Convolution Neural Networks Using Deep Matrix Factorization for Predicting Circrna-Disease Association.

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Circular RNAs (circRNAs) possess stable structures, making them promising for disease diagnosis.
• Identifying circRNA-disease associations through biological experiments is costly and time-consuming.
• There is a critical need for efficient computational models to predict these associations.

Purpose of the Study:

• To develop a novel deep matrix factorization with convolution neural networks framework (DMFCNNCD) for predicting circRNA-disease associations.
• To leverage circRNA and disease features for accurate association prediction.
• To overcome the limitations of traditional experimental methods.

Main Methods:

• Matrix decomposition of the circRNA-disease association matrix to extract inherent features.
• Utilizing a mapping module to capture potential nonlinear features.
• Integrating extracted features with similarity information to create a comprehensive training dataset.
• Applying convolution neural networks (CNNs) for prediction of unknown circRNA-disease associations.

Main Results:

• The DMFCNNCD framework successfully predicts circRNA-disease associations.
• Experimental results demonstrate the efficacy of the proposed method.
• The model outperforms existing state-of-the-art methods in prediction accuracy.

Conclusions:

• The DMFCNNCD model offers an efficient and achievable computational approach for predicting circRNA-disease associations.
• This method can accelerate the discovery of novel circRNA biomarkers for various diseases.
• The findings contribute to advancing the application of circRNAs in clinical diagnostics.