Related Experiment Video
Updated: Jan 29, 2026
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
Dual-network sparse graph regularized matrix factorization for predicting miRNA-disease associations
Ming-Ming Gao1, Zhen Cui1, Ying-Lian Gao2
1School of Information Science and Engineering, Qufu Normal University, Rizhao, China. gaommzjr@126.com sdcavell@126.com cuizhensdws@126.com.
Abstract:
With the development of biological research and scientific experiments, it has been discovered that microRNAs (miRNAs) are closely related to many serious human diseases; however, finding the correct miRNA-disease associations is both time consuming and challenging. Therefore, it is very necessary to develop some new methods. Although the existing methods are very helpful in this regard, they all present some shortcomings; thus, some new methods need to be developed to overcome these shortcomings. In this study, a method based on dual network sparse graph regularized matrix factorization (DNSGRMF) was proposed, which increased the sparsity by adding the L2,1-norm. Moreover, Gaussian interaction profile kernels were introduced. The experiments showed that our method was feasible and had a high AUC value. Additionally, the five-fold cross-validation method was used to evaluate this method. A simulation experiment was used to predict some new associations on the datasets, and the obtained experimental results were satisfactory, which proved that our method was indeed feasible.
Insights
Identifying microRNA-disease associations is crucial but challenging. A new dual network sparse graph regularized matrix factorization method (DNSGRMF) effectively predicts these links, improving upon existing approaches.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- MicroRNAs (miRNAs) are implicated in numerous human diseases.
- Accurate identification of miRNA-disease associations is critical for understanding disease mechanisms.
- Current methods for predicting miRNA-disease associations have limitations.
Purpose of the Study:
- To develop a novel computational method for predicting miRNA-disease associations.
- To overcome the shortcomings of existing prediction approaches.
- To improve the accuracy and efficiency of miRNA-disease association identification.
Main Methods:
- Proposed a dual network sparse graph regularized matrix factorization (DNSGRMF) method.
- Incorporated L2,1-norm to enhance sparsity.
- Utilized Gaussian interaction profile kernels for improved feature representation.
Main Results:
- The DNSGRMF method demonstrated high feasibility and performance.
- Achieved a high Area Under the Curve (AUC) value, indicating strong predictive power.
- Five-fold cross-validation confirmed the method's robustness and reliability.
Conclusions:
- The proposed DNSGRMF method is a feasible and effective tool for predicting miRNA-disease associations.
- The method shows promise for discovering novel miRNA-disease relationships.
- Further development of computational approaches is essential for advancing biological research.
Related Concept Videos
02:26Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
01:42The Extracellular Matrix
02:35Transcription Elongation Factors
The transcription elongation is regulated via pausing of RNA polymerase on several occasions during transcription. In bacteria, these halts are necessary because the transcription of DNA into mRNA is coupled to the translation of that mRNA...
01:07Ogive Graph
01:30Graphing Antiderivatives
01:07Bar Graph