Related Experiment Video
Updated: Sep 20, 2025
06:16
mirMachine: A One-Stop Shop for Plant miRNA Annotation
Published on: May 1, 2021
2.6K
idenMD-NRF: a ranking framework for miRNA-disease association identification
Wenxiang Zhang1, Hang Wei2, Bin Liu1,3
1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China.
Briefings in Bioinformatics
|June 9, 2022
Summary
A new computational framework, idenMD-NRF, accurately predicts diseases associated with novel microRNAs (miRNAs). This approach improves upon existing methods by treating miRNA-disease association identification as an information retrieval task.
Area of Science:
- Biomedical Informatics
- Computational Biology
- Genomics
Background:
- Identifying microRNA (miRNA)-disease associations is crucial for understanding complex disease pathogenesis.
- Existing computational methods excel at finding known associations but struggle with predicting diseases for novel miRNAs.
Purpose of the Study:
- To develop a novel computational framework, idenMD-NRF, for accurate miRNA-disease association identification, particularly for new miRNAs.
- To address the challenge of predicting associated diseases for previously uncharacterized miRNAs.
Main Methods:
- The idenMD-NRF framework treats miRNA-disease association identification as an information retrieval problem.
- It utilizes a Learning to Rank algorithm to rank potential associated diseases for a given novel miRNA.
- The ranking is based on high-level association features and multiple predictive models.
Main Results:
- Experimental results on two independent datasets demonstrate the superiority of idenMD-NRF compared to existing predictors.
- The framework shows enhanced performance in identifying disease associations for novel miRNAs.
Conclusions:
- The idenMD-NRF framework offers a significant advancement in predicting miRNA-disease associations for novel miRNAs.
- A publicly accessible web server for idenMD-NRF is available at http://bliulab.net/idenMD-NRF/.
