Journal
FRONTIERS IN GENETICS
Volume 12, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fgene.2021.742992
Keywords
miRNA-disease association; credibility similarity; weighted voting; miRNA; disease
Categories
Funding
- National Natural Science Foundation of China [61873001, U19A2064, 11701318]
- Natural Science Foundation of Shandong Province [ZR2020KC022]
- Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University [MMC202006]
Ask authors/readers for more resources
miRNA expression is related to human diseases, serving as an indicator for clinical diagnosis and treatment. The WVMDA model utilizes weighted voting to predict miRNA-disease associations, incorporating credibility similarity and a filter to improve accuracy and reliability.
An increasing number of experiments had verified that miRNA expression is related to human diseases. The miRNA expression profile may be an indicator of clinical diagnosis and provides a new direction for the prevention and treatment of complex diseases. In this work, we present a weighted voting-based model for predicting miRNA-disease association (WVMDA). To reasonably build a network of similarity, we established credibility similarity based on the reliability of known associations and used it to improve the original incomplete similarity. To eliminate noise interference as much as possible while maintaining more reliable similarity information, we developed a filter. More importantly, to ensure the fairness and efficiency of weighted voting, we focus on the design of weighting. Finally, cross-validation experiments and case studies are undertaken to verify the efficacy of the proposed model. The results showed that WVMDA could efficiently identify miRNAs associated with the disease.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available