metaCDA: A Novel Framework for CircRNA-Driven Drug Discovery Utilizing Adaptive Aggregation and Meta-Knowledge...

Area of Science:

• Biotechnology
• Genomics
• Computational Biology

Background:

• Circular RNAs (circRNAs) are emerging as critical multifunctional therapeutic targets in RNA drug development.
• Understanding circRNA-disease interactions is vital for advancing circRNA-based drug discovery.
• Existing computational methods struggle with aggregate and higher-order fusion information in heterogeneous networks.

Purpose of the Study:

• To introduce metaCDA, a novel computational approach for enhancing circRNA-disease association prediction.
• To address limitations in current methods regarding information aggregation and fusion.
• To improve the accuracy and effectiveness of identifying disease-associated circRNAs.

Main Methods:

• Constructing a heterogeneous graph integrating multiple circRNA-disease similarity measures.
• Utilizing meta-networks to extract meta-knowledge and adaptive contrast enhancement.
• Implementing a nodal adaptive attention aggregation system with multihead attention for higher-order information capture.

Main Results:

• metaCDA demonstrated superior performance compared to existing state-of-the-art models.
• The method effectively predicts associations between circular RNAs and diseases.
• Experimental validation confirms the efficacy of the proposed approach.

Conclusions:

• metaCDA offers a significant advancement in predicting circRNA-disease associations.
• The approach overcomes key limitations of previous computational methods.
• This work opens new avenues for circRNA-driven therapeutic target identification and drug discovery.