GIMDA: Graphlet interaction-based MiRNA-disease association
* , Na-Na Guan
, Jian-Qiang Li
*, Gui-Ying Yan
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China
Received: July 24, 2017; Accepted: September 22, 2017
MicroRNAs (miRNAs) have been conﬁrmed to be closely related to various human complex diseases by many experimental studies. It is neces-
sary and valuable to develop powerful and effective computational models to predict potential associations between miRNAs and diseases. In
this work, we presented a prediction model of Graphlet Interaction for MiRNA-Disease Association prediction (GIMDA) by integrating the dis-
ease semantic similarity, miRNA functional similarity, Gaussian interaction proﬁle kernel similarity and the experimentally conﬁrmed miRNA-dis-
ease associations. The related score of a miRNA to a disease was calculated by measuring the graphlet interactions between two miRNAs or
two diseases. The novelty of GIMDA lies in that we used graphlet interaction to analyse the complex relationships between two nodes in a graph.
The AUCs of GIMDA in global and local leave-one-out cross-validation (LOOCV) turned out to be 0.9006 and 0.8455, respectively. The average
result of ﬁve-fold cross-validation reached to 0.8927 Æ 0.0012. In case study for colon neoplasms, kidney neoplasms and prostate neoplasms
based on the database of HMDD V2.0, 45, 45, 41 of the top 50 potential miRNAs predicted by GIMDA were validated by dbDEMC and miR2Di-
sease. Additionally, in the case study of new diseases without any known associated miRNAs and the case study of predicting potential miRNA-
disease associations using HMDD V1.0, there were also high percentages of top 50 miRNAs veriﬁed by the experimental literatures.
MicroRNAs (miRNAs) are a category of single-stranded non-coding
RNAs which contain about 20~25 nucleotides in length. They play an
important role in the regulation of gene expression at the post-tran-
scriptional and translational level by binding to the 3
regions (UTRs) of the target mRNAs [1–4]. MiRNAs have been
detected in various organisms ranging from viruses and microbes to
eukaryotic organisms and their number have reached to 28645 (2588
for human) in the latest release of miRBase [5–7]. Many studies have
implied that miRNAs participate in manifold biological processes,
such as cell proliferation , development , apoptosis , differ-
entiation , signal transduction  and so on. Therefore, more
and more evidences have conﬁrmed that miRNAs are closely related
to many kinds of human diseases [13–16]. For example, Heegaard
et al.  developed a method to use quantitative real-time PCR
(qRT-PCR) to measure the circulating levels of 30 miRNAs and found
that the expressions of miR-146b, miR-221, let-7a, miR-155,
miR-17-5p, miR-27a and miR-106a were signiﬁcantly reduced in the
serum of non-small cell lung cancer (NSCLC) cases although miR-
29c was much increased. Meanwhile, they also obtained evidence that
expression of let-7b was associated with prognosis in NSCLC.
Besides, authors of Ref.  and  reported a connection between
miR-137, miR-181c, miR-9, miR-29a/b and Alzheimer’s disease (AD)
and concluded that these miRNAs could be treated as diagnostic
markers for AD. In addition, miR-17~92 cluster was found to be up-
regulated in polycystic kidney disease (PKD) and could be identiﬁed
as a therapeutic target in PKD . Most recently, using qRT-PCR
analyses, studies have shown that peripheral blood miRNA-720 and
miRNA-1246 might be considered as a promoting factor in the devel-
opment of multiple myeloma (MM) and hence could be used as diag-
nostic factor, therapeutic effect evaluator and prognostic indicator in
the prognosis of MM . Although experiments have achieved many
signiﬁcant results, they are expensive and time-consuming.
*Correspondence to: Xing CHEN
ª 2017 The Authors.
Journal of Cellular and Molecular Medicine published by John Wiley & Sons Ltd and Foundation for Cellular and Molecular Medicine.
This is an open access article under the terms of the Creative Commons Attribution License, which permits use,
distribution and reproduction in any medium, provided the original work is properly cited.
J. Cell. Mol. Med. Vol 22, No 3, 2018 pp. 1548-1561