Format

Send to

Choose Destination
Genome Biol. 2019 Oct 8;20(1):202. doi: 10.1186/s13059-019-1811-3.

Benchmark of computational methods for predicting microRNA-disease associations.

Author information

1
Department of Biomedical Informatics, Department of Physiology and Pathophysiology, Center for Noncoding RNA Medicine, MOE Key Lab of Cardiovascular Sciences, School of Basic Medical Sciences, Peking University, 38 Xueyuan Rd, Beijing, 100191, China.
2
Institute of Computational Medicine, School of Artificial Intelligence, Hebei University of Technology, Tianjin, 300401, China.
3
Center of Bioinformatics, Key Laboratory for Neuro-Information of Ministry of Education, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
4
Institute of Computational Medicine, School of Artificial Intelligence, Hebei University of Technology, Tianjin, 300401, China. lijianwei@hebut.edu.cn.
5
Department of Biomedical Informatics, Department of Physiology and Pathophysiology, Center for Noncoding RNA Medicine, MOE Key Lab of Cardiovascular Sciences, School of Basic Medical Sciences, Peking University, 38 Xueyuan Rd, Beijing, 100191, China. zhouyuanbioinfo@hsc.pku.edu.cn.

Abstract

BACKGROUND:

A series of miRNA-disease association prediction methods have been proposed to prioritize potential disease-associated miRNAs. Independent benchmarking of these methods is warranted to assess their effectiveness and robustness.

RESULTS:

Based on more than 8000 novel miRNA-disease associations from the latest HMDD v3.1 database, we perform systematic comparison among 36 readily available prediction methods. Their overall performances are evaluated with rigorous precision-recall curve analysis, where 13 methods show acceptable accuracy (AUPRC >‚ÄČ0.200) while the top two methods achieve a promising AUPRC over 0.300, and most of these methods are also highly ranked when considering only the causal miRNA-disease associations as the positive samples. The potential of performance improvement is demonstrated by combining different predictors or adopting a more updated miRNA similarity matrix, which would result in up to 16% and 46% of AUPRC augmentations compared to the best single predictor and the predictors using the previous similarity matrix, respectively. Our analysis suggests a common issue of the available methods, which is that the prediction results are severely biased toward well-annotated diseases with many associated miRNAs known and cannot further stratify the positive samples by discriminating the causal miRNA-disease associations from the general miRNA-disease associations.

CONCLUSION:

Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate miRNA-disease association predictors for their purpose, but also suggest the future directions for the development of more robust miRNA-disease association predictors.

KEYWORDS:

Benchmarking test; Disease miRNA prediction; miRNA-disease association

PMID:
31594544
DOI:
10.1186/s13059-019-1811-3
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center