Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm

Area of Science:

• Computational biology
• Pharmacology
• Bioinformatics

Background:

• Drug repositioning accelerates drug development by finding new uses for existing drugs.
• Current computational methods often neglect the influence of known drug-disease associations on similarity calculations.
• There is a need for improved computational strategies that leverage comprehensive data for drug repositioning.

Purpose of the Study:

• To propose a novel computational method, MBiRW, for identifying potential new drug indications.
• To integrate drug/disease features with known drug-disease associations for enhanced similarity measures.
• To validate the performance of MBiRW in predicting novel drug-disease associations.

Main Methods:

• Developed comprehensive similarity measures by integrating drug/disease features and known associations.
• Constructed drug and disease similarity networks.
• Incorporated these networks into a heterogeneous network with known drug-disease interactions.
• Applied the Bi-Random Walk (BiRW) algorithm on the heterogeneous network for prediction.

Main Results:

• MBiRW demonstrated reliable prediction performance across various datasets.
• The proposed approach outperformed several recent computational drug repositioning methods.
• Case studies confirmed MBiRW's effectiveness in discovering practical drug indications.

Conclusions:

• MBiRW offers a superior computational approach for drug repositioning.
• The method effectively leverages integrated data for accurate prediction of novel drug-disease associations.
• MBiRW has practical implications for accelerating the discovery of new therapeutic uses for existing drugs.