MSPCD: predicting circRNA-disease associations via integrating multi-source data and hierarchical neural network

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Circular RNAs (circRNAs) play a crucial regulatory role in diseases via interactions with microRNAs (miRNAs).
• Identifying circRNA-disease associations is vital for precise disease diagnosis and treatment.
• Traditional experimental methods for identifying these associations are time-consuming and costly.

Purpose of the Study:

• To develop an efficient computational framework for inferring unknown circRNA-disease associations.
• To overcome the limitations of traditional experimental approaches.

Main Methods:

• Proposed an efficient framework named MSPCD.
• Integrated biological information including circRNA-miRNA and circRNA-gene ontology associations.
• Extracted high-order features of circRNAs and diseases using neural networks.
• Employed Deep Neural Networks (DNN) for predicting circRNA-disease associations.

Main Results:

• MSPCD demonstrated significantly more accurate performance compared to existing state-of-the-art methods.
• Validation was performed on the circFunBase dataset.
• Case studies confirmed the effectiveness of MSPCD.

Conclusions:

• MSPCD is an effective computational tool for inferring circRNA-disease associations.
• The framework offers a promising approach for advancing disease diagnosis and treatment strategies.
• The study highlights the potential of computational methods in uncovering complex biological relationships.