Related Experiment Video
Updated: Jun 4, 2025
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
Prediction of miRNA-disease associations based on PCA and cascade forest
Chuanlei Zhang1, Yubo Li1, Yinglun Dong1
1Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300457, China.
Background:
As a key non-coding RNA molecule, miRNA profoundly affects gene expression regulation and connects to the pathological processes of several kinds of human diseases. However, conventional experimental methods for validating miRNA-disease associations are laborious. Consequently, the development of efficient and reliable computational prediction models is crucial for the identification and validation of these associations.
Results:
In this research, we developed the PCACFMDA method to predict the potential associations between miRNAs and diseases. To construct a multidimensional feature matrix, we consider the fusion similarities of miRNA and disease and miRNA-disease pairs. We then use principal component analysis(PCA) to reduce data complexity and extract low-dimensional features. Subsequently, a tuned cascade forest is used to mine the features and output prediction scores deeply. The results of the 5-fold cross-validation using the HMDD v2.0 database indicate that the PCACFMDA algorithm achieved an AUC of 98.56%. Additionally, we perform case studies on breast, esophageal and lung neoplasms. The findings revealed that the top 50 miRNAs most strongly linked to each disease have been validated.
Conclusions:
Based on PCA and optimized cascade forests, we propose the PCACFMDA model for predicting undiscovered miRNA-disease associations. The experimental results demonstrate superior prediction performance and commendable stability. Consequently, the PCACFMDA is a potent instrument for in-depth exploration of miRNA-disease associations.
Insights
This study introduces PCACFMDA, a computational model for predicting microRNA (miRNA)-disease associations. The method uses principal component analysis (PCA) and cascade forests, achieving high accuracy and aiding in discovering novel miRNA-disease links.
Area of Science:
- Genomics
- Bioinformatics
- Computational Biology
Background:
- MicroRNAs (miRNAs) are key non-coding RNA molecules regulating gene expression.
- miRNAs are implicated in various human diseases.
- Experimental validation of miRNA-disease associations is time-consuming.
Purpose of the Study:
- To develop an efficient computational model for predicting miRNA-disease associations.
- To overcome limitations of traditional experimental validation methods.
Main Methods:
- Developed the PCACFMDA method integrating miRNA and disease similarities.
- Utilized Principal Component Analysis (PCA) for feature dimensionality reduction.
- Employed a tuned cascade forest for deep feature mining and prediction.
Main Results:
- PCACFMDA achieved an Area Under the Curve (AUC) of 98.56% in 5-fold cross-validation on the HMDD v2.0 database.
- Case studies on breast, esophageal, and lung neoplasms demonstrated successful validation of top predicted miRNA-disease associations.
- The model shows high prediction accuracy and stability.
Conclusions:
- The PCACFMDA model, based on PCA and cascade forests, effectively predicts novel miRNA-disease associations.
- The model demonstrates superior performance and stability, making it a valuable tool for research.
- PCACFMDA facilitates in-depth exploration of the complex relationships between miRNAs and diseases.
More Related Videos
07:35A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
