iPiDA-GCN: Identification of piRNA-disease associations based on Graph Convolutional Network.
iPiDA-GCN: Identification of piRNA-disease associations based on Graph Convolutional Network.
复制标题
DOI：
10.1371/journal.pcbi.1010671
复制
发表时间：
2022-10
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
Piwi相互作用RNA（piRNA）在各种疾病的进展中起关键作用。准确鉴定piRNA与疾病之间的关联对于诊断和鉴定疾病是重要的。尽管已经提出了一些计算方法来检测piRNA-疾病关联，但是由于有限的训练数据和不充分的关联表示，这些方法有效地捕获piRNA和疾病之间的非线性和复杂关系是具有挑战性的。随着piRNA-疾病关联数据的增长，有可能设计更复杂的机器学习方法来解决这个问题。在这项研究中，我们提出了一种名为iPiDA-GCN的计算方法，用于基于图卷积网络（GCN）的piRNA-疾病关联识别。iPiDA-GCN预测器基于皮尔纳序列信息、疾病语义信息和已知的piRNA-疾病关联来构建图。使用两个GCN（Asso-GCN和Sim-GCN）通过捕获来自piRNA-疾病相互作用网络和两个相似性网络的关联模式来提取piRNA和疾病的特征。GCN可以从这些网络中捕获复杂的网络结构信息，并学习有区别的特征。最后，利用全连接网络和内部产生作为输出模块来预测piRNA-疾病关联得分。实验结果表明，iPiDA-GCN取得了更好的性能比其他国家的最先进的方法，受益于鉴别特征提取Asso-GCN和Sim-GCN。iPiDA-GCN预测因子能够检测新的piRNA-疾病关联，以揭示RNA水平上的潜在发病机制。数据和源代码可在http://bliulab.net/iPiDA-GCN/上获得。PiRNA在多种生物学过程中发挥重要作用，其异常表达可能导致疾病的发生。同时，一些生物学实验表明piRNA具有成为诊断和治疗疾病的生物标志物或治疗靶标的潜力。已经提出了一些计算方法来检测piRNA-疾病关联，并提供了有希望的结果。然而，随着越来越多的发现piRNA-疾病的关联，现有的方法无法捕捉非线性和复杂的关联模式，因为有限的训练数据和不足的关联表示。针对上述问题，提出了一种基于图卷积网络的piRNA-疾病关联识别新算法iPiDA-GCN。iPiDA-GCN构建了异构生物网络，并设计了Asso-GCN和Sim-GCN模块，用于学习不同生物网络中隐藏的关联模式。实验结果表明，iPiDA-GCN能够检测新的piRNA-疾病关联，并且优于其他最先进的方法。
Piwi-interacting RNAs (piRNAs) play a critical role in the progression of various diseases. Accurately identifying the associations between piRNAs and diseases is important for diagnosing and prognosticating diseases. Although some computational methods have been proposed to detect piRNA-disease associations, it is challenging for these methods to effectively capture nonlinear and complex relationships between piRNAs and diseases because of the limited training data and insufficient association representation. With the growth of piRNA-disease association data, it is possible to design a more complex machine learning method to solve this problem. In this study, we propose a computational method called iPiDA-GCN for piRNA-disease association identification based on graph convolutional networks (GCNs). The iPiDA-GCN predictor constructs the graphs based on piRNA sequence information, disease semantic information and known piRNA-disease associations. Two GCNs (Asso-GCN and Sim-GCN) are used to extract the features of both piRNAs and diseases by capturing the association patterns from piRNA-disease interaction network and two similarity networks. GCNs can capture complex network structure information from these networks, and learn discriminative features. Finally, the full connection networks and inner production are utilized as the output module to predict piRNA-disease association scores. Experimental results demonstrate that iPiDA-GCN achieves better performance than the other state-of-the-art methods, benefitted from the discriminative features extracted by Asso-GCN and Sim-GCN. The iPiDA-GCN predictor is able to detect new piRNA-disease associations to reveal the potential pathogenesis at the RNA level. The data and source code are available at http://bliulab.net/iPiDA-GCN/. PiRNAs play critical roles in various biological processes and the abnormal expression of piRNAs may lead to diseases. Meanwhile, several biological experiments show that piRNAs have the potential to be biomarkers or therapeutic targets to diagnose and prognosticate diseases. Some computational methods have been proposed to detect piRNA-disease associations, and provide promising results. However, with the increasing discovery of piRNA-disease associations, the existing methods fail to capture nonlinear and complex association patterns because of the limited training data and insufficient association representation. To overcome above questions, a novel computational method named iPiDA-GCN is proposed for piRNA-disease association identification based on graph convolutional networks. iPiDA-GCN constructs heterogeneous biological networks, and designs Asso-GCN and Sim-GCN modules for learning hidden association patterns in different biological networks. The experimental results show that iPiDA-GCN is able to detect new piRNA-disease associations, and outperforms the other state-of-the-art methods.
登录
查看更多内容
WBSMDA：miRNA 疾病关联预测的评分内和评分之间
影响因子：
4.6
作者：
Chen X;Yan CC;Zhang X;You ZH;Deng L;Liu Y;Zhang Y;Dai Q
通讯作者：
Dai Q
IRWRLDA：改进随机游走并重新启动 lncRNA 疾病关联预测
影响因子：
--
作者：
Chen X;You ZH;Yan GY;Gong DW
通讯作者：
Gong DW
影响因子：
9.5
作者：
Cai, Lijun;Lu, Changcheng;Su, Yansen
通讯作者：
Su, Yansen
使用图卷积网络完成神经归纳矩阵，用于 miRNA 疾病关联预测
影响因子：
5.8
作者：
Li, Jin;Zhang, Sai;Zhou, Wei
通讯作者：
Zhou, Wei
影响因子：
4.3
作者：
Chen, Xing;Zhu, Chi-Chi;Yin, Jun
通讯作者：
Yin, Jun