The probability of edge existence due to node degree: a baseline for network-based predictions

Area of Science:

• Biomedical Informatics
• Network Science
• Computational Biology

Background:

• Biomedical discovery tasks like gene function prediction and drug repurposing rely on network edge prediction.
• Node degree, the number of connections a node has, varies greatly in biological networks and can bias predictions.
• Existing methods may overstate performance due to the influence of node degree.

Conclusions:

• Node degree is a dominant factor in many biomedical network edge prediction tasks.
• The proposed edge prior provides a crucial baseline for assessing nonspecific performance.
• Researchers should incorporate degree-aware methods and baselines for accurate biological network analysis.