A learning-based framework for miRNA-disease association identification using neural networks

Peng, Jiajie; Hui, Weiwei; Li, Qianqian; Chen, Bolin; Hao, Jianye; Jiang, Qinghua; Shang, Xuequn; Wei, Zhongyu

doi:10.1093/bioinformatics/btz254

Cited by 152 publications

(50 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The top 3 gene classes are protein coding, pseudogene, and lncRNA genes. Although many studies have shown that non-coding RNAs play key roles in the complex regulatory networks in cell system, most of their functions are still missing (Cheng et al, 2018a;Cheng et al, 2018d;Peng et al, 2019b). Further computational methods and biological experiments are still needed to understand these unknown markers, such as using phynotypes, ontologies, deep learning methods, etc.…”

Section: Discussionmentioning

confidence: 99%

eQTLMAPT: Fast and Accurate eQTL Mediation Analysis With Efficient Permutation Testing Approaches

et al. 2020

Self Cite

View full text Add to dashboard Cite

Expression quantitative trait locus (eQTL) analyses are critical in understanding the complex functional regulatory natures of genetic variation and have been widely used in the interpretation of disease-associated variants identified by genome-wide association studies (GWAS). Emerging evidence has shown that trans-eQTL effects on remote gene expression could be mediated by local transcripts, which is known as the mediation effects. To discover the genome-wide eQTL mediation effects combing genomic and transcriptomic profiles, it is necessary to develop novel computational methods to rapidly scan large number of candidate associations while controlling for multiple testing appropriately. Here, we present eQTLMAPT, an R package aiming to perform eQTL mediation analysis with implementation of efficient permutation procedures in multiple testing correction. eQTLMAPT is advantageous in threefold. First, it accelerates mediation analysis by effectively pruning the permutation process through adaptive permutation scheme. Second, it can efficiently and accurately estimate the significance level of mediation effects by modeling the null distribution with generalized Pareto distribution (GPD) trained from a few permutation statistics. Third, eQTLMAPT provides flexible interfaces for users to combine various permutation schemes with different confounding adjustment methods. Experiments on real eQTL dataset demonstrate that eQTLMAPT provides higher resolution of estimated significance of mediation effects and is an order of magnitude faster than compared methods with similar accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

eQTLMAPT: Fast and Accurate eQTL Mediation Analysis With Efficient Permutation Testing Approaches

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Secondly, this approach will lead to class-imbalance problem since the number of known circRNAs is much fewer than the number of unknown circRNAs. is phenomenon has also been widely discussed in identifying disease-related genes, miRNAs and lncRNAs [47,[51][52][53]. erefore, it is not scienti c to regard all unknown genes as negative samples.…”

Section: Complexitymentioning

confidence: 99%

BRWSP: Predicting circRNA‐Disease Associations Based on Biased Random Walk to Search Paths on a Multiple Heterogeneous Network

Lei

Zhang

2019

Complexity

View full text Add to dashboard Cite

e circular RNAs (circRNAs) have signi cant e ects on a variety of biological processes, the dysfunction of which is closely related to the emergence and development of diseases. erefore, identi cation of circRNA-disease associations will contribute to analysing the pathogenesis of diseases. Here, we present a computational model called BRWSP to predict circRNA-disease associations, which searches paths on a multiple heterogeneous network based on biased random walk. Firstly, BRWSP constructs a multiple heterogeneous network by using circRNAs, diseases, and genes. en, the biased random walk algorithm runs on the multiple heterogeneous network to search paths between circRNAs and diseases. Finally, the performance of BRWSP is signi cantly better than the state-of-the-art algorithms. Furthermore, BRWSP further contributes to the discovery of novel circRNAdisease associations.

show abstract

“…They provide important data support for circRNA–disease association analyses. Some methods have been proposed to provide the most promising disease-related biomarkers, including those involving lncRNAs (Chen et al, 2015; Gu et al, 2017; Cheng et al, 2018a; Cheng et al, 2019), miRNAs (Peng et al, 2019b; Shao et al, 2018), genes (Cheng et al, 2016; Hu et al, 2019; Peng et al, 2019a), and drugs (Jiang et al, 2017; Zhang et al, 2017), for further experimental validation. These methods can decrease the time and cost of biological experiments.…”

Section: Introductionmentioning

confidence: 99%

Predicting circRNA-Disease Associations Based on circRNA Expression Similarity and Functional Similarity

et al. 2019

View full text Add to dashboard Cite

Circular RNAs (circRNAs) are a novel class of endogenous noncoding RNAs that have well-conserved sequences. Emerging evidence has shown that circRNAs can be novel biomarkers or therapeutic targets for many diseases and play an important role in the development of various pathological conditions. Therefore, identifying potential disease-related circRNAs is helpful in improving the efficiency of finding therapeutic targets for diseases. Here, we propose a computational model (PreCDA) to predict potential circRNA–disease associations. First, we calculated the circRNA expression similarity based on circRNA expression profiles. The circRNA functional similarity is calculated based on cosine similarity, and the disease similarity is used as the dimension of each circRNA vector. The associations between circRNAs and diseases are defined based on the circRNA functional similarity and expression similarity. We constructed a disease-related circRNA association network and used a graph-based recommendation algorithm (PersonalRank) to sort candidate disease-related circRNAs. As a result, PreCDA has an average area under the receiver operating characteristic curve value of 78.15% in predicting candidate disease-related circRNAs. In addition, we discuss the factors that affect the performance of this method and find some unknown circRNAs related to diseases, with several common diseases used as case studies. These results show that PreCDA has good performance in predicting potential circRNA–disease associations and is helpful for the diagnosis and treatment of human diseases.

show abstract

A learning-based framework for miRNA-disease association identification using neural networks

Cited by 152 publications

References 48 publications

eQTLMAPT: Fast and Accurate eQTL Mediation Analysis With Efficient Permutation Testing Approaches

eQTLMAPT: Fast and Accurate eQTL Mediation Analysis With Efficient Permutation Testing Approaches

BRWSP: Predicting circRNA‐Disease Associations Based on Biased Random Walk to Search Paths on a Multiple Heterogeneous Network

Predicting circRNA-Disease Associations Based on circRNA Expression Similarity and Functional Similarity

Contact Info

Product

Resources

About