A network embedding framework based on integrating multiplex network for drug combination prediction.

Area of Science:

• Computational biology
• Pharmacology
• Network science

Background:

• Drug combinations enhance treatment efficacy and reduce side effects.
• Exhaustive screening of drug combinations is computationally prohibitive.
• Existing drug combination prediction methods lack optimal performance and scalability.

Purpose of the Study:

• To propose a novel Network Embedding frameWork in MultIplex Network (NEWMIN) for predicting synthetic drug combinations.
• To improve the performance and scalability of drug combination prediction.

Main Methods:

• Constructed a multiplex drug similarity network.
• Developed methods to integrate diverse information and weigh network importance.
• Utilized network embedding techniques for prediction.

Main Results:

• Identified seven novel drug combinations validated by external sources.
• NEWMIN demonstrated superior performance compared to five other methods.
• Achieved higher area under the precision-recall and receiver operating characteristic curves.

Conclusions:

• NEWMIN offers a promising approach for accurate and scalable drug combination prediction.
• The framework effectively integrates multi-faceted drug similarity information.
• Validated novel drug combinations warrant further investigation for therapeutic applications.