Machine Learning Applications in Drug Repurposing.

Area of Science:

• Pharmacology and Computational Biology
• Drug Discovery and Development
• Artificial Intelligence in Medicine

Background:

• Drug repurposing offers a faster, cost-effective alternative to de novo drug discovery.
• The COVID-19 pandemic highlighted the need for rapid therapeutic development through drug repurposing.
• Variable quality of evidence necessitates advanced methods for effective drug repurposing.

Purpose of the Study:

• To provide guidelines on utilizing machine learning (ML) for accelerating drug repurposing.
• To explore ML applications in precision medicine and therapeutic target identification.
• To demonstrate ML's potential in accelerating COVID-19 drug repurposing, including traditional Chinese medicine.

Main Methods:

• Leveraging large-scale machine learning algorithms and data science techniques.
• Analyzing massive observed data from existing drugs and diseases.
• Applying ML to identify therapeutic targets and predict drug efficacy.

Main Results:

• Machine learning provides state-of-the-art data analysis for drug repurposing.
• ML methods can significantly accelerate the identification of viable drug candidates.
• The study outlines strategies for employing ML in precision medicine and COVID-19 drug development.

Conclusions:

• Machine learning offers a robust framework for accelerating drug repurposing efforts.
• ML is crucial for advancing precision medicine and developing novel therapeutic strategies.
• Employing ML is highly reasonable for drug repurposing, especially during global health crises like COVID-19.