accurate prediction and interpretable analysis of circRNA-drug sensitivity associations.
MiGNN2CDS achieves better prediction accuracy than many state-of-the-art models do. Case studies show that MiGNN2CDS can effectively predict unknown associations, and the model interpretability of MiGNN2CDS is verified by high-confidence meta-path analysis. The code and data are available at https://github.com/nmt315320/MiGNN2CDS.git .
环状RNA（circRNA）的不同表达水平会影响人类细胞对药物的敏感性，从而对药物治疗效果产生不同反应。利用传统生物医学实验来发现和确认敏感性关系不仅耗时，而且成本高昂。因此，开发一种有效方法来准确预测circRNA与药物敏感性之间的新关联至关重要且迫在眉睫。因此，我们基于多实例学习（MIL）构建了一个异构图网络MiGNN2CDS。
我们首先提取circRNA和药物的相似特征以及药物的结构特征来构建异质网络。为了学习异质网络的深度嵌入特征，我们设计了一种异构图卷积网络（GCN）架构。通过引入实例学习，我们随后设计了一个伪元路径实例生成器和一个双向翻译嵌入投影仪BiTrans来学习circRNA-药物对的元路径级表示。最后，设计了一个可解释的多尺度注意力网络联合预测器，以实现对circRNA-药物敏感性关联的准确预测和可解释分析。
MiGNN2CDS比许多现有先进模型具有更好的预测准确性。案例研究表明，MiGNN2CDS可以有效预测未知关联，并且通过高置信度元路径分析验证了MiGNN2CDS的模型可解释性。代码和数据可在https://github.com/nmt315320/MiGNN2CDS.git获取。
