Related Experiment Video
Updated: Jul 26, 2025
mirMachine: A One-Stop Shop for Plant miRNA Annotation
Published on: May 1, 2021
IMC-MDA: Prediction of miRNA-disease association based on induction matrix completion
Zejun Li1, Yuxiang Zhang2, Yuting Bai3
1School of Computer and Information Science, Hunan Institute of Technology, Hengyang 412002, China.
Abstract:
To comprehend the etiology and pathogenesis of many illnesses, it is essential to identify disease-associated microRNAs (miRNAs). However, there are a number of challenges with current computational approaches, such as the lack of "negative samples", that is, confirmed irrelevant miRNA-disease pairs, and the poor performance in terms of predicting miRNAs related with "isolated diseases", i.e. illnesses with no known associated miRNAs, which presents the need for novel computational methods. In this study, for the purpose of predicting the connection between disease and miRNA, an inductive matrix completion model was designed, referred to as IMC-MDA. In the model of IMC-MDA, for each miRNA-disease pair, the predicted marks are calculated by combining the known miRNA-disease connection with the integrated disease similarities and miRNA similarities. Based on LOOCV, IMC-MDA had an AUC of 0.8034, which shows better performance than previous methods. Furthermore, experiments have validated the prediction of disease-related miRNAs for three major human diseases: colon cancer, kidney cancer, and lung cancer.
Insights
A new computational model, IMC-MDA, accurately predicts disease-associated microRNAs (miRNAs). This method improves upon existing approaches by incorporating disease and miRNA similarities for better prediction of miRNA-disease relationships.
Area of Science:
- Bioinformatics
- Genomics
- Computational Biology
Background:
- Identifying disease-associated microRNAs (miRNAs) is crucial for understanding disease etiology and pathogenesis.
- Current computational methods face challenges, including a lack of negative samples and poor performance in predicting miRNAs for isolated diseases.
Purpose of the Study:
- To develop a novel computational method for predicting miRNA-disease associations.
- To address limitations of existing approaches, particularly for isolated diseases and the absence of negative samples.
Main Methods:
- An inductive matrix completion model named IMC-MDA was designed.
- IMC-MDA integrates known miRNA-disease connections with disease and miRNA similarities to predict associations.
- Leave-One-Out Cross-Validation (LOOCV) was employed for model evaluation.
Main Results:
- The IMC-MDA model achieved an Area Under the Curve (AUC) of 0.8034 based on LOOCV.
- This performance surpasses that of previous computational methods.
- The model's predictions were validated for miRNAs associated with colon cancer, kidney cancer, and lung cancer.
Conclusions:
- IMC-MDA demonstrates superior performance in predicting miRNA-disease associations compared to existing methods.
- The developed model offers a promising approach for identifying novel disease-related miRNAs, including for isolated diseases.
- This advancement aids in comprehending disease mechanisms and can inform future research in precision medicine.
