Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec 11;10:1234.
doi: 10.3389/fgene.2019.01234. eCollection 2019.

Identifying Potential miRNAs-Disease Associations With Probability Matrix Factorization

Affiliations
Free PMC article

Identifying Potential miRNAs-Disease Associations With Probability Matrix Factorization

Junlin Xu et al. Front Genet. .
Free PMC article

Abstract

In recent years, miRNAs have been verified to play an irreplaceable role in biological processes associated with human disease. Discovering potential disease-related miRNAs helps explain the underlying pathogenesis of the disease at the molecular level. Given the high cost and labor intensity of biological experiments, computational predictions will be an indispensable alternative. Therefore, we design a new model called probability matrix factorization (PMFMDA). Specifically, we first integrate miRNA and disease similarity. Next, the known association matrix and integrated similarity matrix are utilized to construct a probability matrix factorization algorithm to identify potentially relevant miRNAs for disease. We find that PMFMDA achieves reliable performance in the frameworks of global leave-one-out cross validation (LOOCV) and 5-fold cross validation (AUCs are 0.9237 and 0.9187, respectively) in the HMDD (V2.0) dataset, significantly outperforming a few state-of-the-art methods including CMFMDA, IMCMDA, NCPMDA, RLSMDA, and RWRMDA. In addition, case studies show that PMFMDA has good predictive performance for new associations, and the evidence can be identified by literature mining.

Keywords: association prediction; diseases; miRNAs; probabilistic matrix factorization; receiver operating characteristic curve (ROC).

Figures

Figure 1
Figure 1
The workflow of PMFMDA is used to infer disease-associated unknown miRNAs.
Figure 2
Figure 2
The ROC curves for PMFMDA and benchmark algorithms for 5-fold CV and global LOOCV.
Figure 3
Figure 3
The PR curves for PMFMDA and benchmark algorithms for 5-fold CV.
Figure 4
Figure 4
Performance evaluation of PMFMDA in two situations for 5-fold cross validation. (1) PMFMDA with similarity information; (2) PMFMDA without similarity information.
Figure 5
Figure 5
The network of the top 20 predicted associations for the three selected diseases via PMFMDA.

Similar articles

See all similar articles

Cited by 1 article

References

    1. Azmi A. S. (2012). Systems biology in cancer research and drug discovery. Springer. 10.1007/978-94-007-4819-4 - DOI
    1. Bandyopadhyay S., Mitra R., Maulik U., Zhang M. Q. (2010). Development of the human cancer microRNA network. Silence 1, 6. 10.1186/1758-907X-1-6 - DOI - PMC - PubMed
    1. Chen X., Yan G. Y. (2014). Semi-supervised learning for potential human microRNA-disease associations inference. Sci. Rep. 4, 5501. 10.1038/srep05501 - DOI - PMC - PubMed
    1. Chen H., Zhang Z. (2013). Similarity-based methods for potential human microRNA-disease association prediction. BMC Med. Genomics 6. 10.1186/1755-8794-6-12 - DOI - PMC - PubMed
    1. Chen X., Liu M. X., Yan G. Y. (2012). RWRMDA: predicting novel human microRNA-disease associations. Mol. Biosyst. 8, 2792–2798. 10.1039/c2mb25180a - DOI - PubMed

LinkOut - more resources

Feedback