Related Experiment Video
Updated: Oct 5, 2025
03:37
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
Published on: March 1, 2024
942
Predicting miRNA-disease associations based on graph random propagation network and attention network.
Tangbo Zhong1,2, Zhengwei Li1,2, Zhu-Hong You3
1Engineering Research Center of Mine Digitalization of Ministry of Education, China University of Mining and Technology, Xuzhou, China.
Briefings in Bioinformatics
|January 26, 2022
Summary
This study introduces GRPAMDA, a novel deep learning model for predicting microRNA-disease associations. GRPAMDA enhances disease research by uncovering new links between microRNAs (miRNAs) and diseases.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Abnormal microRNA (miRNA) expression is linked to various diseases, making miRNA research crucial for disease prevention and drug development.
- Numerous undiscovered associations between miRNAs and diseases hinder comprehensive research and therapeutic advancements.
Purpose of the Study:
- To develop a novel deep learning model, GRPAMDA, for predicting unknown miRNA-disease associations.
- To enhance the understanding of miRNA roles in disease pathogenesis.
Main Methods:
- Constructed a miRNA-disease heterogeneous graph using known association data.
- Applied DropFeature and graph random propagation to enhance node features.
- Utilized an attention mechanism to fuse propagated features and aggregate neighbor information.
- Generated miRNA-disease association scores using a fully connected layer.
Main Results:
- The GRPAMDA model achieved an average area under the curve of 93.46% on the HMDD v2.0 dataset via 5-fold cross-validation.
- Case studies demonstrated high accuracy in identifying disease-associated miRNAs for esophageal tumors, lymphomas, and prostate tumors, with many validated by external databases.
- The model effectively predicts novel miRNA-disease associations.
Conclusions:
- GRPAMDA offers a valuable computational method for exploring and predicting miRNA-disease associations.
- The model's performance highlights its potential to accelerate miRNA-related disease research and therapeutic discovery.
Related Concept Videos
02:26Protein Networks
4.1K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
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,...
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,...
4.1K
01:22MicroRNAs
3.2K
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns (non-coding regions of a gene) or intergenic regions (stretches of DNA present between genes). Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself, forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA...
3.2K