FuDiCo: Gene Fusion-Initiated Path Propagation for Disease Comorbidity Prediction.

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Disease comorbidity, the co-occurrence of multiple diseases, complicates treatment and worsens patient outcomes.
• Current methods for predicting disease comorbidity rely on gene-disease associations within protein-protein interaction (PPI) networks, but are limited by incomplete data.
• Gene fusions are increasingly recognized as significant contributors to disease mechanisms.

Purpose of the Study:

• To introduce a novel framework, Gene Fusion-Initiated Path Propagation for Disease Comorbidity Prediction (FuDiCo), for predicting disease comorbidity.
• To leverage gene fusion events as a novel data source for understanding disease relationships.
• To capture molecular influence propagation patterns linking diseases.

Main Methods:

• Modeled disease comorbidity through influence propagation on a PPI network.
• Represented gene fusions as localized perturbation sources.
• Learned how influence propagates from fusion-associated genes to disease-associated subgraphs.

Main Results:

• FuDiCo demonstrated superior performance compared to existing state-of-the-art methods on a benchmark dataset.
• Achieved statistically significant improvements in disease comorbidity prediction.
• Highlighted the importance of gene fusion events in understanding disease interconnections.

Conclusions:

• Gene fusion events play a crucial role in disease development and comorbidity.
• The FuDiCo framework offers a powerful new approach for disease comorbidity prediction by incorporating gene fusion data.
• Understanding molecular propagation patterns can elucidate complex disease relationships.