[Artificial Intelligence-based Drug Discovery and Drug Repositioning]

Area of Science:

• Bioinformatics
• Computational Biology
• Pharmacology

Background:

• Computational methods are crucial for accelerating drug discovery and repositioning (DR).
• Biomolecular profile information, including gene expression and network data, offers rich insights.
• Big data analytics and artificial intelligence (AI) are transforming these fields.

Purpose of the Study:

• To systematically review computational drug discovery and DR methodologies.
• To highlight approaches utilizing big data and AI for drug development.
• To provide an overview of current techniques for predicting drug effects and toxicity.

Main Methods:

• Review of gene expression profile comparison between diseased and drug-treated states for effect and toxicity prediction.
• Description of drug repositioning (DR) methods leveraging disease networks.
• Explanation of biological network analysis for predicting drug effects.
• Overview of AI-driven virtual screening and drug target exploration.

Main Results:

• Identified key computational strategies for drug discovery and DR.
• Demonstrated the utility of gene expression and network analysis in predicting drug outcomes.
• Highlighted the growing role of AI in accelerating drug discovery pipelines.

Conclusions:

• Computational approaches, particularly those using big data and AI, are essential for efficient drug discovery and repositioning.
• Biomolecular profiling and network analysis provide powerful tools for understanding drug mechanisms and predicting efficacy.
• AI-driven methods show significant promise for future drug development and target identification.