Related Experiment Video
Updated: Sep 6, 2025
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
Published on: March 1, 2024
MSHGANMDA: Meta-Subgraphs Heterogeneous Graph Attention Network for miRNA-Disease Association Prediction
Abstract:
MicroRNAs (miRNAs) influence several biological processes involved in human disease. Biological experiments for verifying the association between miRNA and disease are always costly in terms of both money and time. Although numerous biological experiments have identified multi-types of associations between miRNAs and diseases, existing computational methods are unable to sufficiently mine the knowledge in these associations to predict unknown associations. In this study, we innovatively propose a heterogeneous graph attention network model based on meta-subgraphs (MSHGANMDA) to predict the potential miRNA-disease associations. Firstly, we define five types of meta-subgraph from the known miRNA-disease associations. Then, we use meta-subgraph attention and meta-subgraph semantic attention to extract features of miRNA-disease pairs within and between these five meta-subgraphs, respectively. Finally, we apply a fully-connected layer (FCL) to predict the scores of unknown miRNA-disease associations and cross-entropy loss to train our model end-to-end. To evaluate the effectiveness of MSHGANMDA, we apply five-fold cross-validation to calculate the mean values of evaluation metrics Accuracy, Precision, Recall, and F1-score as 0.8595, 0.8601, 0.8596, and 0.8595, respectively. Experiments show that our model, which primarily utilizes multi-types of miRNA-disease association data, gets the greatest ROC-AUC value of 0.934 when compared to other state-of-the-art approaches. Furthermore, through case studies, we further confirm the effectiveness of MSHGANMDA in predicting unknown diseases.
Insights
This study introduces a novel computational model, MSHGANMDA, to predict microRNA-disease associations efficiently. The model accurately identifies potential links, reducing the need for costly biological experiments.
Area of Science:
- Genomics
- Computational Biology
- Bioinformatics
Background:
- MicroRNAs (miRNAs) play crucial roles in human diseases.
- Experimental validation of miRNA-disease associations is time-consuming and expensive.
- Existing computational methods struggle to fully leverage known associations for novel predictions.
Purpose of the Study:
- To develop an innovative computational model for predicting potential miRNA-disease associations.
- To address the limitations of current methods in mining complex association data.
- To reduce the cost and time associated with identifying novel miRNA-disease links.
Main Methods:
- Proposed a heterogeneous graph attention network model based on meta-subgraphs (MSHGANMDA).
- Defined five types of meta-subgraphs from known miRNA-disease associations.
- Employed meta-subgraph attention and semantic attention for feature extraction.
- Utilized a fully-connected layer and cross-entropy loss for end-to-end training.
Main Results:
- Achieved high performance in five-fold cross-validation with Accuracy (0.8595), Precision (0.8601), Recall (0.8596), and F1-score (0.8595).
- Obtained the highest ROC-AUC value of 0.934 compared to state-of-the-art approaches.
- Demonstrated effectiveness through case studies confirming prediction accuracy.
Conclusions:
- MSHGANMDA effectively predicts potential miRNA-disease associations by utilizing multi-type data.
- The model offers a cost-effective and efficient alternative to experimental validation.
- This approach advances the field of computational disease-gene association prediction.
