A Computational Model to Predict the Causal miRNAs for Diseases

Gao, Yuanxu; Jia, Kaiwen; Shi, Jiangcheng; Zhou, Yuan; Cui, Qinghua

doi:10.3389/fgene.2019.00935

Cited by 13 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, since there was no established database of disease-causal miRNAs at the time, they con rmed their results through corroboration with other computational methods, such as miRsig and TAM [10,11]. Building on recent data advances, MiRNA Disease-Causal Association Predictor (MDCAP) is a label propagation algorithm that utilizes the miRNA and disease similarity matrix to predict potential disease-causal associations [12]. Like other miRNA disease-association prediction algorithms, MDCAP uses clustering of miRNAs based on their associations to similar diseases to predict further miRNA-disease associations [13].…”

Section: Introductionmentioning

confidence: 83%

“…We use one other piece of biological information to predict pathogenic miRNAs: miRNA conservation. The authors of MDCAP discovered that miRNAs that were causally implicated in more diseases were generally more conserved across species [12]. MiRNAs that are highly conserved are more important to key biological functions, and thus have a higher probability of causing disease when they are dysregulated.…”

Section: Methods Disimirmentioning

confidence: 99%

“…MDCAP can effectively differentiate between the causal and non-causal miRNAs in the HMDD database; however, like other disease-association prediction algorithms, it is restricted by the size and quality of its training dataset and thus struggles to generalize to diseases less characterized in the literature and to produce novel discoveries. Both works discovered important characteristics about pathogenic miRNAs: miR uence discovered that miRNA pathogenicity was linked to miRNA network in uence, and MDCAP discovered that miRNA pathogenicity was associated with conservation [7,12]. We build on these insights in our work with DisiMiR.…”

Section: Introductionmentioning

confidence: 97%

See 2 more Smart Citations

DisiMiR: Predicting Pathogenic miRNAs Using Network Influence and miRNA Conservation

Wang

McGeachie

2022

Preprint

View full text Add to dashboard Cite

Deadly diseases, like cancer and Alzheimer’s, are complex conditions with elusive cures that consistently form the leading causes of death globally every year. MiRNAs have been shown to play a powerful regulatory role in the progression of these diseases, forming promising novel drug targets. Current experimental methods, like differential expression analysis, can discover disease-associated miRNAs, yet many of these miRNAs play no functional role in disease progression. Interventional experiments used to discover disease-causing miRNAs can be time consuming and costly. We present DisiMiR: a novel computational method that predicts pathogenic miRNAs by inferring biological characteristics of pathogenicity including network influence and gene conservation. DisiMiR separates disease-causal miRNAs from merely disease-associated miRNAs and was accurate in four diseases: breast cancer (0.817 AUC), Alzheimer's (0.727 AUC), gastric cancer (0.843 AUC) and hepatocellular cancer (0.949 AUC). Additionally, DisiMiR can generate hypotheses effectively: 41.2% of its false positives that are mentioned in the literature have been confirmed to be causal. In this work, we show that DisiMiR is a powerful tool that can be used to efficiently and flexibly predict pathogenic miRNAs in an expression dataset, for the further elucidation of disease mechanisms and the potential identification of novel drug targets.

show abstract

Section: Introductionmentioning

confidence: 83%

Section: Methods Disimirmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

DisiMiR: Predicting Pathogenic miRNAs Using Network Influence and miRNA Conservation

Wang

McGeachie

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The criteria of the HMDD database for studies reflecting causal associations are as follows: a) the target miRNAs' functional acquisition/loss experiments were included in the study; b) the functional experiments should be performed on cell lines or diseased animals; c) miRNAs that only enhanced efficacy but did not contribute to the diseases were excluded [31]. Based on these criteria, there are 53 records indicate that hsa-miR-135b, hsa-miR-142, hsa-miR-182, hsa-miR-183, and hsa-miR-3607 are associated with lung cancer, including two subtypes of NSCLC: LUAD and LUSC.…”

Section: Discussionmentioning

confidence: 99%

The Lung Cancer Associated MicroRNAs and Single Nucleotides Polymorphisms: a Mendelian Randomization Analysis

Huang

Cho

Sun

et al. 2020

2020 42nd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Lung cancer is a major public health burden and among the highest incidence and mortality rates of the cancers. MicroRNAs (miRNAs) play an important role in the development of lung cancer. The aim of this study was to investigate whether there was a potential causal relation between miRNAs and non-small-cell lung cancer (NSCLC). 1,026 patients with NSCLC from The Cancer Genome Atlas (TCGA) were analyzed. NSCLC associated SNPs' allele scores were established, and candidate miRNAs were filtered from differential expression analysis. Mendelian randomization (MR) analysis was conducted for 5 candidate miRNA (hsa-miR-135b, hsa-miR-142, hsa-miR-182, hsa-miR-183 and hsa-miR-3607) and 76 candidate SNPs in lung adenocarcinoma (LUAD) group. According to the core assumptions of MR, there was no clear evidence of a causal relation between the 5 candidate miRNAs and LUAD. The reads per million miRNAs mapped (RPM) level of candidate miRNAs changed less than 3% per allele score. To our knowledge, this is the first study using the TCGA data set to investigate the causal relation between miRNAs and lung cancer using the MR approach, and also one of the first MR studies to use miRNA expression as an exposure factor, with the SNPs as instrumental variables.

show abstract

“…In the last decade, a large number of methods and models have been proposed to identify potential relationships between miRNAs and diseases [ 13 , 14 ]. These methods and models have mainly focused on solving the above problem by machine learning, network mining, combinatorial optimization, and related approaches [ 15 – 17 ].…”

Section: Introductionmentioning

confidence: 99%

Bipartite graph-based collaborative matrix factorization method for predicting miRNA-disease associations

et al. 2021

View full text Add to dashboard Cite

Background With the rapid development of various advanced biotechnologies, researchers in related fields have realized that microRNAs (miRNAs) play critical roles in many serious human diseases. However, experimental identification of new miRNA–disease associations (MDAs) is expensive and time-consuming. Practitioners have shown growing interest in methods for predicting potential MDAs. In recent years, an increasing number of computational methods for predicting novel MDAs have been developed, making a huge contribution to the research of human diseases and saving considerable time. In this paper, we proposed an efficient computational method, named bipartite graph-based collaborative matrix factorization (BGCMF), which is highly advantageous for predicting novel MDAs. Results By combining two improved recommendation methods, a new model for predicting MDAs is generated. Based on the idea that some new miRNAs and diseases do not have any associations, we adopt the bipartite graph based on the collaborative matrix factorization method to complete the prediction. The BGCMF achieves a desirable result, with AUC of up to 0.9514 ± (0.0007) in the five-fold cross-validation experiments. Conclusions Five-fold cross-validation is used to evaluate the capabilities of our method. Simulation experiments are implemented to predict new MDAs. More importantly, the AUC value of our method is higher than those of some state-of-the-art methods. Finally, many associations between new miRNAs and new diseases are successfully predicted by performing simulation experiments, indicating that BGCMF is a useful method to predict more potential miRNAs with roles in various diseases.

show abstract

A Computational Model to Predict the Causal miRNAs for Diseases

Cited by 13 publications

References 27 publications

DisiMiR: Predicting Pathogenic miRNAs Using Network Influence and miRNA Conservation

DisiMiR: Predicting Pathogenic miRNAs Using Network Influence and miRNA Conservation

The Lung Cancer Associated MicroRNAs and Single Nucleotides Polymorphisms: a Mendelian Randomization Analysis

Bipartite graph-based collaborative matrix factorization method for predicting miRNA-disease associations

Contact Info

Product

Resources

About