iCircDA-MF: identification of circRNA-disease associations based on matrix factorization

Area of Science:

• Bioinformatics
• Genomics
• Computational Biology

Background:

• Circular RNAs (circRNAs) are novel non-coding RNAs with critical roles in biological processes.
• Identifying circRNA-disease associations is crucial for understanding disease mechanisms and developing targeted therapies.
• Existing computational predictors for circRNA-disease associations have limited performance.

Purpose of the Study:

• To propose a novel computational method, iCircDA-MF, for predicting circRNA-disease associations.
• To address the challenge of limited experimentally validated circRNA-disease associations.
• To improve the accuracy and effectiveness of circRNA-disease association prediction.

Main Methods:

• Utilizing circRNA and disease similarity derived from semantic information and known interactions (circRNA-gene, gene-disease).
• Updating circRNA-disease interaction profiles using neighbor interaction profiles to correct false negatives.
• Applying matrix factorization on updated interaction profiles for prediction.

Main Results:

• The proposed iCircDA-MF method demonstrates superior performance compared to existing state-of-the-art predictors.
• iCircDA-MF effectively identifies novel circRNA-disease associations.
• Experimental results on a benchmark dataset validate the method's efficacy.

Conclusions:

• iCircDA-MF offers an effective computational approach for predicting circRNA-disease associations.
• The method holds promise for advancing the understanding of disease mechanisms and facilitating targeted therapies.
• Further development and application of iCircDA-MF can enhance circRNA-disease association discovery.