Scholarlink

Background <p>Accumulating evidence demonstrates that microRNA (miRNA) dysregulation drives the pathogenesis of diverse human diseases via intricate, context-dependent molecular mechanisms. Hence, prediction of miRNA-disease association types is a critical prerequisite for dissecting functional roles of miRNAs in disease initiation and progression. Although computational methods offer cost-effective, time-efficient alternatives to wet-lab experiments for miRNA-disease association type prediction, most of them are hampered by three key limitations: excessive reliance on association-derived similarity metrics gives rise to quantification bias, traditional pairwise graph architectures inadequately capture high-order biological interactions, and existing representation learning strategies fail to generate consistent embeddings across heterogeneous views and modalities.</p> Results <p>To address these issues, this study presents DHGCMDA, a dual-view heterogeneous graph contrastive learning framework for miRNA-disease association type prediction. Specifically, dual-view hypergraphs are first constructed based on heterogeneous similarity data to avoid excessive reliance on association-derived similarity metrics. A hypergraph convolutional network is then employed to capture high-order topological relationships between miRNAs and diseases, with its convolution cooperatively integrated with contrastive learning, intra-modality for cross-view consistency and cross-modality for embedding space alignment, to enhance feature representation quality. Finally, an attention-guided adaptive view fusion strategy dynamically weights and integrates distinct view representations, and type-aware message passing via heterogeneous graph Transformer simultaneously enables prediction of association presence and functional types. 5-fold cross-validation on HMDD v2.0 and v3.2 datasets demonstrates that DHGCMDA outperforms several state-of-the-art methods. Furthermore, case studies on breast neoplasms and hepatocellular carcinoma reveal that most predicted association types are corroborated by published literature, thereby validating the efficacy of DHGCMDA in miRNA-disease association type prediction.</p> Conclusions <p>DHGCMDA exhibits robust discriminative power and generalization capability, providing a reliable computational alternative for miRNA-disease association type prediction. The source code is publicly available at <a href="https://github.com/CDMBlab/DHGCMDA">https://github.com/CDMBlab/DHGCMDA</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DHGCMDA: a dual-view heterogeneous graph contrastive learning framework for miRNA-disease association type prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月1日

查看全文
  • Yan Sun,
  • Fanyu Zhang,
  • Shijia Yan,
  • Xiaotong Kong,
  • Hanxiang Wang,
  • Junliang Shang,
  • Jin-Xing Liu

摘要

Background

Accumulating evidence demonstrates that microRNA (miRNA) dysregulation drives the pathogenesis of diverse human diseases via intricate, context-dependent molecular mechanisms. Hence, prediction of miRNA-disease association types is a critical prerequisite for dissecting functional roles of miRNAs in disease initiation and progression. Although computational methods offer cost-effective, time-efficient alternatives to wet-lab experiments for miRNA-disease association type prediction, most of them are hampered by three key limitations: excessive reliance on association-derived similarity metrics gives rise to quantification bias, traditional pairwise graph architectures inadequately capture high-order biological interactions, and existing representation learning strategies fail to generate consistent embeddings across heterogeneous views and modalities.

Results

To address these issues, this study presents DHGCMDA, a dual-view heterogeneous graph contrastive learning framework for miRNA-disease association type prediction. Specifically, dual-view hypergraphs are first constructed based on heterogeneous similarity data to avoid excessive reliance on association-derived similarity metrics. A hypergraph convolutional network is then employed to capture high-order topological relationships between miRNAs and diseases, with its convolution cooperatively integrated with contrastive learning, intra-modality for cross-view consistency and cross-modality for embedding space alignment, to enhance feature representation quality. Finally, an attention-guided adaptive view fusion strategy dynamically weights and integrates distinct view representations, and type-aware message passing via heterogeneous graph Transformer simultaneously enables prediction of association presence and functional types. 5-fold cross-validation on HMDD v2.0 and v3.2 datasets demonstrates that DHGCMDA outperforms several state-of-the-art methods. Furthermore, case studies on breast neoplasms and hepatocellular carcinoma reveal that most predicted association types are corroborated by published literature, thereby validating the efficacy of DHGCMDA in miRNA-disease association type prediction.

Conclusions

DHGCMDA exhibits robust discriminative power and generalization capability, providing a reliable computational alternative for miRNA-disease association type prediction. The source code is publicly available at https://github.com/CDMBlab/DHGCMDA.