Artificial Intelligence to Guide Repurposing of Drugs

Area of Science:

• Pharmacology and Computational Biology
• Genetics and Multiomics Data Analysis
• Translational Medicine

Background:

• Drug repurposing offers a rapid strategy for developing treatments for challenging diseases, leveraging existing drug data.
• Current drug repurposing efforts are limited by the underutilization of extensive genetic and multiomics datasets.
• A gap exists in accurately applying advanced computational approaches to explore these rich biological datasets for novel therapeutic discoveries.

Purpose of the Study:

• To critically review the application of artificial intelligence (AI) and machine learning (ML) in drug repurposing.
• To explore the potential and impact of AI/ML in identifying new, affordable repurposable medicines.
• To guide geneticists, pharmacologists, and computational scientists in contributing to AI-driven drug discovery.

Main Methods:

• Review of current literature on AI and ML applications in drug repurposing.
• Discussion of AI/ML integration with genetics, multiomics data (genomics, transcriptomics, proteomics, metabolomics, radiomics), and electronic health records.
• Exploration of real-world data collection and crowdsourcing knowledge in the context of AI/ML.

Main Results:

• AI and ML can effectively analyze large-scale datasets to identify potential drug candidates for repurposing.
• These technologies facilitate the rapid identification of effective treatments for challenging diseases.
• AI/ML approaches are crucial for understanding clinically meaningful effect sizes and implications for precision medicine.

Conclusions:

• AI and ML are transformative tools for drug repurposing, enabling efficient analysis of complex biological data.
• Integrating AI/ML with diverse data sources can accelerate the discovery of inexpensive and accessible medicines.
• These methodologies hold significant promise for uniting translational medicine and developing novel treatments for challenging human diseases.