A novel bi-directional heterogeneous network selection method for disease and microbial association prediction

Area of Science:

• Microbiology
• Computational Biology
• Medical Informatics

Background:

• The human microbiome significantly impacts health.
• Understanding microbial-disease links is crucial for disease pathogenesis, diagnosis, and treatment.
• Existing methods for predicting microbial disease relationships require improvement.

Purpose of the Study:

• To develop a novel computational model for predicting potential microbial-disease associations.
• To enhance the accuracy and effectiveness of microbial disease relationship prediction.

Main Methods:

• Constructed a bi-directional heterogeneous microbial-disease network integrating multiple similarity measures (Gaussian kernel, microbial function, disease semantics, disease symptoms).
• Employed random walk to learn network neighbor information.
• Utilized a selection model for information aggregation and microbial-disease node pair analysis.

Main Results:

• The proposed model demonstrated superior performance compared to existing methods in leave-one-out and five-fold cross-validation.
• Case studies confirmed the model's effectiveness in identifying microbial-disease relationships for various conditions.

Conclusions:

• The developed computational model offers a robust approach for predicting microbial-disease relationships.
• This work contributes to a deeper understanding of disease pathogenesis and aids in clinical applications.
• The model's accuracy and validated effectiveness highlight its potential for advancing personalized medicine.