A New Method for Computational Drug Repositioning Using Drug Pairwise Similarity

Area of Science:

• Computational drug discovery
• Pharmacology
• Bioinformatics

Background:

• Traditional de novo drug discovery is costly and time-consuming.
• Drug repositioning offers a cost-effective alternative for identifying new therapeutic indications.
• Computational methods are increasingly employed for drug repositioning.

Purpose of the Study:

• To develop a systematic computational approach for identifying potential new indications of existing drugs.
• To leverage drug target information, drug-target interactions, and chemical structures for improved drug repositioning.
• To validate the proposed method against existing state-of-the-art techniques.

Main Methods:

• A novel bipartite-graph based method was adapted to analyze common drug targets and their interactions.
• Drug structure information was incorporated to calculate pairwise drug similarity.
• Cross-validation experiments were conducted to evaluate prediction performance.

Main Results:

• The proposed method achieved high accuracy with a sensitivity of 0.77 and specificity of 0.92 (AUC = 0.888).
• Performance favorably compared to existing state-of-the-art methods.
• Drug repositioning results were significantly enriched in biomedical literature and clinical trials.

Conclusions:

• Combining chemical structure and drug target information enhances prediction performance in drug repositioning.
• The proposed approach effectively captures implicit information between drug targets.
• This method offers a promising strategy for efficient drug repositioning and discovery of new indications.