Heterogeneous Types of miRNA-Disease Associations Stratified by Multi-Layer Network Embedding and Prediction.
Heterogeneous Types of miRNA-Disease Associations Stratified by Multi-Layer Network Embedding and Prediction.
复制标题
通过多层网络嵌入和预测分层的异质类型 miRNA 疾病关联
DOI：
10.3390/biomedicines9091152
复制
发表时间：
2021-09-03
期刊：
影响因子：
4.7
通讯作者：
Anh V
中科院分区：
文献类型：
--
作者：
Yu DL;Yu ZG;Han GS;Li J;Anh V
在实验支持的人类miRNA-疾病关联数据库（HMDD）中记录的许多疾病中，miRNA功能异常被广泛参与。其中一些关联是复杂的：同一疾病可能存在多达五种不同的miRNA关联类型，包括遗传学型、表观遗传学型、循环miRNA型、miRNA组织表达型和miRNA-靶标相互作用型。当已知mirna -疾病对的一种关联类型时，预测任何其他类型的关联对于更好地了解疾病机制是很重要的。揭示目前未关联的mirna与疾病的关联更为重要。最近提出了通过受限玻尔兹曼机、标签传播理论和张量补全算法来预测mirna -疾病对关联类型的方法。他们都没有利用mirna -疾病关联网络的非线性特征来提高性能。我们建议使用属性多层异构网络嵌入，从每种关联类型中学习mirna和疾病的潜在表征，然后预测所有mirna -疾病对的关联类型的存在性。通过在数据库HMDD v3.2上进行10倍交叉验证，将该方法与两种最新方法的性能进行了比较，验证了该方法在不同设置下的优越预测效果。此外，我们在HMDD数据库之外做出的真实预测都可以被NCBI文献验证，证实我们的方法能够准确预测mirna与疾病的新关联及其关联类型。
Abnormal miRNA functions are widely involved in many diseases recorded in the database of experimentally supported human miRNA-disease associations (HMDD). Some of the associations are complicated: There can be up to five heterogeneous association types of miRNA with the same disease, including genetics type, epigenetics type, circulating miRNAs type, miRNA tissue expression type and miRNA-target interaction type. When one type of association is known for an miRNA-disease pair, it is important to predict any other types of the association for a better understanding of the disease mechanism. It is even more important to reveal associations for currently unassociated miRNAs and diseases. Methods have been recently proposed to make predictions on the association types of miRNA-disease pairs through restricted Boltzman machines, label propagation theories and tensor completion algorithms. None of them has exploited the non-linear characteristics in the miRNA-disease association network to improve the performance. We propose to use attributed multi-layer heterogeneous network embedding to learn the latent representations of miRNAs and diseases from each association type and then to predict the existence of the association type for all the miRNA-disease pairs. The performance of our method is compared with two newest methods via 10-fold cross-validation on the database HMDD v3.2 to demonstrate the superior prediction achieved by our method under different settings. Moreover, our real predictions made beyond the HMDD database can be all validated by NCBI literatures, confirming that our method is capable of accurately predicting new associations of miRNAs with diseases and their association types as well.
登录
查看更多内容
DOI：
10.1145/2939672.2939754
发表时间：
2016-08
期刊：
KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
影响因子：
--
作者：
Grover A;Leskovec J
通讯作者：
Leskovec J
影响因子：
4.8
作者：
Fujita, Yasunori;Kojima, Keitaro;Ito, Masafumi
通讯作者：
Ito, Masafumi
具有关系约束的张量分解，用于预测多种类型的 microRNA 疾病关联。
影响因子：
9.5
作者：
Huang, Feng;Yue, Xiang;Zhang, Wen
通讯作者：
Zhang, Wen
影响因子：
9.5
作者：
Chen, Xing;Xie, Di;You, Zhu-Hong
通讯作者：
You, Zhu-Hong
DOI：
10.1073/pnas.0804549105
发表时间：
2008-07-29
影响因子：
11.1
作者：
Mitchell, Patrick S.;Parkin, Rachael K.;Tewari, Muneesh
通讯作者：
Tewari, Muneesh