Meta-Path Methods for Prioritizing Candidate Disease miRNAs.

Zhang, X; Zou, Q; Rodriguez-Paton, A; Zeng, X

Meta-Path Methods for Prioritizing Candidate Disease miRNAs.

Zhang, X

Zou, Q Rodriguez-Paton, A Zeng, X

Permalink

Publisher:: IEEE COMPUTER SOC
Publication Type:: Journal Article
Citation:: IEEE/ACM Trans Comput Biol Bioinform, 2019, 16, (1), pp. 283-291
Issue Date:: 2019-01

Closed Access

	Filename	Description	Size
	Meta-Path_Methods_for_Prioritizing_Candidate_Disease_miRNAs.pdf	Published version	659.36 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, X https://orcid.org/0000-0002-3089-9809
dc.contributor.author	Zou, Q
dc.contributor.author	Rodriguez-Paton, A
dc.contributor.author	Zeng, X
dc.date.accessioned	2022-10-30T00:51:53Z
dc.date.available	2022-10-30T00:51:53Z
dc.date.issued	2019-01
dc.identifier.citation	IEEE/ACM Trans Comput Biol Bioinform, 2019, 16, (1), pp. 283-291
dc.identifier.issn	1545-5963
dc.identifier.issn	1557-9964
dc.identifier.uri	http://hdl.handle.net/10453/162882
dc.description.abstract	MicroRNAs (miRNAs) play critical roles in regulating gene expression at post-transcriptional levels. Numerous experimental studies indicate that alterations and dysregulations in miRNAs are associated with important complex diseases, especially cancers. Predicting potential miRNA-disease association is beneficial not only to explore the pathogenesis of diseases, but also to understand biological processes. In this work, we propose two methods that can effectively predict potential miRNA-disease associations using our reconstructed miRNA and disease similarity networks, which are based on the latest experimental data. We reconstruct a miRNA functional similarity network using the following biological information: the miRNA family information, miRNA cluster information, experimentally valid miRNA-target association and disease-miRNA information. We also reconstruct a disease similarity network using disease functional information and disease semantic information. We present Katz with specific weights and Katz with machine learning, on the comprehensive heterogeneous network. These methods, which achieve corresponding AUC values of 0.897 and 0.919, exhibit performance superior to the existing methods. Comprehensive data networks and reasonable considerations guarantee the high performance of our methods. Contrary to several methods, which cannot work in such situations, the proposed methods also predict associations for diseases without any known related miRNAs. A web service for the download and prediction of relationships between diseases and miRNAs is available at http://lab.malab.cn/soft/MDPredict/.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	IEEE COMPUTER SOC
dc.relation.ispartof	IEEE/ACM Trans Comput Biol Bioinform
dc.relation.isbasedon	10.1109/TCBB.2017.2776280
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	01 Mathematical Sciences, 06 Biological Sciences, 08 Information and Computing Sciences
dc.subject.classification	Bioinformatics
dc.subject.mesh	Databases, Genetic
dc.subject.mesh	Disease Progression
dc.subject.mesh	Humans
dc.subject.mesh	MicroRNAs
dc.subject.mesh	Models, Statistical
dc.subject.mesh	Neoplasms
dc.subject.mesh	ROC Curve
dc.subject.mesh	Systems Biology
dc.subject.mesh	Humans
dc.subject.mesh	Neoplasms
dc.subject.mesh	Disease Progression
dc.subject.mesh	MicroRNAs
dc.subject.mesh	Models, Statistical
dc.subject.mesh	ROC Curve
dc.subject.mesh	Systems Biology
dc.subject.mesh	Databases, Genetic
dc.title	Meta-Path Methods for Prioritizing Candidate Disease miRNAs.
dc.type	Journal Article
utslib.citation.volume	16
utslib.location.activity	United States
utslib.for	01 Mathematical Sciences
utslib.for	06 Biological Sciences
utslib.for	08 Information and Computing Sciences
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2022-10-30T00:51:52Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	16
utslib.citation.issue	1

Abstract:

MicroRNAs (miRNAs) play critical roles in regulating gene expression at post-transcriptional levels. Numerous experimental studies indicate that alterations and dysregulations in miRNAs are associated with important complex diseases, especially cancers. Predicting potential miRNA-disease association is beneficial not only to explore the pathogenesis of diseases, but also to understand biological processes. In this work, we propose two methods that can effectively predict potential miRNA-disease associations using our reconstructed miRNA and disease similarity networks, which are based on the latest experimental data. We reconstruct a miRNA functional similarity network using the following biological information: the miRNA family information, miRNA cluster information, experimentally valid miRNA-target association and disease-miRNA information. We also reconstruct a disease similarity network using disease functional information and disease semantic information. We present Katz with specific weights and Katz with machine learning, on the comprehensive heterogeneous network. These methods, which achieve corresponding AUC values of 0.897 and 0.919, exhibit performance superior to the existing methods. Comprehensive data networks and reasonable considerations guarantee the high performance of our methods. Contrary to several methods, which cannot work in such situations, the proposed methods also predict associations for diseases without any known related miRNAs. A web service for the download and prediction of relationships between diseases and miRNAs is available at http://lab.malab.cn/soft/MDPredict/.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/162882