Format

Send to

Choose Destination
BMC Bioinformatics. 2019 Sep 12;20(1):468. doi: 10.1186/s12859-019-3063-3.

A network embedding-based multiple information integration method for the MiRNA-disease association prediction.

Author information

1
School of Computer Science, Wuhan University, Wuhan, 430072, China.
2
School of Mathematics and Statistics, South-Central University for Nationalities, Wuhan, 430074, China.
3
College of Informatics, Huazhong Agricultural University, Wuhan, 430070, China. zhangwen@mail.hzau.edu.cn.
4
School of Computer Science, Wuhan University, Wuhan, 430072, China. leexh@whu.edu.cn.

Abstract

BACKGROUND:

MiRNAs play significant roles in many fundamental and important biological processes, and predicting potential miRNA-disease associations makes contributions to understanding the molecular mechanism of human diseases. Existing state-of-the-art methods make use of miRNA-target associations, miRNA-family associations, miRNA functional similarity, disease semantic similarity and known miRNA-disease associations, but the known miRNA-disease associations are not well exploited.

RESULTS:

In this paper, a network embedding-based multiple information integration method (NEMII) is proposed for the miRNA-disease association prediction. First, known miRNA-disease associations are formulated as a bipartite network, and the network embedding method Structural Deep Network Embedding (SDNE) is adopted to learn embeddings of nodes in the bipartite network. Second, the embedding representations of miRNAs and diseases are combined with biological features about miRNAs and diseases (miRNA-family associations and disease semantic similarities) to represent miRNA-disease pairs. Third, the prediction models are constructed based on the miRNA-disease pairs by using the random forest. In computational experiments, NEMII achieves high-accuracy performances and outperforms other state-of-the-art methods: GRNMF, NTSMDA and PBMDA. The usefulness of NEMII is further validated by case studies. The studies demonstrate the great potential of network embedding method for the miRNA-disease association prediction, and SDNE outperforms other popular network embedding methods: DeepWalk, High-Order Proximity preserved Embedding (HOPE) and Laplacian Eigenmaps (LE).

CONCLUSION:

We propose a new method, named NEMII, for predicting miRNA-disease associations, which has great potential to benefit the field of miRNA-disease association prediction.

KEYWORDS:

Network embedding; Random forest; miRNA-disease associations

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center