Drug repositioning based on multi-view learning with matrix completion.

Area of Science:

• Computational biology
• Bioinformatics
• Drug discovery

Background:

• Traditional drug discovery is costly and time-consuming.
• Drug repositioning offers a more efficient alternative by identifying new indications for existing drugs.
• Accurate prediction of drug-disease associations is crucial for effective drug repositioning.

Purpose of the Study:

• To develop and evaluate a novel computational method for predicting potential drug-disease associations.
• To improve the efficiency and accuracy of drug repositioning strategies.
• To facilitate the discovery of new therapeutic indications for existing drugs.

Main Methods:

• A multi-view learning with matrix completion (MLMC) approach was developed.
• MLMC integrates multiple drug and disease similarity matrices using Laplacian graph regularization.
• Matrix completion is employed to refine the drug-disease association matrix and enhance predictions.

Main Results:

• The MLMC method demonstrated higher prediction accuracy compared to existing state-of-the-art approaches.
• Evaluations using 10-fold cross-validation and de novo tests validated the method's performance.
• Case studies confirmed MLMC's capability in discovering novel drug-disease associations.

Conclusions:

• The proposed MLMC method is effective for predicting drug-disease associations.
• MLMC offers a valuable tool for accelerating drug repositioning and drug discovery.
• The method shows promise for identifying new therapeutic applications of existing drugs.