4.7 Article

MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph

期刊

BRIEFINGS IN BIOINFORMATICS
卷 22, 期 6, 页码 -

出版社

OXFORD UNIV PRESS
DOI: 10.1093/bib/bbab165

关键词

miRNA- disease associations; the feature and topology graph; graph convolutional network; graph sampling

资金

  1. National Science Foundation of China [32070662, 61832019, 32030063]
  2. Key Research Area Grant of the Ministry of Science and Technology of China [2016YFA0501703]
  3. Science and Technology Commission of Shanghai Municipality [19430750600]
  4. SJTU JiRLMDS Joint Research Fund
  5. Joint Research Funds for Medical and Engineering and Scientific Research at Shanghai Jiao Tong University [ZH2018QNA41, YG2019GD01, YG2019ZDA12, YG2021ZD02]

向作者/读者索取更多资源

The study introduces a novel method MDA-GCNFTG, which predicts miRNA-disease associations (MDAs) based on Graph Convolutional Networks through graph sampling, achieving significantly superior performance compared to other methods. By considering disease semantic similarity, miRNA functional similarity, and Gaussian interaction profile kernel similarity, the method achieves satisfactory results in MDA prediction.
Accurate identification of the miRNA-disease associations (MDAs) helps to understand the etiology and mechanisms of various diseases. However, the experimental methods are costly and time-consuming. Thus, it is urgent to develop computational methods towards the prediction of MDA5. Based on the graph theory, the MDA prediction is regarded as a node classification task in the present study. To solve this task, we propose a novel method MDA-GCNFTG, which predicts MDA5 based on Graph Convolutional Networks (GCNs) via graph sampling through the Feature and Topology Graph to improve the training efficiency and accuracy. This method models both the potential connections of feature space and the structural relationships of MDA data. The nodes of the graphs are represented by the disease semantic similarity, miRNA functional similarity and Gaussian interaction profile kernel similarity. Moreover, we considered six tasks simultaneously on the MDA prediction problem at the first time, which ensure that under both balanced and unbalanced sample distribution, MDA-GCNFTG can predict not only new MDAs but also new diseases without known related miRNAs and new miRNAs without known related diseases. The results of 5-fold cross-validation show that the MDA-GCNFTG method has achieved satisfactory performance on all six tasks and is significantly superior to the classic machine learning methods and the state-of-the-art MDA prediction methods. Moreover, the effectiveness of GCNs via the graph sampling strategy and the feature and topology graph in MDA-GCNFTG has also been demonstrated. More importantly, case studies for two diseases and three miRNAs are conducted and achieved satisfactory performance.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据