DrugNet: network-based drug-disease prioritization by integrating heterogeneous data

Area of Science:

• Computational biology
• Pharmacology
• Bioinformatics

Background:

• Drug repositioning accelerates drug development by identifying new uses for existing drugs.
• Network-based approaches are increasingly used for complex biological data analysis and prioritization.
• Integrating diverse biological data is crucial for effective drug discovery.

Purpose of the Study:

• To propose a novel computational drug repositioning methodology called DrugNet.
• To leverage heterogeneous network prioritization for improved drug-disease and disease-drug identification.
• To aid researchers in efficiently discovering new therapeutic applications for existing drugs.

Main Methods:

• Developed DrugNet, a methodology based on the ProphNet network prioritization algorithm.
• Constructed a heterogeneous network integrating drugs, proteins, and diseases.
• Applied DrugNet to various drug repositioning validation tests.

Main Results:

• DrugNet achieved high performance in validation tests, with a mean AUC of 0.9552 in 5-fold cross-validation.
• The method demonstrated strong predictive power on recent clinical trials (phases 0-4) not included in the training data (mean AUC 0.8364).
• Heterogeneous data integration proved beneficial for drug repositioning tasks.

Conclusions:

• The DrugNet methodology enables efficient drug repositioning through ranked lists of drugs for specific diseases or vice versa.
• Simultaneous integration of disease, drug, and target information significantly enhances drug repositioning efficacy.
• DrugNet is accessible as a web tool and its source code is available for research use.