Related Experiment Video
Updated: Oct 7, 2025
mirMachine: A One-Stop Shop for Plant miRNA Annotation
Published on: May 1, 2021
MiRNA-disease association prediction based on meta-paths
Liang Yu1, Yujia Zheng1, Lin Gao1
1School of Computer Science and Technology, Xidian University, Xi'an 710071, P.R. China.
Abstract:
Since miRNAs can participate in the posttranscriptional regulation of gene expression, they may provide ideas for the development of new drugs or become new biomarkers for drug targets or disease diagnosis. In this work, we propose an miRNA-disease association prediction method based on meta-paths (MDPBMP). First, an miRNA-disease-gene heterogeneous information network was constructed, and seven symmetrical meta-paths were defined according to different semantics. After constructing the initial feature vector for the node, the vector information carried by all nodes on the meta-path instance is extracted and aggregated to update the feature vector of the starting node. Then, the vector information obtained by the nodes on different meta-paths is aggregated. Finally, miRNA and disease embedding feature vectors are used to calculate their associated scores. Compared with the other methods, MDPBMP obtained the highest AUC value of 0.9214. Among the top 50 predicted miRNAs for lung neoplasms, esophageal neoplasms, colon neoplasms and breast neoplasms, 49, 48, 49 and 50 have been verified. Furthermore, for breast neoplasms, we deleted all the known associations between breast neoplasms and miRNAs from the training set. These results also show that for new diseases without known related miRNA information, our model can predict their potential miRNAs. Code and data are available at https://github.com/LiangYu-Xidian/MDPBMP.
Insights
This study introduces a novel method for predicting microRNA-disease associations using meta-paths, achieving high accuracy. The model effectively identifies potential microRNA biomarkers for various cancers, even for diseases with limited prior data.
Area of Science:
- Bioinformatics
- Genomics
- Computational Biology
Background:
- MicroRNAs (miRNAs) are crucial regulators of gene expression with potential as diagnostic biomarkers and therapeutic targets.
- Accurate prediction of miRNA-disease associations is vital for advancing precision medicine and drug discovery.
- Existing methods face challenges in capturing complex relationships within biological networks.
Purpose of the Study:
- To develop and validate a novel computational method, miRNA-disease association prediction based on meta-paths (MDPBMP), for identifying potential miRNA-disease associations.
- To construct a heterogeneous information network integrating miRNAs, diseases, and genes to model their intricate relationships.
- To assess the predictive performance and clinical relevance of the proposed MDPBMP method.
Main Methods:
- Construction of an miRNA-disease-gene heterogeneous information network.
- Definition and application of seven symmetrical meta-paths to capture diverse semantic relationships.
- Feature vector extraction and aggregation from meta-path instances to update node embeddings.
- Calculation of miRNA-disease association scores using aggregated feature vectors.
Main Results:
- The MDPBMP method achieved a superior Area Under the Curve (AUC) of 0.9214, outperforming existing approaches.
- High validation rates were observed for predicted miRNAs across lung, esophageal, colon, and breast neoplasms (49%, 48%, 49%, and 50% respectively).
- The model demonstrated robust performance in predicting potential miRNAs for diseases with no prior known associations, as shown in the breast neoplasm case study.
Conclusions:
- The MDPBMP method provides an effective and accurate approach for predicting miRNA-disease associations.
- The findings highlight the potential of miRNAs as biomarkers for cancer diagnosis and therapeutic targets.
- The model's ability to predict novel associations underscores its utility in uncovering previously unknown etiological links between miRNAs and diseases.
